diff --git a/rpent/benchmarks/docs.css b/rpent/benchmarks/docs.css
index 6cc32b9..13684c6 100644
--- a/rpent/benchmarks/docs.css
+++ b/rpent/benchmarks/docs.css
@@ -8,3 +8,5 @@
 .rpent-static-leaderboard .table-wrap table{min-width:900px}
 html[data-theme="dark"] .rpent-static-leaderboard{--rpent-fallback-border:#494052;color:var(--pst-color-text-base,#f4f0fa)}
 .rpent-static-leaderboard .memory-context{margin:1rem 0}
+.rpent-static-leaderboard .cost-section .table-wrap table{min-width:340px}
+.rpent-static-leaderboard .cost-method small{display:block;font-size:12px;margin-top:4px}
diff --git a/rpent/benchmarks/embed.css b/rpent/benchmarks/embed.css
index ad3d14c..11170a3 100644
--- a/rpent/benchmarks/embed.css
+++ b/rpent/benchmarks/embed.css
@@ -23,8 +23,11 @@
 .legend .astra{background:var(--astra)}
 .comparison-matrix>summary{font-size:20px}
 .comparison-matrix table,.comparison-matrix .matrix-label{font-size:16px}
+.cost-section{background:var(--band);border-top:4px solid var(--best);padding:30px 0 24px}.cost-section h2{font-size:27px}.cost-group{margin-top:24px}.cost-group h3{font-size:21px}.cost-group table{font-size:16px;min-width:340px;table-layout:fixed}.cost-group th{font-size:14px;white-space:normal}.cost-group th:first-child{width:42%}.cost-group th,.cost-group td{padding:10px 8px}.cost-group td:first-child{overflow-wrap:anywhere}.cost-group .table-wrap{max-width:100%}th[aria-sort=ascending]{color:var(--best)}th[aria-sort=ascending] img{opacity:1;transform:rotate(180deg)}
+@media(max-width:700px){.cost-group table{font-size:14px}.cost-section h2{font-size:23px}.cost-group h3{font-size:19px}}
 .comparison-matrix thead th{font-size:14px}
 .comparison-matrix .matrix-label small{font-size:12px}
+.cost-group .matrix-label{font-size:inherit}.cost-group .matrix-label small,.cost-method small{display:block;font-size:12px;margin-top:4px}
 footer{background:var(--band)}
 th[aria-sort=ascending]{color:var(--best)}th[aria-sort=ascending] img{opacity:1;transform:rotate(180deg)}
 footer{max-width:none;padding-left:max(var(--gutter),calc((100% - 1344px)/2));padding-right:max(var(--gutter),calc((100% - 1344px)/2))}
diff --git a/rpent/benchmarks/embed.html b/rpent/benchmarks/embed.html
index d83cffe..7ab8ddb 100644
--- a/rpent/benchmarks/embed.html
+++ b/rpent/benchmarks/embed.html
@@ -6,10 +6,11 @@
       <div class="header-links"><a href="https://github.com/RLinf/RPent" target="_blank" rel="noopener">GitHub</a><a href="https://arxiv.org/abs/2607.08448v4" target="_blank" rel="noopener" data-i18n="paper">论文</a><button id="language" type="button" lang="en" aria-label="Switch to English">English</button></div>
     </div>
     <div class="title-row"><h1 data-i18n="title">RPent Leaderboard</h1></div>
-    <nav class="bench-nav" aria-label="Leaderboards"><a href="#libero-pro">LIBERO-PRO</a><a href="#standard-libero">LIBERO</a><a href="#robocasa">RoboCasa365</a><a href="#robotwin">RoboTwin</a></nav>
+    <nav class="bench-nav" aria-label="Leaderboards"><a href="#libero-pro">LIBERO-PRO</a><a href="#standard-libero">LIBERO</a><a href="#robocasa">RoboCasa365</a><a href="#robotwin">RoboTwin</a><a href="#time-token-costs">Time &amp; Token Costs</a></nav>
   </header>
   <main id="main">
     <div id="leaderboards"></div>
+    <section id="time-token-costs" class="cost-section"></section>
   </main>
   <footer><span>RPent Leaderboard</span><a href="#top" data-i18n="backTop">返回顶部</a></footer>
   <div id="chart-tooltip" class="chart-tooltip" role="tooltip" hidden></div>
diff --git a/rpent/benchmarks/index.html b/rpent/benchmarks/index.html
index 0f1dead..c07a1b1 100644
--- a/rpent/benchmarks/index.html
+++ b/rpent/benchmarks/index.html
@@ -7,15 +7,17 @@
       <div class="header-links"><a href="https://github.com/RLinf/RPent" target="_blank" rel="noopener">GitHub</a><a href="https://arxiv.org/abs/2607.08448v4" target="_blank" rel="noopener" data-i18n="paper">论文</a><button id="language" type="button" lang="en" aria-label="Switch to English">English</button></div>
     </div>
     <div class="title-row"><h1 data-i18n="title">RPent Leaderboard</h1></div>
-    <nav class="bench-nav" aria-label="Leaderboards"><a href="#libero-pro">LIBERO-PRO</a><a href="#standard-libero">LIBERO</a><a href="#robocasa">RoboCasa365</a><a href="#robotwin">RoboTwin</a></nav>
+    <nav class="bench-nav" aria-label="Leaderboards"><a href="#libero-pro">LIBERO-PRO</a><a href="#standard-libero">LIBERO</a><a href="#robocasa">RoboCasa365</a><a href="#robotwin">RoboTwin</a><a href="#time-token-costs">Time &amp; Token Costs</a></nav>
   </header>
   <main id="main">
     <div id="leaderboards"></div>
+    <section id="time-token-costs" class="cost-section"></section>
   </main>
   <footer><span>RPent Leaderboard</span><a href="#top" data-i18n="backTop">返回顶部</a></footer>
   <div id="chart-tooltip" class="chart-tooltip" role="tooltip" hidden></div>
   <p id="announcement" class="sr-only" aria-live="polite"></p>
-<noscript><div class="section-inner"><section data-benchmark="libero-pro"><h2>LIBERO-PRO</h2><table><thead><tr><th>方法 / 模型</th><th>成功率</th></tr></thead><tbody><tr><td>Codex / GPT-6 Astra / low / reasoning</td><td>92.63%</td></tr><tr><td>Claude Code / Opus-4.7 / max.reasoning</td><td>82.4%</td></tr><tr><td>RPent Flash Mode</td><td>72.63%</td></tr><tr><td>Codex / GPT-5.5 / xhigh / reasoning</td><td>72.1%</td></tr><tr><td>ASPIRE</td><td>61.36%</td></tr><tr><td>π_RLinf</td><td>50.0%</td></tr><tr><td>π0.5</td><td>11.0%</td></tr><tr><td>AtomVLA</td><td>6.3%</td></tr><tr><td>X-VLA</td><td>3.8%</td></tr><tr><td>MolmoAct</td><td>1.5%</td></tr><tr><td>π0</td><td>0.3%</td></tr></tbody></table><p>GPT-6 Astra: 92.63% (741/800). RPent Flash Mode / Molmo2-8B: 72.63% (581/800).</p><h3>完整方法与分项成绩</h3><div class="table-wrap" tabindex="0"><table><thead><tr><th>方法 / 模型</th><th>总体</th><th>Spatial Task</th><th>Spatial Swap</th><th>Object Task</th><th>Object Swap</th><th>Goal Task</th><th>Goal Swap</th><th>Long Task</th><th>Long Swap</th></tr></thead><tbody><tr><td>GPT-6 Astra</td><td>92.63%</td><td>100%</td><td>98%</td><td>100%</td><td>99%</td><td>88%</td><td>99%</td><td>85%</td><td>72%</td></tr><tr><td>Opus-4.7 / max.reasoning</td><td>82.4%</td><td>—</td><td>—</td><td>—</td><td>—</td><td>—</td><td>—</td><td>—</td><td>—</td></tr><tr><td>RPent Flash Mode / Molmo2-8B</td><td>72.63%</td><td>79.00%</td><td>70.00%</td><td>86.00%</td><td>93.00%</td><td>74.00%</td><td>65.00%</td><td>60.00%</td><td>54.00%</td></tr><tr><td>GPT-5.5</td><td>72.1%</td><td>81.0%</td><td>69.0%</td><td>94.0%</td><td>91.0%</td><td>75.0%</td><td>66.0%</td><td>52.0%</td><td>49.0%</td></tr><tr><td>ASPIRE</td><td>61.36%</td><td>60.0%</td><td>51.0%</td><td>95.0%</td><td>98.0%</td><td>45.0%</td><td>81.0%</td><td>38.3%</td><td>22.6%</td></tr><tr><td>π_RLinf</td><td>50.0%</td><td>42.0%</td><td>59.0%</td><td>71.0%</td><td>78.0%</td><td>45.0%</td><td>42.0%</td><td>49.0%</td><td>14.0%</td></tr><tr><td>π0.5</td><td>11.0%</td><td>1.0%</td><td>20.0%</td><td>1.0%</td><td>17.0%</td><td>2.0%</td><td>38.0%</td><td>1.0%</td><td>8.0%</td></tr><tr><td>AtomVLA</td><td>6.3%</td><td>1.0%</td><td>16.0%</td><td>0.0%</td><td>10.0%</td><td>11.0%</td><td>2.0%</td><td>9.0%</td><td>1.0%</td></tr><tr><td>X-VLA</td><td>3.8%</td><td>0.0%</td><td>0.0%</td><td>8.0%</td><td>2.0%</td><td>9.0%</td><td>1.0%</td><td>10.0%</td><td>0.0%</td></tr><tr><td>MolmoAct</td><td>1.5%</td><td>0.0%</td><td>0.0%</td><td>0.0%</td><td>6.0%</td><td>0.0%</td><td>0.0%</td><td>6.0%</td><td>0.0%</td></tr><tr><td>π0</td><td>0.3%</td><td>0.0%</td><td>0.0%</td><td>0.0%</td><td>2.0%</td><td>0.0%</td><td>0.0%</td><td>0.0%</td><td>0.0%</td></tr><tr><td>Cap-X</td><td>—</td><td>14.0%</td><td>12.0%</td><td>18.0%</td><td>22.0%</td><td>17.0%</td><td>26.0%</td><td>—</td><td>—</td></tr><tr><td>RATS</td><td>—</td><td>31.0%</td><td>29.0%</td><td>63.0%</td><td>61.0%</td><td>36.0%</td><td>43.0%</td><td>—</td><td>—</td></tr></tbody></table></div><p>ASPIRE：Long Task 和 Long Swap 使用 LIBERO-90 技能库进行 zero-shot 迁移。</p><p id="libero-pro-astra-memory" class="memory-context">GPT-6 Astra：Long Task/Swap 与其余六套件使用各自探索后冻结的 memory 文件快照，评测期间不更新。Overall 合并两个不重叠批次：Long 157/200，加上其余套件 584/600，得到 741/800（92.63%）；并非全部回合共享同一份 memory 快照。</p></section>
-<section data-benchmark="standard-libero"><h2>LIBERO</h2><table><thead><tr><th>方法 / 模型</th><th>成功率</th></tr></thead><tbody><tr><td>AtomVLA</td><td>97.0%</td></tr><tr><td>Claude Code / Opus-4.7 / max.reasoning</td><td>96.0%</td></tr><tr><td>π_RLinf</td><td>95.3%</td></tr><tr><td>π0</td><td>94.2%</td></tr><tr><td>NORA</td><td>79.5%</td></tr><tr><td>OpenVLA</td><td>76.5%</td></tr></tbody></table></section>
-<section data-benchmark="robocasa"><h2>RoboCasa365 · Target50</h2><table><thead><tr><th>方法 / 模型</th><th>成功率</th></tr></thead><tbody><tr><td>Codex / GPT-6 Astra / low / reasoning</td><td>59.20%</td></tr><tr><td>Xiaomi-Robotics-1</td><td>57.4%</td></tr><tr><td>Codex / GPT-5.5 / xhigh / reasoning</td><td>57.1%</td></tr><tr><td>Claude Code / Opus-4.7 / max.reasoning</td><td>48.6%</td></tr><tr><td>WorldDreamer</td><td>35.3%</td></tr><tr><td>RLDX-1</td><td>30.0%</td></tr><tr><td>π0.5</td><td>16.9%</td></tr><tr><td>π0</td><td>14.8%</td></tr></tbody></table><h3>RoboCasa365 · Target50 · 完整方法与分项成绩</h3><div class="table-wrap" tabindex="0"><table><thead><tr><th>方法 / 模型</th><th>总体</th><th>Atomic-Seen</th><th>Composite-Seen</th><th>Composite-Unseen</th></tr></thead><tbody><tr><td>GPT-6 Astra</td><td>59.20%</td><td>87.78%</td><td>43.75%</td><td>42.50%</td></tr><tr><td>Xiaomi-Robotics-1</td><td>57.4%</td><td>80.2%</td><td>57.1%</td><td>32.1%</td></tr><tr><td>GPT-5.5</td><td>57.1%</td><td>92.0%</td><td>61.0%</td><td>13.8%</td></tr><tr><td>Opus-4.7 / max.reasoning</td><td>48.6%</td><td>79.4%</td><td>47.5%</td><td>15.0%</td></tr><tr><td>WorldDreamer</td><td>35.3%</td><td>66.3%</td><td>26.7%</td><td>9.0%</td></tr><tr><td>RLDX-1</td><td>30.0%</td><td>60.0%</td><td>21.3%</td><td>5.0%</td></tr><tr><td>π0.5</td><td>16.9%</td><td>39.6%</td><td>7.1%</td><td>1.2%</td></tr><tr><td>π0</td><td>14.8%</td><td>34.6%</td><td>6.1%</td><td>1.1%</td></tr></tbody></table></div></section>
-<section data-benchmark="robotwin"><h2>RoboTwin</h2><table><thead><tr><th>方法 / 模型</th><th>成功率</th></tr></thead><tbody><tr><td>Codex / GPT-5.5 / xhigh / reasoning</td><td>62.4%</td></tr><tr><td>Claude Code / Opus-4.7 / max.reasoning</td><td>58.4%</td></tr><tr><td>LingBot-VLA</td><td>50.4%</td></tr><tr><td>π0.5</td><td>47.9%</td></tr><tr><td>GR00T-N1.7</td><td>20.7%</td></tr><tr><td>StarVLA</td><td>10.6%</td></tr></tbody></table></section></div></noscript><script id="results-data" type="application/json">{"schema_version":2,"checked_at":"2026-09-17","paper_revision":"2607.08448v4","repository_revision":"43f32aa08cba07bd4d49a4bfa5eba4ef633e9b92","configurations":[{"id":"gpt-5-5-xhigh","kind":"rpent","backend":"Codex","model":"GPT-5.5","reasoning":true,"effort":"xhigh"},{"id":"opus-4-7-max","kind":"rpent","backend":"Claude Code","model":"Opus-4.7","reasoning":true,"effort":"max"},{"id":"gpt-6-astra-low","kind":"rpent","backend":"Codex","model":"GPT-6 Astra","reasoning":true,"effort":"low"},{"id":"openvla","kind":"external","backend":null,"model":"OpenVLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"nora","kind":"external","backend":null,"model":"NORA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"pi0","kind":"external","backend":null,"model":"π0","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"pi-rlinf","kind":"external","backend":null,"model":"π_RLinf","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"atomvla","kind":"external","backend":null,"model":"AtomVLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"pi0-5","kind":"external","backend":null,"model":"π0.5","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"molmoact","kind":"external","backend":null,"model":"MolmoAct","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"x-vla","kind":"external","backend":null,"model":"X-VLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"cap-x","kind":"external","backend":null,"model":"Cap-X","reasoning":null,"effort":null,"metadata_status":"not_reported"},{"id":"rats","kind":"external","backend":null,"model":"RATS","reasoning":null,"effort":null,"metadata_status":"not_reported"},{"id":"rldx-1","kind":"external","backend":null,"model":"RLDX-1","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"worlddreamer","kind":"external","backend":null,"model":"WorldDreamer","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"gr00t-n1-7","kind":"external","backend":null,"model":"GR00T-N1.7","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"starvla","kind":"external","backend":null,"model":"StarVLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"lingbot-vla","kind":"external","backend":null,"model":"LingBot-VLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"opus-4-7-reported","kind":"rpent","backend":"Claude Code","model":"Opus-4.7","reasoning":true,"effort":"max"},{"id":"rpent-flash-mode","kind":"rpent","backend":null,"model":null,"reasoning":null,"effort":null,"display_name":"RPent Flash Mode","perception_model":"Molmo2-8B"},{"id":"xiaomi-robotics-1","kind":"external","backend":null,"model":"Xiaomi-Robotics-1","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"aspire","kind":"external","backend":null,"model":"ASPIRE","reasoning":null,"effort":null}],"views":[{"id":"standard-spatial","benchmark_id":"standard-libero","label":{"en":"Spatial","zh":"Spatial"},"record_ids":["standard-spatial--opus-4-7-max","standard-spatial--openvla","standard-spatial--nora","standard-spatial--pi0","standard-spatial--pi-rlinf","standard-spatial--atomvla"]},{"id":"standard-object","benchmark_id":"standard-libero","label":{"en":"Object","zh":"Object"},"record_ids":["standard-object--opus-4-7-max","standard-object--openvla","standard-object--nora","standard-object--pi0","standard-object--pi-rlinf","standard-object--atomvla"]},{"id":"standard-goal","benchmark_id":"standard-libero","label":{"en":"Goal","zh":"Goal"},"record_ids":["standard-goal--opus-4-7-max","standard-goal--openvla","standard-goal--nora","standard-goal--pi0","standard-goal--pi-rlinf","standard-goal--atomvla"]},{"id":"standard-long","benchmark_id":"standard-libero","label":{"en":"Long","zh":"Long"},"record_ids":["standard-long--opus-4-7-max","standard-long--openvla","standard-long--nora","standard-long--pi0","standard-long--pi-rlinf","standard-long--atomvla"]},{"id":"standard-libero","benchmark_id":"standard-libero","label":{"en":"Overall","zh":"总体"},"record_ids":["standard-libero--opus-4-7-max","standard-libero--openvla","standard-libero--nora","standard-libero--pi0","standard-libero--pi-rlinf","standard-libero--atomvla"]},{"id":"spatial-task","benchmark_id":"libero-pro","label":{"en":"Spatial Task","zh":"Spatial Task"},"record_ids":["spatial-task--gpt-5-5-xhigh","spatial-task--gpt-6-astra-low","spatial-task--pi0","spatial-task--pi0-5","spatial-task--molmoact","spatial-task--x-vla","spatial-task--atomvla","spatial-task--cap-x","spatial-task--rats","spatial-task--pi-rlinf","spatial-task--aspire","spatial-task--rpent-flash-mode"]},{"id":"spatial-swap","benchmark_id":"libero-pro","label":{"en":"Spatial Swap","zh":"Spatial Swap"},"record_ids":["spatial-swap--gpt-5-5-xhigh","spatial-swap--gpt-6-astra-low","spatial-swap--pi0","spatial-swap--pi0-5","spatial-swap--molmoact","spatial-swap--x-vla","spatial-swap--atomvla","spatial-swap--cap-x","spatial-swap--rats","spatial-swap--pi-rlinf","spatial-swap--aspire","spatial-swap--rpent-flash-mode"]},{"id":"object-task","benchmark_id":"libero-pro","label":{"en":"Object Task","zh":"Object Task"},"record_ids":["object-task--gpt-5-5-xhigh","object-task--gpt-6-astra-low","object-task--pi0","object-task--pi0-5","object-task--molmoact","object-task--x-vla","object-task--atomvla","object-task--cap-x","object-task--rats","object-task--pi-rlinf","object-task--aspire","object-task--rpent-flash-mode"]},{"id":"object-swap","benchmark_id":"libero-pro","label":{"en":"Object Swap","zh":"Object Swap"},"record_ids":["object-swap--gpt-5-5-xhigh","object-swap--gpt-6-astra-low","object-swap--pi0","object-swap--pi0-5","object-swap--molmoact","object-swap--x-vla","object-swap--atomvla","object-swap--cap-x","object-swap--rats","object-swap--pi-rlinf","object-swap--aspire","object-swap--rpent-flash-mode"]},{"id":"goal-task","benchmark_id":"libero-pro","label":{"en":"Goal Task","zh":"Goal Task"},"record_ids":["goal-task--gpt-5-5-xhigh","goal-task--gpt-6-astra-low","goal-task--pi0","goal-task--pi0-5","goal-task--molmoact","goal-task--x-vla","goal-task--atomvla","goal-task--cap-x","goal-task--rats","goal-task--pi-rlinf","goal-task--aspire","goal-task--rpent-flash-mode"]},{"id":"goal-swap","benchmark_id":"libero-pro","label":{"en":"Goal Swap","zh":"Goal Swap"},"record_ids":["goal-swap--gpt-5-5-xhigh","goal-swap--gpt-6-astra-low","goal-swap--pi0","goal-swap--pi0-5","goal-swap--molmoact","goal-swap--x-vla","goal-swap--atomvla","goal-swap--cap-x","goal-swap--rats","goal-swap--pi-rlinf","goal-swap--aspire","goal-swap--rpent-flash-mode"]},{"id":"long-task","benchmark_id":"libero-pro","label":{"en":"Long Task","zh":"Long Task"},"record_ids":["long-task--gpt-5-5-xhigh","long-task--gpt-6-astra-low","long-task--pi0","long-task--pi0-5","long-task--molmoact","long-task--x-vla","long-task--atomvla","long-task--pi-rlinf","long-task--aspire","long-task--rpent-flash-mode"]},{"id":"long-swap","benchmark_id":"libero-pro","label":{"en":"Long Swap","zh":"Long Swap"},"record_ids":["long-swap--gpt-5-5-xhigh","long-swap--gpt-6-astra-low","long-swap--pi0","long-swap--pi0-5","long-swap--molmoact","long-swap--x-vla","long-swap--atomvla","long-swap--pi-rlinf","long-swap--aspire","long-swap--rpent-flash-mode"]},{"id":"libero-pro","benchmark_id":"libero-pro","label":{"en":"Overall","zh":"总体"},"record_ids":["libero-pro--gpt-5-5-xhigh","libero-pro--gpt-6-astra-low","libero-pro--pi0","libero-pro--pi0-5","libero-pro--molmoact","libero-pro--x-vla","libero-pro--atomvla","libero-pro--pi-rlinf","libero-pro--opus-4-7-reported","libero-pro--rpent-flash-mode","libero-pro--aspire"]},{"id":"robocasa-atomic-seen","benchmark_id":"robocasa","label":{"en":"Atomic-Seen","zh":"Atomic-Seen"},"record_ids":["robocasa-atomic-seen--gpt-5-5-xhigh","robocasa-atomic-seen--opus-4-7-max","robocasa-atomic-seen--rldx-1","robocasa-atomic-seen--worlddreamer","robocasa-atomic-seen--pi0-5","robocasa-atomic-seen--pi0","robocasa-atomic-seen--xiaomi-robotics-1","robocasa-atomic-seen--gpt-6-astra-low"]},{"id":"robocasa-composite-seen","benchmark_id":"robocasa","label":{"en":"Composite-Seen","zh":"Composite-Seen"},"record_ids":["robocasa-composite-seen--gpt-5-5-xhigh","robocasa-composite-seen--opus-4-7-max","robocasa-composite-seen--rldx-1","robocasa-composite-seen--worlddreamer","robocasa-composite-seen--pi0-5","robocasa-composite-seen--pi0","robocasa-composite-seen--xiaomi-robotics-1","robocasa-composite-seen--gpt-6-astra-low"]},{"id":"robocasa-composite-unseen","benchmark_id":"robocasa","label":{"en":"Composite-Unseen","zh":"Composite-Unseen"},"record_ids":["robocasa-composite-unseen--gpt-5-5-xhigh","robocasa-composite-unseen--opus-4-7-max","robocasa-composite-unseen--rldx-1","robocasa-composite-unseen--worlddreamer","robocasa-composite-unseen--pi0-5","robocasa-composite-unseen--pi0","robocasa-composite-unseen--xiaomi-robotics-1","robocasa-composite-unseen--gpt-6-astra-low"]},{"id":"robocasa","benchmark_id":"robocasa","label":{"en":"Overall","zh":"总体"},"record_ids":["robocasa--gpt-5-5-xhigh","robocasa--opus-4-7-max","robocasa--rldx-1","robocasa--worlddreamer","robocasa--pi0-5","robocasa--pi0","robocasa--gpt-6-astra-reported","robocasa--xiaomi-robotics-1"]},{"id":"robotwin","benchmark_id":"robotwin","label":{"en":"C2R","zh":"C2R"},"record_ids":["robotwin--opus-4-7-max","robotwin--gr00t-n1-7","robotwin--pi0-5","robotwin--starvla","robotwin--lingbot-vla","robotwin--gpt-5-5-xhigh"]}],"results":[{"id":"standard-spatial--opus-4-7-max","view_id":"standard-spatial","configuration_id":"opus-4-7-max","status":"reported","rate":"97.0","successes":null,"episodes":100,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"standard-object--opus-4-7-max","view_id":"standard-object","configuration_id":"opus-4-7-max","status":"reported","rate":"100.0","successes":null,"episodes":100,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"standard-goal--opus-4-7-max","view_id":"standard-goal","configuration_id":"opus-4-7-max","status":"reported","rate":"94.0","successes":null,"episodes":100,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"standard-long--opus-4-7-max","view_id":"standard-long","configuration_id":"opus-4-7-max","status":"reported","rate":"93.0","successes":null,"episodes":100,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"standard-libero--opus-4-7-max","view_id":"standard-libero","configuration_id":"opus-4-7-max","status":"reported","rate":"96.0","successes":384,"episodes":400,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"spatial-task--gpt-5-5-xhigh","view_id":"spatial-task","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"81.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"spatial-task--gpt-6-astra-low","view_id":"spatial-task","configuration_id":"gpt-6-astra-low","status":"reported","rate":"100","successes":100,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"spatial-swap--gpt-5-5-xhigh","view_id":"spatial-swap","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"69.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"spatial-swap--gpt-6-astra-low","view_id":"spatial-swap","configuration_id":"gpt-6-astra-low","status":"reported","rate":"98","successes":98,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"object-task--gpt-5-5-xhigh","view_id":"object-task","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"94.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"object-task--gpt-6-astra-low","view_id":"object-task","configuration_id":"gpt-6-astra-low","status":"reported","rate":"100","successes":100,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"object-swap--gpt-5-5-xhigh","view_id":"object-swap","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"91.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"object-swap--gpt-6-astra-low","view_id":"object-swap","configuration_id":"gpt-6-astra-low","status":"reported","rate":"99","successes":99,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"goal-task--gpt-5-5-xhigh","view_id":"goal-task","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"75.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"goal-task--gpt-6-astra-low","view_id":"goal-task","configuration_id":"gpt-6-astra-low","status":"reported","rate":"88","successes":88,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"goal-swap--gpt-5-5-xhigh","view_id":"goal-swap","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"66.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"goal-swap--gpt-6-astra-low","view_id":"goal-swap","configuration_id":"gpt-6-astra-low","status":"reported","rate":"99","successes":99,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"long-task--gpt-5-5-xhigh","view_id":"long-task","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"52.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"long-task--gpt-6-astra-low","view_id":"long-task","configuration_id":"gpt-6-astra-low","status":"reported","rate":"85","successes":85,"episodes":100,"source_ids":["astra-long-20260907","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-long"},{"id":"long-swap--gpt-5-5-xhigh","view_id":"long-swap","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"49.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"long-swap--gpt-6-astra-low","view_id":"long-swap","configuration_id":"gpt-6-astra-low","status":"reported","rate":"72","successes":72,"episodes":100,"source_ids":["astra-long-20260907","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-long"},{"id":"libero-pro--gpt-5-5-xhigh","view_id":"libero-pro","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"72.1","successes":null,"episodes":800,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"libero-pro--gpt-6-astra-low","view_id":"libero-pro","configuration_id":"gpt-6-astra-low","status":"reported","rate":"92.63","successes":741,"episodes":800,"source_ids":["astra-long-20260907","astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-mixed-batches"},{"id":"robocasa-atomic-seen--gpt-5-5-xhigh","view_id":"robocasa-atomic-seen","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"92.0","successes":null,"episodes":180,"source_ids":["paper-table-4"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-atomic-seen--opus-4-7-max","view_id":"robocasa-atomic-seen","configuration_id":"opus-4-7-max","status":"reported","rate":"79.4","successes":null,"episodes":180,"source_ids":["paper-table-4","contributor-correction-20260916"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-composite-seen--gpt-5-5-xhigh","view_id":"robocasa-composite-seen","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"61.0","successes":null,"episodes":80,"source_ids":["paper-table-4"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-composite-seen--opus-4-7-max","view_id":"robocasa-composite-seen","configuration_id":"opus-4-7-max","status":"reported","rate":"47.5","successes":null,"episodes":80,"source_ids":["paper-table-4","contributor-correction-20260916"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-composite-unseen--gpt-5-5-xhigh","view_id":"robocasa-composite-unseen","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"13.8","successes":null,"episodes":80,"source_ids":["paper-table-4"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-composite-unseen--opus-4-7-max","view_id":"robocasa-composite-unseen","configuration_id":"opus-4-7-max","status":"reported","rate":"15.0","successes":null,"episodes":80,"source_ids":["paper-table-4","contributor-correction-20260916"],"protocol_id":"rpent-robocasa"},{"id":"robocasa--gpt-5-5-xhigh","view_id":"robocasa","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"57.1","successes":null,"episodes":340,"source_ids":["paper-table-4"],"protocol_id":"rpent-robocasa"},{"id":"robocasa--opus-4-7-max","view_id":"robocasa","configuration_id":"opus-4-7-max","status":"reported","rate":"48.6","successes":null,"episodes":340,"source_ids":["paper-table-4","contributor-correction-20260916"],"protocol_id":"rpent-robocasa"},{"id":"robotwin--opus-4-7-max","view_id":"robotwin","configuration_id":"opus-4-7-max","status":"reported","rate":"58.4","successes":null,"episodes":250,"source_ids":["paper-table-6","contributor-correction-20260916"],"protocol_id":"rpent-robotwin"},{"id":"standard-libero--openvla","view_id":"standard-libero","configuration_id":"openvla","status":"reported","rate":"76.5","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-libero--nora","view_id":"standard-libero","configuration_id":"nora","status":"reported","rate":"79.5","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-libero--pi0","view_id":"standard-libero","configuration_id":"pi0","status":"reported","rate":"94.2","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-libero--pi-rlinf","view_id":"standard-libero","configuration_id":"pi-rlinf","status":"reported","rate":"95.3","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-libero--atomvla","view_id":"standard-libero","configuration_id":"atomvla","status":"reported","rate":"97.0","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"libero-pro--pi0","view_id":"libero-pro","configuration_id":"pi0","status":"reported","rate":"0.3","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--pi0-5","view_id":"libero-pro","configuration_id":"pi0-5","status":"reported","rate":"11.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--molmoact","view_id":"libero-pro","configuration_id":"molmoact","status":"reported","rate":"1.5","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--x-vla","view_id":"libero-pro","configuration_id":"x-vla","status":"reported","rate":"3.8","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--atomvla","view_id":"libero-pro","configuration_id":"atomvla","status":"reported","rate":"6.3","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--pi-rlinf","view_id":"libero-pro","configuration_id":"pi-rlinf","status":"reported","rate":"50.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"robocasa--rldx-1","view_id":"robocasa","configuration_id":"rldx-1","status":"reported","rate":"30.0","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa--worlddreamer","view_id":"robocasa","configuration_id":"worlddreamer","status":"reported","rate":"35.3","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa--pi0-5","view_id":"robocasa","configuration_id":"pi0-5","status":"reported","rate":"16.9","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa--pi0","view_id":"robocasa","configuration_id":"pi0","status":"reported","rate":"14.8","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robotwin--gr00t-n1-7","view_id":"robotwin","configuration_id":"gr00t-n1-7","status":"reported","rate":"20.7","successes":null,"episodes":null,"source_ids":["paper-table-6"],"protocol_id":"external-robotwin"},{"id":"robotwin--pi0-5","view_id":"robotwin","configuration_id":"pi0-5","status":"reported","rate":"47.9","successes":null,"episodes":null,"source_ids":["paper-table-6"],"protocol_id":"external-robotwin"},{"id":"robotwin--starvla","view_id":"robotwin","configuration_id":"starvla","status":"reported","rate":"10.6","successes":null,"episodes":null,"source_ids":["paper-table-6"],"protocol_id":"external-robotwin"},{"id":"robotwin--lingbot-vla","view_id":"robotwin","configuration_id":"lingbot-vla","status":"reported","rate":"50.4","successes":null,"episodes":null,"source_ids":["paper-table-6"],"protocol_id":"external-robotwin"},{"id":"standard-spatial--openvla","view_id":"standard-spatial","configuration_id":"openvla","status":"reported","rate":"84.7","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--openvla","view_id":"standard-object","configuration_id":"openvla","status":"reported","rate":"88.4","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--openvla","view_id":"standard-goal","configuration_id":"openvla","status":"reported","rate":"79.2","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--openvla","view_id":"standard-long","configuration_id":"openvla","status":"reported","rate":"53.7","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-spatial--nora","view_id":"standard-spatial","configuration_id":"nora","status":"reported","rate":"85.6","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--nora","view_id":"standard-object","configuration_id":"nora","status":"reported","rate":"89.4","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--nora","view_id":"standard-goal","configuration_id":"nora","status":"reported","rate":"80.0","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--nora","view_id":"standard-long","configuration_id":"nora","status":"reported","rate":"63.0","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-spatial--pi0","view_id":"standard-spatial","configuration_id":"pi0","status":"reported","rate":"96.8","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--pi0","view_id":"standard-object","configuration_id":"pi0","status":"reported","rate":"98.8","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--pi0","view_id":"standard-goal","configuration_id":"pi0","status":"reported","rate":"95.8","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--pi0","view_id":"standard-long","configuration_id":"pi0","status":"reported","rate":"85.2","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-spatial--pi-rlinf","view_id":"standard-spatial","configuration_id":"pi-rlinf","status":"reported","rate":"99.0","successes":null,"episodes":100,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--pi-rlinf","view_id":"standard-object","configuration_id":"pi-rlinf","status":"reported","rate":"96.0","successes":null,"episodes":100,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--pi-rlinf","view_id":"standard-goal","configuration_id":"pi-rlinf","status":"reported","rate":"97.0","successes":null,"episodes":100,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--pi-rlinf","view_id":"standard-long","configuration_id":"pi-rlinf","status":"reported","rate":"89.0","successes":null,"episodes":100,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-spatial--atomvla","view_id":"standard-spatial","configuration_id":"atomvla","status":"reported","rate":"96.4","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--atomvla","view_id":"standard-object","configuration_id":"atomvla","status":"reported","rate":"99.6","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--atomvla","view_id":"standard-goal","configuration_id":"atomvla","status":"reported","rate":"97.6","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--atomvla","view_id":"standard-long","configuration_id":"atomvla","status":"reported","rate":"94.4","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"spatial-task--pi0","view_id":"spatial-task","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--pi0","view_id":"spatial-swap","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--pi0","view_id":"object-task","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--pi0","view_id":"object-swap","configuration_id":"pi0","status":"reported","rate":"2.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--pi0","view_id":"goal-task","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--pi0","view_id":"goal-swap","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--pi0","view_id":"long-task","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--pi0","view_id":"long-swap","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--pi0-5","view_id":"spatial-task","configuration_id":"pi0-5","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--pi0-5","view_id":"spatial-swap","configuration_id":"pi0-5","status":"reported","rate":"20.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--pi0-5","view_id":"object-task","configuration_id":"pi0-5","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--pi0-5","view_id":"object-swap","configuration_id":"pi0-5","status":"reported","rate":"17.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--pi0-5","view_id":"goal-task","configuration_id":"pi0-5","status":"reported","rate":"2.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--pi0-5","view_id":"goal-swap","configuration_id":"pi0-5","status":"reported","rate":"38.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--pi0-5","view_id":"long-task","configuration_id":"pi0-5","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--pi0-5","view_id":"long-swap","configuration_id":"pi0-5","status":"reported","rate":"8.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--molmoact","view_id":"spatial-task","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--molmoact","view_id":"spatial-swap","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--molmoact","view_id":"object-task","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--molmoact","view_id":"object-swap","configuration_id":"molmoact","status":"reported","rate":"6.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--molmoact","view_id":"goal-task","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--molmoact","view_id":"goal-swap","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--molmoact","view_id":"long-task","configuration_id":"molmoact","status":"reported","rate":"6.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--molmoact","view_id":"long-swap","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--x-vla","view_id":"spatial-task","configuration_id":"x-vla","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--x-vla","view_id":"spatial-swap","configuration_id":"x-vla","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--x-vla","view_id":"object-task","configuration_id":"x-vla","status":"reported","rate":"8.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--x-vla","view_id":"object-swap","configuration_id":"x-vla","status":"reported","rate":"2.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--x-vla","view_id":"goal-task","configuration_id":"x-vla","status":"reported","rate":"9.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--x-vla","view_id":"goal-swap","configuration_id":"x-vla","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--x-vla","view_id":"long-task","configuration_id":"x-vla","status":"reported","rate":"10.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--x-vla","view_id":"long-swap","configuration_id":"x-vla","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--atomvla","view_id":"spatial-task","configuration_id":"atomvla","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--atomvla","view_id":"spatial-swap","configuration_id":"atomvla","status":"reported","rate":"16.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--atomvla","view_id":"object-task","configuration_id":"atomvla","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--atomvla","view_id":"object-swap","configuration_id":"atomvla","status":"reported","rate":"10.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--atomvla","view_id":"goal-task","configuration_id":"atomvla","status":"reported","rate":"11.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--atomvla","view_id":"goal-swap","configuration_id":"atomvla","status":"reported","rate":"2.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--atomvla","view_id":"long-task","configuration_id":"atomvla","status":"reported","rate":"9.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--atomvla","view_id":"long-swap","configuration_id":"atomvla","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--cap-x","view_id":"spatial-task","configuration_id":"cap-x","status":"reported","rate":"14.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--cap-x","view_id":"spatial-swap","configuration_id":"cap-x","status":"reported","rate":"12.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--cap-x","view_id":"object-task","configuration_id":"cap-x","status":"reported","rate":"18.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--cap-x","view_id":"object-swap","configuration_id":"cap-x","status":"reported","rate":"22.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--cap-x","view_id":"goal-task","configuration_id":"cap-x","status":"reported","rate":"17.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--cap-x","view_id":"goal-swap","configuration_id":"cap-x","status":"reported","rate":"26.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--rats","view_id":"spatial-task","configuration_id":"rats","status":"reported","rate":"31.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--rats","view_id":"spatial-swap","configuration_id":"rats","status":"reported","rate":"29.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--rats","view_id":"object-task","configuration_id":"rats","status":"reported","rate":"63.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--rats","view_id":"object-swap","configuration_id":"rats","status":"reported","rate":"61.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--rats","view_id":"goal-task","configuration_id":"rats","status":"reported","rate":"36.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--rats","view_id":"goal-swap","configuration_id":"rats","status":"reported","rate":"43.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--pi-rlinf","view_id":"spatial-task","configuration_id":"pi-rlinf","status":"reported","rate":"42.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--pi-rlinf","view_id":"spatial-swap","configuration_id":"pi-rlinf","status":"reported","rate":"59.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--pi-rlinf","view_id":"object-task","configuration_id":"pi-rlinf","status":"reported","rate":"71.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--pi-rlinf","view_id":"object-swap","configuration_id":"pi-rlinf","status":"reported","rate":"78.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--pi-rlinf","view_id":"goal-task","configuration_id":"pi-rlinf","status":"reported","rate":"45.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--pi-rlinf","view_id":"goal-swap","configuration_id":"pi-rlinf","status":"reported","rate":"42.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--pi-rlinf","view_id":"long-task","configuration_id":"pi-rlinf","status":"reported","rate":"49.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--pi-rlinf","view_id":"long-swap","configuration_id":"pi-rlinf","status":"reported","rate":"14.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"robocasa-atomic-seen--rldx-1","view_id":"robocasa-atomic-seen","configuration_id":"rldx-1","status":"reported","rate":"60.0","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-seen--rldx-1","view_id":"robocasa-composite-seen","configuration_id":"rldx-1","status":"reported","rate":"21.3","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-unseen--rldx-1","view_id":"robocasa-composite-unseen","configuration_id":"rldx-1","status":"reported","rate":"5.0","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-atomic-seen--worlddreamer","view_id":"robocasa-atomic-seen","configuration_id":"worlddreamer","status":"reported","rate":"66.3","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-seen--worlddreamer","view_id":"robocasa-composite-seen","configuration_id":"worlddreamer","status":"reported","rate":"26.7","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-unseen--worlddreamer","view_id":"robocasa-composite-unseen","configuration_id":"worlddreamer","status":"reported","rate":"9.0","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-atomic-seen--pi0-5","view_id":"robocasa-atomic-seen","configuration_id":"pi0-5","status":"reported","rate":"39.6","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-seen--pi0-5","view_id":"robocasa-composite-seen","configuration_id":"pi0-5","status":"reported","rate":"7.1","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-unseen--pi0-5","view_id":"robocasa-composite-unseen","configuration_id":"pi0-5","status":"reported","rate":"1.2","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-atomic-seen--pi0","view_id":"robocasa-atomic-seen","configuration_id":"pi0","status":"reported","rate":"34.6","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-seen--pi0","view_id":"robocasa-composite-seen","configuration_id":"pi0","status":"reported","rate":"6.1","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-unseen--pi0","view_id":"robocasa-composite-unseen","configuration_id":"pi0","status":"reported","rate":"1.1","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"libero-pro--opus-4-7-reported","view_id":"libero-pro","configuration_id":"opus-4-7-reported","status":"reported","rate":"82.4","successes":null,"episodes":800,"source_ids":["contributor-correction-20260916"],"protocol_id":"contributor-pro-eight"},{"id":"libero-pro--rpent-flash-mode","view_id":"libero-pro","configuration_id":"rpent-flash-mode","status":"reported","rate":"72.63","successes":581,"episodes":800,"source_ids":["repo-flash-mode-800","flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"robocasa--gpt-6-astra-reported","view_id":"robocasa","configuration_id":"gpt-6-astra-low","status":"reported","rate":"59.20","successes":148,"episodes":250,"source_ids":["contributor-20260915","contributor-settings-20260915","robocasa-astra-contributor-250-outcomes"],"protocol_id":"contributor-target50-astra-five-seed"},{"id":"robotwin--gpt-5-5-xhigh","view_id":"robotwin","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"62.4","successes":156,"episodes":250,"source_ids":["repo-robotwin-20260915"],"protocol_id":"repo-robotwin-20260915","task_failures":58,"episode_timeouts":36},{"id":"robocasa--xiaomi-robotics-1","view_id":"robocasa","configuration_id":"xiaomi-robotics-1","status":"reported","rate":"57.4","successes":null,"episodes":null,"source_ids":["xiaomi-official-robocasa365","xiaomi-paper-v2-table-3"],"protocol_id":"xiaomi-official-robocasa365"},{"id":"robocasa-atomic-seen--xiaomi-robotics-1","view_id":"robocasa-atomic-seen","configuration_id":"xiaomi-robotics-1","status":"reported","rate":"80.2","successes":null,"episodes":null,"source_ids":["xiaomi-official-robocasa365","xiaomi-paper-v2-table-3"],"protocol_id":"xiaomi-official-robocasa365"},{"id":"robocasa-composite-seen--xiaomi-robotics-1","view_id":"robocasa-composite-seen","configuration_id":"xiaomi-robotics-1","status":"reported","rate":"57.1","successes":null,"episodes":null,"source_ids":["xiaomi-official-robocasa365","xiaomi-paper-v2-table-3"],"protocol_id":"xiaomi-official-robocasa365"},{"id":"robocasa-composite-unseen--xiaomi-robotics-1","view_id":"robocasa-composite-unseen","configuration_id":"xiaomi-robotics-1","status":"reported","rate":"32.1","successes":null,"episodes":null,"source_ids":["xiaomi-official-robocasa365","xiaomi-paper-v2-table-3"],"protocol_id":"xiaomi-official-robocasa365"},{"id":"spatial-task--aspire","view_id":"spatial-task","configuration_id":"aspire","status":"reported","rate":"60.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"spatial-swap--aspire","view_id":"spatial-swap","configuration_id":"aspire","status":"reported","rate":"51.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"object-task--aspire","view_id":"object-task","configuration_id":"aspire","status":"reported","rate":"95.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"object-swap--aspire","view_id":"object-swap","configuration_id":"aspire","status":"reported","rate":"98.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"goal-task--aspire","view_id":"goal-task","configuration_id":"aspire","status":"reported","rate":"45.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"goal-swap--aspire","view_id":"goal-swap","configuration_id":"aspire","status":"reported","rate":"81.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"long-task--aspire","view_id":"long-task","configuration_id":"aspire","status":"reported","rate":"38.3","successes":null,"episodes":500,"source_ids":["aspire-table-5"],"protocol_id":"aspire-libero90-zero-shot","evaluation_note":{"en":"Long zero-shot transfer (LIBERO-90 library)","zh":"Long 零样本迁移（LIBERO-90 技能库）"}},{"id":"long-swap--aspire","view_id":"long-swap","configuration_id":"aspire","status":"reported","rate":"22.6","successes":null,"episodes":500,"source_ids":["aspire-table-5"],"protocol_id":"aspire-libero90-zero-shot","evaluation_note":{"en":"Long zero-shot transfer (LIBERO-90 library)","zh":"Long 零样本迁移（LIBERO-90 技能库）"}},{"id":"libero-pro--aspire","view_id":"libero-pro","configuration_id":"aspire","status":"derived","rate":"61.36","successes":null,"episodes":null,"source_ids":["aspire-table-2","aspire-table-5"],"protocol_id":"aspire-eight-component-mean","derived_from":["spatial-task--aspire","spatial-swap--aspire","object-task--aspire","object-swap--aspire","goal-task--aspire","goal-swap--aspire","long-task--aspire","long-swap--aspire"],"calculation":"Unweighted arithmetic mean of the eight displayed percentages; six main-suite and two Long zero-shot results.","evaluation_note":{"en":"Eight-score arithmetic mean","zh":"八项算术平均"}},{"id":"spatial-task--rpent-flash-mode","view_id":"spatial-task","configuration_id":"rpent-flash-mode","status":"reported","rate":"79.00","successes":79,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"spatial-swap--rpent-flash-mode","view_id":"spatial-swap","configuration_id":"rpent-flash-mode","status":"reported","rate":"70.00","successes":70,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"object-task--rpent-flash-mode","view_id":"object-task","configuration_id":"rpent-flash-mode","status":"reported","rate":"86.00","successes":86,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"object-swap--rpent-flash-mode","view_id":"object-swap","configuration_id":"rpent-flash-mode","status":"reported","rate":"93.00","successes":93,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"goal-task--rpent-flash-mode","view_id":"goal-task","configuration_id":"rpent-flash-mode","status":"reported","rate":"74.00","successes":74,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"goal-swap--rpent-flash-mode","view_id":"goal-swap","configuration_id":"rpent-flash-mode","status":"reported","rate":"65.00","successes":65,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"long-task--rpent-flash-mode","view_id":"long-task","configuration_id":"rpent-flash-mode","status":"reported","rate":"60.00","successes":60,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"long-swap--rpent-flash-mode","view_id":"long-swap","configuration_id":"rpent-flash-mode","status":"reported","rate":"54.00","successes":54,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"robocasa-atomic-seen--gpt-6-astra-low","view_id":"robocasa-atomic-seen","configuration_id":"gpt-6-astra-low","status":"reported","rate":"87.78","successes":79,"episodes":90,"source_ids":["robocasa-astra-contributor-250-outcomes","contributor-settings-20260915"],"protocol_id":"contributor-target50-astra-five-seed"},{"id":"robocasa-composite-seen--gpt-6-astra-low","view_id":"robocasa-composite-seen","configuration_id":"gpt-6-astra-low","status":"reported","rate":"43.75","successes":35,"episodes":80,"source_ids":["robocasa-astra-contributor-250-outcomes","contributor-settings-20260915"],"protocol_id":"contributor-target50-astra-five-seed"},{"id":"robocasa-composite-unseen--gpt-6-astra-low","view_id":"robocasa-composite-unseen","configuration_id":"gpt-6-astra-low","status":"reported","rate":"42.50","successes":34,"episodes":80,"source_ids":["robocasa-astra-contributor-250-outcomes","contributor-settings-20260915"],"protocol_id":"contributor-target50-astra-five-seed"}],"sources":[{"id":"paper-table-2","url":"https://arxiv.org/html/2607.08448v4#S3.T2"},{"id":"paper-table-3","url":"https://arxiv.org/html/2607.08448v4#S3.T3"},{"id":"paper-table-4","url":"https://arxiv.org/html/2607.08448v4#S3.T4"},{"id":"paper-table-6","url":"https://arxiv.org/html/2607.08448v4#S3.T6"},{"id":"astra-long-20260907","report_sha256":"627d6d8a95fb1e10357961694867cd0bf0a2aa9011c96c8a33504b904cb96c80"},{"id":"astra-pro-remaining-20260913","report_sha256":"627d6d8a95fb1e10357961694867cd0bf0a2aa9011c96c8a33504b904cb96c80"},{"id":"contributor-20260915","kind":"contributor-confirmed"},{"id":"contributor-settings-20260915","kind":"contributor-confirmed"},{"id":"contributor-correction-20260916","kind":"contributor-confirmed","note":"Corrected model labels and aggregate scores; removed requested configurations. No missing suite scores inferred."},{"id":"repo-flash-mode-800","url":"https://github.com/RLinf/RPent/blob/c19727c7bbdd277cd86a985aae3f2741ba01df7a/docs/source-en/rst_source/usage/task_card.rst","note":"581 successes across all 800 LIBERO-PRO cases; missing source traces count as failures. Molmo is used for visual localization, not planning."},{"id":"repo-robotwin-20260915","url":"https://github.com/RLinf/RPent/blob/849143bf740a562367345cec0de9ef4657dafd73/docs/source-en/rst_source/usage/robotwin.rst"},{"id":"xiaomi-official-robocasa365","url":"https://robocasa.ai/leaderboard.html","submission_url":"https://github.com/robocasa-benchmark/leaderboard/blob/main/submissions_md/Xiaomi-Robotics_2026_07_08.md","checked_at":"2026-09-16","environment_split":"pretrain","note":"Published 50-task benchmark scores. Displayed alongside RPent by request; protocol equivalence has not been verified. Episode counts for this reported batch are unspecified here."},{"id":"xiaomi-paper-v2-table-3","url":"https://arxiv.org/html/2607.15330v2#S3.T3"},{"id":"aspire-table-2","url":"https://arxiv.org/html/2607.00272v1#A2.T2","note":"Table 2 main LIBERO-Pro results; Pos maps to Swap, Task maps to Task. Ten tasks and seeds 1-50 per suite. Published rounded rates are preserved, not converted to integer successes. Six-item Overall 72% is not an eight-suite Overall."},{"id":"aspire-table-5","url":"https://arxiv.org/html/2607.00272v1#A3.T5","note":"Table 5, N=90 zero-shot library transfer: Task 0.383, Pos 0.226. A different evaluation regime from the six main suites; no combined Overall is inferred."},{"id":"flash-published-family-counts","url":"https://github.com/RLinf/misc/blob/main/rpent/task_card/task_card_libero_pro_performance_time.png","note":"Exact printed titles: Spatial 149/200, Object 179/200, Goal 139/200, Long 114/200. Sum 581/800. Cross-check only; independent Task/Swap scores come from contributor outcome records, not digitized bar heights."},{"id":"molmo2-model-card","url":"https://huggingface.co/allenai/Molmo2-8B","note":"Official model identity. RPent uses Molmo2-8B for visual localization only."},{"id":"flash-contributor-800-outcomes","type":"contributor_archive","artifact":"task_card.zip","sha256":"a997e5a0f823abf2402e1374e22a068c43dfecc35a778a185d0274efd45e31e2","note":"Eight Task/Swap aggregates from 800 unique contributor result.json cases, checked against summary.json and published family totals. Each component includes all 100 expected cases (task IDs 0–9, seeds 0–9). The 20 no-card cases remain in the denominator and are not counted as successes.","aggregates":{"spatial_task":{"successes":79,"episodes":100,"outcomes":{"success":79,"failure":21},"rate":"79.00"},"spatial_swap":{"successes":70,"episodes":100,"outcomes":{"success":70,"failure":30},"rate":"70.00"},"object_task":{"successes":86,"episodes":100,"outcomes":{"success":86,"failure":14},"rate":"86.00"},"object_swap":{"successes":93,"episodes":100,"outcomes":{"success":93,"failure":7},"rate":"93.00"},"goal_task":{"successes":74,"episodes":100,"outcomes":{"failure":26,"success":74},"rate":"74.00"},"goal_swap":{"successes":65,"episodes":100,"outcomes":{"no_card":10,"failure":25,"success":65},"rate":"65.00"},"long_task":{"successes":60,"episodes":100,"outcomes":{"success":60,"failure":40},"rate":"60.00"},"long_swap":{"successes":54,"episodes":100,"outcomes":{"success":54,"failure":36,"no_card":10},"rate":"54.00"}}},{"id":"robocasa-astra-contributor-250-outcomes","kind":"contributor_archive","artifact":"robocasa_astra.zip","sha256":"3ee89135bb69f0e6d29770f6103f4b53429481f9efde619ca6e7360597ce702c","environment_split":"target","tasks":50,"seeds":[1,2,3,4,5],"episodes":250,"successes":148,"groups":{"atomic":{"tasks":18,"successes":79,"episodes":90,"failures":11,"rate":"87.78"},"composite_seen":{"tasks":16,"successes":35,"episodes":80,"failures":45,"rate":"43.75"},"composite_unseen":{"tasks":16,"successes":34,"episodes":80,"failures":46,"rate":"42.50"}},"note":"250 unique contributor result.json outcomes match summary.json and final trace terminated flags. Five seeds per task make task-weighted Overall equal to 148/250. This corrects the previously assumed 340-case denominator; no missing cases are inferred. Model settings retain contributor confirmation."}],"astra":{"completed":800,"successes":741,"failures":59,"overall_rate":"92.63","memory_batches":[{"campaign_id":"libero_long_gpt6_astra_20260907","suites":["long-task","long-swap"]},{"campaign_id":"libero_pro_remaining_gpt6_astra_20260913","suites":["spatial-task","spatial-swap","object-task","object-swap","goal-task","goal-swap"],"manifest_sha256":"f08702d7c13d9b40a3127b64765ad4d336d022be028396d5f873d7fc4c4c4928"}],"suites":[{"view_id":"spatial-task","suite":"Spatial Task","dataset":"libero_spatial_task","completed":100,"planned":100,"successes":100,"failures":0,"remaining":0,"rate":"100.00","status":"complete"},{"view_id":"spatial-swap","suite":"Spatial Swap","dataset":"libero_spatial_swap","completed":100,"planned":100,"successes":98,"failures":2,"remaining":0,"rate":"98.00","status":"complete"},{"view_id":"object-task","suite":"Object Task","dataset":"libero_object_task","completed":100,"planned":100,"successes":100,"failures":0,"remaining":0,"rate":"100.00","status":"complete"},{"view_id":"object-swap","suite":"Object Swap","dataset":"libero_object_swap","completed":100,"planned":100,"successes":99,"failures":1,"remaining":0,"rate":"99.00","status":"complete"},{"view_id":"goal-task","suite":"Goal Task","dataset":"libero_goal_task","completed":100,"planned":100,"successes":88,"failures":12,"remaining":0,"rate":"88.00","status":"complete"},{"view_id":"goal-swap","suite":"Goal Swap","dataset":"libero_goal_swap","completed":100,"planned":100,"successes":99,"failures":1,"remaining":0,"rate":"99.00","status":"complete"},{"view_id":"long-task","suite":"Long Task","dataset":"libero_10_task","completed":100,"planned":100,"successes":85,"failures":15,"remaining":0,"rate":"85.00","status":"complete"},{"view_id":"long-swap","suite":"Long Swap","dataset":"libero_10_swap","completed":100,"planned":100,"successes":72,"failures":28,"remaining":0,"rate":"72.00","status":"complete"}]},"sections":[{"id":"libero-pro","name":"LIBERO-PRO","heading":{"en":"Eight-suite evaluation","zh":"八套件评测"},"summary":{"en":"Astra · low · reasoning: 92.63% (741/800)","zh":"Astra · low · reasoning：92.63%（741/800）"},"context":{"en":"GPT-6 Astra: Long Task/Swap and the other six suites use separate memory-file snapshots frozen after their respective exploration phases, with no updates during evaluation. Overall combines two non-overlapping batches: Long 157/200 plus the other suites 584/600, giving 741/800 (92.63%); the 800 episodes do not share a single memory snapshot.","zh":"GPT-6 Astra：Long Task/Swap 与其余六套件使用各自探索后冻结的 memory 文件快照，评测期间不更新。Overall 合并两个不重叠批次：Long 157/200，加上其余套件 584/600，得到 741/800（92.63%）；并非全部回合共享同一份 memory 快照。"},"default_view":"libero-pro","views":["libero-pro","spatial-task","spatial-swap","object-task","object-swap","goal-task","goal-swap","long-task","long-swap"],"notes":{"en":"ASPIRE: Long Task and Long Swap use zero-shot transfer from the LIBERO-90 skill library.","zh":"ASPIRE：Long Task 和 Long Swap 使用 LIBERO-90 技能库进行 zero-shot 迁移。"}},{"id":"standard-libero","name":"LIBERO","heading":{"en":"Four-suite evaluation","zh":"四套件评测"},"default_view":"standard-libero","views":["standard-libero","standard-spatial","standard-object","standard-goal","standard-long"]},{"id":"robocasa","name":"RoboCasa365 · Target50","heading":{"en":"50 tasks · task-weighted Overall","zh":"50 个任务 · Overall 按任务等权"},"default_view":"robocasa","views":["robocasa","robocasa-atomic-seen","robocasa-composite-seen","robocasa-composite-unseen"]},{"id":"robotwin","name":"RoboTwin","heading":{"en":"Clean → Randomized","zh":"Clean → Randomized"},"summary":{"en":"50 tasks · 250 episodes","zh":"50 个任务 · 250 回合"},"default_view":"robotwin","views":["robotwin"]}],"assets":["ellipsis.svg","download.svg","arrow-down.svg"]}</script><script src="table-sort.js"></script><script src="leaderboard.js"></script></body></html>
+<noscript><div class="section-inner"><section data-benchmark="libero-pro"><h2>LIBERO-PRO</h2><table><thead><tr><th>方法</th><th>成功率</th></tr></thead><tbody><tr><td>Codex / GPT-6 Astra / low / reasoning</td><td>92.63%</td></tr><tr><td>Claude Code / Opus-4.7 / max.reasoning</td><td>82.4%</td></tr><tr><td>RPent Flash Mode</td><td>72.63%</td></tr><tr><td>Codex / GPT-5.5 / xhigh / reasoning</td><td>72.1%</td></tr><tr><td>Qwen3.6 27B / no-reasoning</td><td>70.63%</td></tr><tr><td>ASPIRE</td><td>61.36%</td></tr><tr><td>π_RLinf</td><td>50.0%</td></tr><tr><td>π0.5</td><td>11.0%</td></tr><tr><td>AtomVLA</td><td>6.3%</td></tr><tr><td>X-VLA</td><td>3.8%</td></tr><tr><td>MolmoAct</td><td>1.5%</td></tr><tr><td>π0</td><td>0.3%</td></tr></tbody></table><p>GPT-6 Astra: 92.63% (741/800). RPent Flash Mode / Molmo2-8B: 72.63% (581/800). Qwen3.6 27B / no-reasoning: 70.63% (565/800).</p><h3>完整方法与分项成绩</h3><div class="table-wrap" tabindex="0"><table><thead><tr><th>方法</th><th>总体</th><th>Spatial Task</th><th>Spatial Swap</th><th>Object Task</th><th>Object Swap</th><th>Goal Task</th><th>Goal Swap</th><th>Long Task</th><th>Long Swap</th></tr></thead><tbody><tr><td>GPT-6 Astra</td><td>92.63%</td><td>100%</td><td>98%</td><td>100%</td><td>99%</td><td>88%</td><td>99%</td><td>85%</td><td>72%</td></tr><tr><td>Opus-4.7 / max.reasoning</td><td>82.4%</td><td>—</td><td>—</td><td>—</td><td>—</td><td>—</td><td>—</td><td>—</td><td>—</td></tr><tr><td>RPent Flash Mode / Molmo2-8B</td><td>72.63%</td><td>79.00%</td><td>70.00%</td><td>86.00%</td><td>93.00%</td><td>74.00%</td><td>65.00%</td><td>60.00%</td><td>54.00%</td></tr><tr><td>GPT-5.5</td><td>72.1%</td><td>81.0%</td><td>69.0%</td><td>94.0%</td><td>91.0%</td><td>75.0%</td><td>66.0%</td><td>52.0%</td><td>49.0%</td></tr><tr><td>Qwen3.6 27B / no-reasoning</td><td>70.63%</td><td>82.00%</td><td>78.00%</td><td>83.00%</td><td>84.00%</td><td>68.00%</td><td>68.00%</td><td>61.00%</td><td>41.00%</td></tr><tr><td>ASPIRE</td><td>61.36%</td><td>60.0%</td><td>51.0%</td><td>95.0%</td><td>98.0%</td><td>45.0%</td><td>81.0%</td><td>38.3%</td><td>22.6%</td></tr><tr><td>π_RLinf</td><td>50.0%</td><td>42.0%</td><td>59.0%</td><td>71.0%</td><td>78.0%</td><td>45.0%</td><td>42.0%</td><td>49.0%</td><td>14.0%</td></tr><tr><td>π0.5</td><td>11.0%</td><td>1.0%</td><td>20.0%</td><td>1.0%</td><td>17.0%</td><td>2.0%</td><td>38.0%</td><td>1.0%</td><td>8.0%</td></tr><tr><td>AtomVLA</td><td>6.3%</td><td>1.0%</td><td>16.0%</td><td>0.0%</td><td>10.0%</td><td>11.0%</td><td>2.0%</td><td>9.0%</td><td>1.0%</td></tr><tr><td>X-VLA</td><td>3.8%</td><td>0.0%</td><td>0.0%</td><td>8.0%</td><td>2.0%</td><td>9.0%</td><td>1.0%</td><td>10.0%</td><td>0.0%</td></tr><tr><td>MolmoAct</td><td>1.5%</td><td>0.0%</td><td>0.0%</td><td>0.0%</td><td>6.0%</td><td>0.0%</td><td>0.0%</td><td>6.0%</td><td>0.0%</td></tr><tr><td>π0</td><td>0.3%</td><td>0.0%</td><td>0.0%</td><td>0.0%</td><td>2.0%</td><td>0.0%</td><td>0.0%</td><td>0.0%</td><td>0.0%</td></tr><tr><td>Cap-X</td><td>—</td><td>14.0%</td><td>12.0%</td><td>18.0%</td><td>22.0%</td><td>17.0%</td><td>26.0%</td><td>—</td><td>—</td></tr><tr><td>RATS</td><td>—</td><td>31.0%</td><td>29.0%</td><td>63.0%</td><td>61.0%</td><td>36.0%</td><td>43.0%</td><td>—</td><td>—</td></tr></tbody></table></div><p>ASPIRE：Long Task 和 Long Swap 使用 LIBERO-90 技能库进行 zero-shot 迁移。</p><p id="libero-pro-astra-memory" class="memory-context">GPT-6 Astra：Long Task/Swap 与其余六套件使用各自探索后冻结的 memory 文件快照，评测期间不更新。Overall 合并两个不重叠批次：Long 157/200，加上其余套件 584/600，得到 741/800（92.63%）；并非全部回合共享同一份 memory 快照。</p></section>
+<section data-benchmark="standard-libero"><h2>LIBERO</h2><table><thead><tr><th>方法</th><th>成功率</th></tr></thead><tbody><tr><td>AtomVLA</td><td>97.0%</td></tr><tr><td>Claude Code / Opus-4.7 / max.reasoning</td><td>96.0%</td></tr><tr><td>π_RLinf</td><td>95.3%</td></tr><tr><td>π0</td><td>94.2%</td></tr><tr><td>NORA</td><td>79.5%</td></tr><tr><td>OpenVLA</td><td>76.5%</td></tr></tbody></table></section>
+<section data-benchmark="robocasa"><h2>RoboCasa365 · Target50</h2><table><thead><tr><th>方法</th><th>成功率</th></tr></thead><tbody><tr><td>Codex / GPT-6 Astra / low / reasoning</td><td>59.20%</td></tr><tr><td>Xiaomi-Robotics-1</td><td>57.4%</td></tr><tr><td>Codex / GPT-5.5 / xhigh / reasoning</td><td>57.1%</td></tr><tr><td>Claude Code / Opus-4.7 / max.reasoning</td><td>48.6%</td></tr><tr><td>WorldDreamer</td><td>35.3%</td></tr><tr><td>RLDX-1</td><td>30.0%</td></tr><tr><td>π0.5</td><td>16.9%</td></tr><tr><td>π0</td><td>14.8%</td></tr></tbody></table><h3>RoboCasa365 · Target50 · 完整方法与分项成绩</h3><div class="table-wrap" tabindex="0"><table><thead><tr><th>方法</th><th>总体</th><th>Atomic-Seen</th><th>Composite-Seen</th><th>Composite-Unseen</th></tr></thead><tbody><tr><td>GPT-6 Astra</td><td>59.20%</td><td>87.78%</td><td>43.75%</td><td>42.50%</td></tr><tr><td>Xiaomi-Robotics-1</td><td>57.4%</td><td>80.2%</td><td>57.1%</td><td>32.1%</td></tr><tr><td>GPT-5.5</td><td>57.1%</td><td>92.0%</td><td>61.0%</td><td>13.8%</td></tr><tr><td>Opus-4.7 / max.reasoning</td><td>48.6%</td><td>79.4%</td><td>47.5%</td><td>15.0%</td></tr><tr><td>WorldDreamer</td><td>35.3%</td><td>66.3%</td><td>26.7%</td><td>9.0%</td></tr><tr><td>RLDX-1</td><td>30.0%</td><td>60.0%</td><td>21.3%</td><td>5.0%</td></tr><tr><td>π0.5</td><td>16.9%</td><td>39.6%</td><td>7.1%</td><td>1.2%</td></tr><tr><td>π0</td><td>14.8%</td><td>34.6%</td><td>6.1%</td><td>1.1%</td></tr></tbody></table></div></section>
+<section data-benchmark="robotwin"><h2>RoboTwin</h2><table><thead><tr><th>方法</th><th>成功率</th></tr></thead><tbody><tr><td>Codex / GPT-5.5 / xhigh / reasoning</td><td>62.4%</td></tr><tr><td>Claude Code / Opus-4.7 / max.reasoning</td><td>58.4%</td></tr><tr><td>LingBot-VLA</td><td>50.4%</td></tr><tr><td>π0.5</td><td>47.9%</td></tr><tr><td>GR00T-N1.7</td><td>20.7%</td></tr><tr><td>StarVLA</td><td>10.6%</td></tr></tbody></table></section>
+<section class="cost-section" data-costs="true"><h2>Time &amp; Token Costs</h2><section class="cost-group" data-cost-group="libero-pro"><h3>LIBERO-PRO</h3><div class="table-wrap" tabindex="0"><table data-sort-key="costs-libero-pro" data-sort-direction="ascending" data-highlight-best="false"><thead><tr><th>方法</th><th>平均每回合耗时（秒）</th><th>总输出 token</th></tr></thead><tbody><tr data-cost-record="libero-pro--rpent-flash-mode"><td class="cost-method">RPent Flash Mode<small> Molmo2-8B · 视觉定位</small></td><td data-value="60.19">60.19</td><td data-value="0">0</td></tr><tr data-cost-record="libero-pro--gpt-5-6-no-reasoning"><td class="cost-method">RPent / GPT-5.6 Sol<small> Codex · no-reasoning</small></td><td data-value="344.17">344.17</td><td data-value="2569676">2,569,676</td></tr><tr data-cost-record="libero-pro--gpt-6-astra-low"><td class="cost-method">RPent / GPT-6 Astra<small> Codex · low · reasoning</small></td><td data-value="412.14">412.14</td><td data-value="3364938">3,364,938</td></tr><tr data-cost-record="libero-pro--gpt-5-6-xhigh"><td class="cost-method">RPent / GPT-5.6 Sol<small> Codex · xhigh · reasoning</small></td><td data-value="529.23">529.23</td><td data-value="3635426">3,635,426</td></tr><tr data-cost-record="libero-pro--qwen3-6-27b-no-reasoning"><td class="cost-method">RPent / Qwen3.6 27B<small> no-reasoning</small></td><td data-value="626.3">626.3</td><td data-value="3270754">3,270,754</td></tr></tbody></table></div></section><section class="cost-group" data-cost-group="robocasa"><h3>RoboCasa365</h3><div class="table-wrap" tabindex="0"><table data-sort-key="costs-robocasa" data-sort-direction="ascending" data-highlight-best="false"><thead><tr><th>方法</th><th>平均每回合耗时（秒）</th><th>总输出 token</th></tr></thead><tbody><tr data-cost-record="robocasa--gpt-5-6-no-reasoning"><td class="cost-method">RPent / GPT-5.6 Sol<small> Codex · no-reasoning</small></td><td data-value="1013.21">1,013.21</td><td data-value="4792104">4,792,104</td></tr><tr data-cost-record="robocasa--gpt-6-astra-low"><td class="cost-method">RPent / GPT-6 Astra<small> Codex · low · reasoning</small></td><td data-value="1168.95">1,168.95</td><td data-value="5894436">5,894,436</td></tr><tr data-cost-record="robocasa--gpt-5-6-xhigh"><td class="cost-method">RPent / GPT-5.6 Sol<small> Codex · xhigh · reasoning</small></td><td data-value="1197.56">1,197.56</td><td data-value="5258391">5,258,391</td></tr></tbody></table></div></section><section class="cost-group" data-cost-group="robotwin"><h3>RoboTwin</h3><div class="table-wrap" tabindex="0"><table data-sort-key="costs-robotwin" data-sort-direction="ascending" data-highlight-best="false"><thead><tr><th>方法</th><th>平均每回合耗时（秒）</th><th>总输出 token</th></tr></thead><tbody><tr data-cost-record="robotwin--gpt-5-6-no-reasoning"><td class="cost-method">RPent / GPT-5.6 Sol<small> Codex · no-reasoning</small></td><td data-value="957.4">957.4</td><td data-value="2456401">2,456,401</td></tr><tr data-cost-record="robotwin--gpt-6-astra-low"><td class="cost-method">RPent / GPT-6 Astra<small> Codex · low · reasoning</small></td><td data-value="1078.8">1,078.8</td><td data-value="2763641">2,763,641</td></tr><tr data-cost-record="robotwin--gpt-5-6-xhigh"><td class="cost-method">RPent / GPT-5.6 Sol<small> Codex · xhigh · reasoning</small></td><td data-value="1828.7">1,828.7</td><td data-value="4763915">4,763,915</td></tr></tbody></table></div></section></section></div></noscript><script id="results-data" type="application/json">{"schema_version":2,"checked_at":"2026-09-18","paper_revision":"2607.08448v4","repository_revision":"43f32aa08cba07bd4d49a4bfa5eba4ef633e9b92","configurations":[{"id":"gpt-5-5-xhigh","kind":"rpent","backend":"Codex","model":"GPT-5.5","reasoning":true,"effort":"xhigh"},{"id":"opus-4-7-max","kind":"rpent","backend":"Claude Code","model":"Opus-4.7","reasoning":true,"effort":"max"},{"id":"gpt-6-astra-low","kind":"rpent","backend":"Codex","model":"GPT-6 Astra","reasoning":true,"effort":"low"},{"id":"openvla","kind":"external","backend":null,"model":"OpenVLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"nora","kind":"external","backend":null,"model":"NORA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"pi0","kind":"external","backend":null,"model":"π0","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"pi-rlinf","kind":"external","backend":null,"model":"π_RLinf","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"atomvla","kind":"external","backend":null,"model":"AtomVLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"pi0-5","kind":"external","backend":null,"model":"π0.5","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"molmoact","kind":"external","backend":null,"model":"MolmoAct","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"x-vla","kind":"external","backend":null,"model":"X-VLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"cap-x","kind":"external","backend":null,"model":"Cap-X","reasoning":null,"effort":null,"metadata_status":"not_reported"},{"id":"rats","kind":"external","backend":null,"model":"RATS","reasoning":null,"effort":null,"metadata_status":"not_reported"},{"id":"rldx-1","kind":"external","backend":null,"model":"RLDX-1","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"worlddreamer","kind":"external","backend":null,"model":"WorldDreamer","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"gr00t-n1-7","kind":"external","backend":null,"model":"GR00T-N1.7","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"starvla","kind":"external","backend":null,"model":"StarVLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"lingbot-vla","kind":"external","backend":null,"model":"LingBot-VLA","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"opus-4-7-reported","kind":"rpent","backend":"Claude Code","model":"Opus-4.7","reasoning":true,"effort":"max"},{"id":"rpent-flash-mode","kind":"rpent","backend":null,"model":null,"reasoning":null,"effort":null,"display_name":"RPent Flash Mode","perception_model":"Molmo2-8B"},{"id":"xiaomi-robotics-1","kind":"external","backend":null,"model":"Xiaomi-Robotics-1","reasoning":null,"effort":null,"metadata_status":"not_applicable"},{"id":"aspire","kind":"external","backend":null,"model":"ASPIRE","reasoning":null,"effort":null},{"id":"qwen3-6-27b-no-reasoning","kind":"rpent","backend":null,"model":"Qwen3.6 27B","reasoning":false,"effort":null},{"id":"gpt-5-6-xhigh","kind":"rpent","backend":"Codex","model":"GPT-5.6 Sol","reasoning":true,"effort":"xhigh"},{"id":"gpt-5-6-no-reasoning","kind":"rpent","backend":"Codex","model":"GPT-5.6 Sol","reasoning":false,"effort":null}],"views":[{"id":"standard-spatial","benchmark_id":"standard-libero","label":{"en":"Spatial","zh":"Spatial"},"record_ids":["standard-spatial--opus-4-7-max","standard-spatial--openvla","standard-spatial--nora","standard-spatial--pi0","standard-spatial--pi-rlinf","standard-spatial--atomvla"]},{"id":"standard-object","benchmark_id":"standard-libero","label":{"en":"Object","zh":"Object"},"record_ids":["standard-object--opus-4-7-max","standard-object--openvla","standard-object--nora","standard-object--pi0","standard-object--pi-rlinf","standard-object--atomvla"]},{"id":"standard-goal","benchmark_id":"standard-libero","label":{"en":"Goal","zh":"Goal"},"record_ids":["standard-goal--opus-4-7-max","standard-goal--openvla","standard-goal--nora","standard-goal--pi0","standard-goal--pi-rlinf","standard-goal--atomvla"]},{"id":"standard-long","benchmark_id":"standard-libero","label":{"en":"Long","zh":"Long"},"record_ids":["standard-long--opus-4-7-max","standard-long--openvla","standard-long--nora","standard-long--pi0","standard-long--pi-rlinf","standard-long--atomvla"]},{"id":"standard-libero","benchmark_id":"standard-libero","label":{"en":"Overall","zh":"总体"},"record_ids":["standard-libero--opus-4-7-max","standard-libero--openvla","standard-libero--nora","standard-libero--pi0","standard-libero--pi-rlinf","standard-libero--atomvla"]},{"id":"spatial-task","benchmark_id":"libero-pro","label":{"en":"Spatial Task","zh":"Spatial Task"},"record_ids":["spatial-task--gpt-5-5-xhigh","spatial-task--gpt-6-astra-low","spatial-task--pi0","spatial-task--pi0-5","spatial-task--molmoact","spatial-task--x-vla","spatial-task--atomvla","spatial-task--cap-x","spatial-task--rats","spatial-task--pi-rlinf","spatial-task--aspire","spatial-task--rpent-flash-mode","spatial-task--qwen3-6-27b-no-reasoning"]},{"id":"spatial-swap","benchmark_id":"libero-pro","label":{"en":"Spatial Swap","zh":"Spatial Swap"},"record_ids":["spatial-swap--gpt-5-5-xhigh","spatial-swap--gpt-6-astra-low","spatial-swap--pi0","spatial-swap--pi0-5","spatial-swap--molmoact","spatial-swap--x-vla","spatial-swap--atomvla","spatial-swap--cap-x","spatial-swap--rats","spatial-swap--pi-rlinf","spatial-swap--aspire","spatial-swap--rpent-flash-mode","spatial-swap--qwen3-6-27b-no-reasoning"]},{"id":"object-task","benchmark_id":"libero-pro","label":{"en":"Object Task","zh":"Object Task"},"record_ids":["object-task--gpt-5-5-xhigh","object-task--gpt-6-astra-low","object-task--pi0","object-task--pi0-5","object-task--molmoact","object-task--x-vla","object-task--atomvla","object-task--cap-x","object-task--rats","object-task--pi-rlinf","object-task--aspire","object-task--rpent-flash-mode","object-task--qwen3-6-27b-no-reasoning"]},{"id":"object-swap","benchmark_id":"libero-pro","label":{"en":"Object Swap","zh":"Object Swap"},"record_ids":["object-swap--gpt-5-5-xhigh","object-swap--gpt-6-astra-low","object-swap--pi0","object-swap--pi0-5","object-swap--molmoact","object-swap--x-vla","object-swap--atomvla","object-swap--cap-x","object-swap--rats","object-swap--pi-rlinf","object-swap--aspire","object-swap--rpent-flash-mode","object-swap--qwen3-6-27b-no-reasoning"]},{"id":"goal-task","benchmark_id":"libero-pro","label":{"en":"Goal Task","zh":"Goal Task"},"record_ids":["goal-task--gpt-5-5-xhigh","goal-task--gpt-6-astra-low","goal-task--pi0","goal-task--pi0-5","goal-task--molmoact","goal-task--x-vla","goal-task--atomvla","goal-task--cap-x","goal-task--rats","goal-task--pi-rlinf","goal-task--aspire","goal-task--rpent-flash-mode","goal-task--qwen3-6-27b-no-reasoning"]},{"id":"goal-swap","benchmark_id":"libero-pro","label":{"en":"Goal Swap","zh":"Goal Swap"},"record_ids":["goal-swap--gpt-5-5-xhigh","goal-swap--gpt-6-astra-low","goal-swap--pi0","goal-swap--pi0-5","goal-swap--molmoact","goal-swap--x-vla","goal-swap--atomvla","goal-swap--cap-x","goal-swap--rats","goal-swap--pi-rlinf","goal-swap--aspire","goal-swap--rpent-flash-mode","goal-swap--qwen3-6-27b-no-reasoning"]},{"id":"long-task","benchmark_id":"libero-pro","label":{"en":"Long Task","zh":"Long Task"},"record_ids":["long-task--gpt-5-5-xhigh","long-task--gpt-6-astra-low","long-task--pi0","long-task--pi0-5","long-task--molmoact","long-task--x-vla","long-task--atomvla","long-task--pi-rlinf","long-task--aspire","long-task--rpent-flash-mode","long-task--qwen3-6-27b-no-reasoning"]},{"id":"long-swap","benchmark_id":"libero-pro","label":{"en":"Long Swap","zh":"Long Swap"},"record_ids":["long-swap--gpt-5-5-xhigh","long-swap--gpt-6-astra-low","long-swap--pi0","long-swap--pi0-5","long-swap--molmoact","long-swap--x-vla","long-swap--atomvla","long-swap--pi-rlinf","long-swap--aspire","long-swap--rpent-flash-mode","long-swap--qwen3-6-27b-no-reasoning"]},{"id":"libero-pro","benchmark_id":"libero-pro","label":{"en":"Overall","zh":"总体"},"record_ids":["libero-pro--gpt-5-5-xhigh","libero-pro--gpt-6-astra-low","libero-pro--pi0","libero-pro--pi0-5","libero-pro--molmoact","libero-pro--x-vla","libero-pro--atomvla","libero-pro--pi-rlinf","libero-pro--opus-4-7-reported","libero-pro--rpent-flash-mode","libero-pro--aspire","libero-pro--qwen3-6-27b-no-reasoning"]},{"id":"robocasa-atomic-seen","benchmark_id":"robocasa","label":{"en":"Atomic-Seen","zh":"Atomic-Seen"},"record_ids":["robocasa-atomic-seen--gpt-5-5-xhigh","robocasa-atomic-seen--opus-4-7-max","robocasa-atomic-seen--rldx-1","robocasa-atomic-seen--worlddreamer","robocasa-atomic-seen--pi0-5","robocasa-atomic-seen--pi0","robocasa-atomic-seen--xiaomi-robotics-1","robocasa-atomic-seen--gpt-6-astra-low"]},{"id":"robocasa-composite-seen","benchmark_id":"robocasa","label":{"en":"Composite-Seen","zh":"Composite-Seen"},"record_ids":["robocasa-composite-seen--gpt-5-5-xhigh","robocasa-composite-seen--opus-4-7-max","robocasa-composite-seen--rldx-1","robocasa-composite-seen--worlddreamer","robocasa-composite-seen--pi0-5","robocasa-composite-seen--pi0","robocasa-composite-seen--xiaomi-robotics-1","robocasa-composite-seen--gpt-6-astra-low"]},{"id":"robocasa-composite-unseen","benchmark_id":"robocasa","label":{"en":"Composite-Unseen","zh":"Composite-Unseen"},"record_ids":["robocasa-composite-unseen--gpt-5-5-xhigh","robocasa-composite-unseen--opus-4-7-max","robocasa-composite-unseen--rldx-1","robocasa-composite-unseen--worlddreamer","robocasa-composite-unseen--pi0-5","robocasa-composite-unseen--pi0","robocasa-composite-unseen--xiaomi-robotics-1","robocasa-composite-unseen--gpt-6-astra-low"]},{"id":"robocasa","benchmark_id":"robocasa","label":{"en":"Overall","zh":"总体"},"record_ids":["robocasa--gpt-5-5-xhigh","robocasa--opus-4-7-max","robocasa--rldx-1","robocasa--worlddreamer","robocasa--pi0-5","robocasa--pi0","robocasa--gpt-6-astra-reported","robocasa--xiaomi-robotics-1"]},{"id":"robotwin","benchmark_id":"robotwin","label":{"en":"C2R","zh":"C2R"},"record_ids":["robotwin--opus-4-7-max","robotwin--gr00t-n1-7","robotwin--pi0-5","robotwin--starvla","robotwin--lingbot-vla","robotwin--gpt-5-5-xhigh"]}],"results":[{"id":"standard-spatial--opus-4-7-max","view_id":"standard-spatial","configuration_id":"opus-4-7-max","status":"reported","rate":"97.0","successes":null,"episodes":100,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"standard-object--opus-4-7-max","view_id":"standard-object","configuration_id":"opus-4-7-max","status":"reported","rate":"100.0","successes":null,"episodes":100,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"standard-goal--opus-4-7-max","view_id":"standard-goal","configuration_id":"opus-4-7-max","status":"reported","rate":"94.0","successes":null,"episodes":100,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"standard-long--opus-4-7-max","view_id":"standard-long","configuration_id":"opus-4-7-max","status":"reported","rate":"93.0","successes":null,"episodes":100,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"standard-libero--opus-4-7-max","view_id":"standard-libero","configuration_id":"opus-4-7-max","status":"reported","rate":"96.0","successes":384,"episodes":400,"source_ids":["paper-table-2","contributor-correction-20260916"],"protocol_id":"rpent-standard"},{"id":"spatial-task--gpt-5-5-xhigh","view_id":"spatial-task","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"81.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"spatial-task--gpt-6-astra-low","view_id":"spatial-task","configuration_id":"gpt-6-astra-low","status":"reported","rate":"100","successes":100,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"spatial-swap--gpt-5-5-xhigh","view_id":"spatial-swap","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"69.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"spatial-swap--gpt-6-astra-low","view_id":"spatial-swap","configuration_id":"gpt-6-astra-low","status":"reported","rate":"98","successes":98,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"object-task--gpt-5-5-xhigh","view_id":"object-task","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"94.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"object-task--gpt-6-astra-low","view_id":"object-task","configuration_id":"gpt-6-astra-low","status":"reported","rate":"100","successes":100,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"object-swap--gpt-5-5-xhigh","view_id":"object-swap","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"91.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"object-swap--gpt-6-astra-low","view_id":"object-swap","configuration_id":"gpt-6-astra-low","status":"reported","rate":"99","successes":99,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"goal-task--gpt-5-5-xhigh","view_id":"goal-task","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"75.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"goal-task--gpt-6-astra-low","view_id":"goal-task","configuration_id":"gpt-6-astra-low","status":"reported","rate":"88","successes":88,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"goal-swap--gpt-5-5-xhigh","view_id":"goal-swap","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"66.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"goal-swap--gpt-6-astra-low","view_id":"goal-swap","configuration_id":"gpt-6-astra-low","status":"reported","rate":"99","successes":99,"episodes":100,"source_ids":["astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-remaining"},{"id":"long-task--gpt-5-5-xhigh","view_id":"long-task","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"52.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"long-task--gpt-6-astra-low","view_id":"long-task","configuration_id":"gpt-6-astra-low","status":"reported","rate":"85","successes":85,"episodes":100,"source_ids":["astra-long-20260907","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-long"},{"id":"long-swap--gpt-5-5-xhigh","view_id":"long-swap","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"49.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"long-swap--gpt-6-astra-low","view_id":"long-swap","configuration_id":"gpt-6-astra-low","status":"reported","rate":"72","successes":72,"episodes":100,"source_ids":["astra-long-20260907","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-long"},{"id":"libero-pro--gpt-5-5-xhigh","view_id":"libero-pro","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"72.1","successes":null,"episodes":800,"source_ids":["paper-table-3"],"protocol_id":"rpent-pro"},{"id":"libero-pro--gpt-6-astra-low","view_id":"libero-pro","configuration_id":"gpt-6-astra-low","status":"reported","rate":"92.63","successes":741,"episodes":800,"source_ids":["astra-long-20260907","astra-pro-remaining-20260913","contributor-settings-20260915"],"protocol_id":"rpent-pro-astra-mixed-batches"},{"id":"robocasa-atomic-seen--gpt-5-5-xhigh","view_id":"robocasa-atomic-seen","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"92.0","successes":null,"episodes":180,"source_ids":["paper-table-4"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-atomic-seen--opus-4-7-max","view_id":"robocasa-atomic-seen","configuration_id":"opus-4-7-max","status":"reported","rate":"79.4","successes":null,"episodes":180,"source_ids":["paper-table-4","contributor-correction-20260916"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-composite-seen--gpt-5-5-xhigh","view_id":"robocasa-composite-seen","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"61.0","successes":null,"episodes":80,"source_ids":["paper-table-4"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-composite-seen--opus-4-7-max","view_id":"robocasa-composite-seen","configuration_id":"opus-4-7-max","status":"reported","rate":"47.5","successes":null,"episodes":80,"source_ids":["paper-table-4","contributor-correction-20260916"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-composite-unseen--gpt-5-5-xhigh","view_id":"robocasa-composite-unseen","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"13.8","successes":null,"episodes":80,"source_ids":["paper-table-4"],"protocol_id":"rpent-robocasa"},{"id":"robocasa-composite-unseen--opus-4-7-max","view_id":"robocasa-composite-unseen","configuration_id":"opus-4-7-max","status":"reported","rate":"15.0","successes":null,"episodes":80,"source_ids":["paper-table-4","contributor-correction-20260916"],"protocol_id":"rpent-robocasa"},{"id":"robocasa--gpt-5-5-xhigh","view_id":"robocasa","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"57.1","successes":null,"episodes":340,"source_ids":["paper-table-4"],"protocol_id":"rpent-robocasa"},{"id":"robocasa--opus-4-7-max","view_id":"robocasa","configuration_id":"opus-4-7-max","status":"reported","rate":"48.6","successes":null,"episodes":340,"source_ids":["paper-table-4","contributor-correction-20260916"],"protocol_id":"rpent-robocasa"},{"id":"robotwin--opus-4-7-max","view_id":"robotwin","configuration_id":"opus-4-7-max","status":"reported","rate":"58.4","successes":null,"episodes":250,"source_ids":["paper-table-6","contributor-correction-20260916"],"protocol_id":"rpent-robotwin"},{"id":"standard-libero--openvla","view_id":"standard-libero","configuration_id":"openvla","status":"reported","rate":"76.5","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-libero--nora","view_id":"standard-libero","configuration_id":"nora","status":"reported","rate":"79.5","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-libero--pi0","view_id":"standard-libero","configuration_id":"pi0","status":"reported","rate":"94.2","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-libero--pi-rlinf","view_id":"standard-libero","configuration_id":"pi-rlinf","status":"reported","rate":"95.3","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-libero--atomvla","view_id":"standard-libero","configuration_id":"atomvla","status":"reported","rate":"97.0","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"libero-pro--pi0","view_id":"libero-pro","configuration_id":"pi0","status":"reported","rate":"0.3","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--pi0-5","view_id":"libero-pro","configuration_id":"pi0-5","status":"reported","rate":"11.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--molmoact","view_id":"libero-pro","configuration_id":"molmoact","status":"reported","rate":"1.5","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--x-vla","view_id":"libero-pro","configuration_id":"x-vla","status":"reported","rate":"3.8","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--atomvla","view_id":"libero-pro","configuration_id":"atomvla","status":"reported","rate":"6.3","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"libero-pro--pi-rlinf","view_id":"libero-pro","configuration_id":"pi-rlinf","status":"reported","rate":"50.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"robocasa--rldx-1","view_id":"robocasa","configuration_id":"rldx-1","status":"reported","rate":"30.0","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa--worlddreamer","view_id":"robocasa","configuration_id":"worlddreamer","status":"reported","rate":"35.3","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa--pi0-5","view_id":"robocasa","configuration_id":"pi0-5","status":"reported","rate":"16.9","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa--pi0","view_id":"robocasa","configuration_id":"pi0","status":"reported","rate":"14.8","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robotwin--gr00t-n1-7","view_id":"robotwin","configuration_id":"gr00t-n1-7","status":"reported","rate":"20.7","successes":null,"episodes":null,"source_ids":["paper-table-6"],"protocol_id":"external-robotwin"},{"id":"robotwin--pi0-5","view_id":"robotwin","configuration_id":"pi0-5","status":"reported","rate":"47.9","successes":null,"episodes":null,"source_ids":["paper-table-6"],"protocol_id":"external-robotwin"},{"id":"robotwin--starvla","view_id":"robotwin","configuration_id":"starvla","status":"reported","rate":"10.6","successes":null,"episodes":null,"source_ids":["paper-table-6"],"protocol_id":"external-robotwin"},{"id":"robotwin--lingbot-vla","view_id":"robotwin","configuration_id":"lingbot-vla","status":"reported","rate":"50.4","successes":null,"episodes":null,"source_ids":["paper-table-6"],"protocol_id":"external-robotwin"},{"id":"standard-spatial--openvla","view_id":"standard-spatial","configuration_id":"openvla","status":"reported","rate":"84.7","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--openvla","view_id":"standard-object","configuration_id":"openvla","status":"reported","rate":"88.4","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--openvla","view_id":"standard-goal","configuration_id":"openvla","status":"reported","rate":"79.2","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--openvla","view_id":"standard-long","configuration_id":"openvla","status":"reported","rate":"53.7","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-spatial--nora","view_id":"standard-spatial","configuration_id":"nora","status":"reported","rate":"85.6","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--nora","view_id":"standard-object","configuration_id":"nora","status":"reported","rate":"89.4","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--nora","view_id":"standard-goal","configuration_id":"nora","status":"reported","rate":"80.0","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--nora","view_id":"standard-long","configuration_id":"nora","status":"reported","rate":"63.0","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-spatial--pi0","view_id":"standard-spatial","configuration_id":"pi0","status":"reported","rate":"96.8","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--pi0","view_id":"standard-object","configuration_id":"pi0","status":"reported","rate":"98.8","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--pi0","view_id":"standard-goal","configuration_id":"pi0","status":"reported","rate":"95.8","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--pi0","view_id":"standard-long","configuration_id":"pi0","status":"reported","rate":"85.2","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-spatial--pi-rlinf","view_id":"standard-spatial","configuration_id":"pi-rlinf","status":"reported","rate":"99.0","successes":null,"episodes":100,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--pi-rlinf","view_id":"standard-object","configuration_id":"pi-rlinf","status":"reported","rate":"96.0","successes":null,"episodes":100,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--pi-rlinf","view_id":"standard-goal","configuration_id":"pi-rlinf","status":"reported","rate":"97.0","successes":null,"episodes":100,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--pi-rlinf","view_id":"standard-long","configuration_id":"pi-rlinf","status":"reported","rate":"89.0","successes":null,"episodes":100,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-spatial--atomvla","view_id":"standard-spatial","configuration_id":"atomvla","status":"reported","rate":"96.4","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-object--atomvla","view_id":"standard-object","configuration_id":"atomvla","status":"reported","rate":"99.6","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-goal--atomvla","view_id":"standard-goal","configuration_id":"atomvla","status":"reported","rate":"97.6","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"standard-long--atomvla","view_id":"standard-long","configuration_id":"atomvla","status":"reported","rate":"94.4","successes":null,"episodes":null,"source_ids":["paper-table-2"],"protocol_id":"external-standard"},{"id":"spatial-task--pi0","view_id":"spatial-task","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--pi0","view_id":"spatial-swap","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--pi0","view_id":"object-task","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--pi0","view_id":"object-swap","configuration_id":"pi0","status":"reported","rate":"2.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--pi0","view_id":"goal-task","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--pi0","view_id":"goal-swap","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--pi0","view_id":"long-task","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--pi0","view_id":"long-swap","configuration_id":"pi0","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--pi0-5","view_id":"spatial-task","configuration_id":"pi0-5","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--pi0-5","view_id":"spatial-swap","configuration_id":"pi0-5","status":"reported","rate":"20.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--pi0-5","view_id":"object-task","configuration_id":"pi0-5","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--pi0-5","view_id":"object-swap","configuration_id":"pi0-5","status":"reported","rate":"17.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--pi0-5","view_id":"goal-task","configuration_id":"pi0-5","status":"reported","rate":"2.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--pi0-5","view_id":"goal-swap","configuration_id":"pi0-5","status":"reported","rate":"38.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--pi0-5","view_id":"long-task","configuration_id":"pi0-5","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--pi0-5","view_id":"long-swap","configuration_id":"pi0-5","status":"reported","rate":"8.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--molmoact","view_id":"spatial-task","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--molmoact","view_id":"spatial-swap","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--molmoact","view_id":"object-task","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--molmoact","view_id":"object-swap","configuration_id":"molmoact","status":"reported","rate":"6.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--molmoact","view_id":"goal-task","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--molmoact","view_id":"goal-swap","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--molmoact","view_id":"long-task","configuration_id":"molmoact","status":"reported","rate":"6.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--molmoact","view_id":"long-swap","configuration_id":"molmoact","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--x-vla","view_id":"spatial-task","configuration_id":"x-vla","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--x-vla","view_id":"spatial-swap","configuration_id":"x-vla","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--x-vla","view_id":"object-task","configuration_id":"x-vla","status":"reported","rate":"8.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--x-vla","view_id":"object-swap","configuration_id":"x-vla","status":"reported","rate":"2.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--x-vla","view_id":"goal-task","configuration_id":"x-vla","status":"reported","rate":"9.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--x-vla","view_id":"goal-swap","configuration_id":"x-vla","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--x-vla","view_id":"long-task","configuration_id":"x-vla","status":"reported","rate":"10.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--x-vla","view_id":"long-swap","configuration_id":"x-vla","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--atomvla","view_id":"spatial-task","configuration_id":"atomvla","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--atomvla","view_id":"spatial-swap","configuration_id":"atomvla","status":"reported","rate":"16.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--atomvla","view_id":"object-task","configuration_id":"atomvla","status":"reported","rate":"0.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--atomvla","view_id":"object-swap","configuration_id":"atomvla","status":"reported","rate":"10.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--atomvla","view_id":"goal-task","configuration_id":"atomvla","status":"reported","rate":"11.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--atomvla","view_id":"goal-swap","configuration_id":"atomvla","status":"reported","rate":"2.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--atomvla","view_id":"long-task","configuration_id":"atomvla","status":"reported","rate":"9.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--atomvla","view_id":"long-swap","configuration_id":"atomvla","status":"reported","rate":"1.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--cap-x","view_id":"spatial-task","configuration_id":"cap-x","status":"reported","rate":"14.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--cap-x","view_id":"spatial-swap","configuration_id":"cap-x","status":"reported","rate":"12.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--cap-x","view_id":"object-task","configuration_id":"cap-x","status":"reported","rate":"18.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--cap-x","view_id":"object-swap","configuration_id":"cap-x","status":"reported","rate":"22.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--cap-x","view_id":"goal-task","configuration_id":"cap-x","status":"reported","rate":"17.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--cap-x","view_id":"goal-swap","configuration_id":"cap-x","status":"reported","rate":"26.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--rats","view_id":"spatial-task","configuration_id":"rats","status":"reported","rate":"31.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--rats","view_id":"spatial-swap","configuration_id":"rats","status":"reported","rate":"29.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--rats","view_id":"object-task","configuration_id":"rats","status":"reported","rate":"63.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--rats","view_id":"object-swap","configuration_id":"rats","status":"reported","rate":"61.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--rats","view_id":"goal-task","configuration_id":"rats","status":"reported","rate":"36.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--rats","view_id":"goal-swap","configuration_id":"rats","status":"reported","rate":"43.0","successes":null,"episodes":null,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-task--pi-rlinf","view_id":"spatial-task","configuration_id":"pi-rlinf","status":"reported","rate":"42.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"spatial-swap--pi-rlinf","view_id":"spatial-swap","configuration_id":"pi-rlinf","status":"reported","rate":"59.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-task--pi-rlinf","view_id":"object-task","configuration_id":"pi-rlinf","status":"reported","rate":"71.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"object-swap--pi-rlinf","view_id":"object-swap","configuration_id":"pi-rlinf","status":"reported","rate":"78.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-task--pi-rlinf","view_id":"goal-task","configuration_id":"pi-rlinf","status":"reported","rate":"45.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"goal-swap--pi-rlinf","view_id":"goal-swap","configuration_id":"pi-rlinf","status":"reported","rate":"42.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-task--pi-rlinf","view_id":"long-task","configuration_id":"pi-rlinf","status":"reported","rate":"49.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"long-swap--pi-rlinf","view_id":"long-swap","configuration_id":"pi-rlinf","status":"reported","rate":"14.0","successes":null,"episodes":100,"source_ids":["paper-table-3"],"protocol_id":"external-pro"},{"id":"robocasa-atomic-seen--rldx-1","view_id":"robocasa-atomic-seen","configuration_id":"rldx-1","status":"reported","rate":"60.0","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-seen--rldx-1","view_id":"robocasa-composite-seen","configuration_id":"rldx-1","status":"reported","rate":"21.3","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-unseen--rldx-1","view_id":"robocasa-composite-unseen","configuration_id":"rldx-1","status":"reported","rate":"5.0","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-atomic-seen--worlddreamer","view_id":"robocasa-atomic-seen","configuration_id":"worlddreamer","status":"reported","rate":"66.3","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-seen--worlddreamer","view_id":"robocasa-composite-seen","configuration_id":"worlddreamer","status":"reported","rate":"26.7","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-unseen--worlddreamer","view_id":"robocasa-composite-unseen","configuration_id":"worlddreamer","status":"reported","rate":"9.0","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-atomic-seen--pi0-5","view_id":"robocasa-atomic-seen","configuration_id":"pi0-5","status":"reported","rate":"39.6","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-seen--pi0-5","view_id":"robocasa-composite-seen","configuration_id":"pi0-5","status":"reported","rate":"7.1","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-unseen--pi0-5","view_id":"robocasa-composite-unseen","configuration_id":"pi0-5","status":"reported","rate":"1.2","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-atomic-seen--pi0","view_id":"robocasa-atomic-seen","configuration_id":"pi0","status":"reported","rate":"34.6","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-seen--pi0","view_id":"robocasa-composite-seen","configuration_id":"pi0","status":"reported","rate":"6.1","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"robocasa-composite-unseen--pi0","view_id":"robocasa-composite-unseen","configuration_id":"pi0","status":"reported","rate":"1.1","successes":null,"episodes":null,"source_ids":["paper-table-4"],"protocol_id":"external-robocasa"},{"id":"libero-pro--opus-4-7-reported","view_id":"libero-pro","configuration_id":"opus-4-7-reported","status":"reported","rate":"82.4","successes":null,"episodes":800,"source_ids":["contributor-correction-20260916"],"protocol_id":"contributor-pro-eight"},{"id":"libero-pro--rpent-flash-mode","view_id":"libero-pro","configuration_id":"rpent-flash-mode","status":"reported","rate":"72.63","successes":581,"episodes":800,"source_ids":["repo-flash-mode-800","flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"robocasa--gpt-6-astra-reported","view_id":"robocasa","configuration_id":"gpt-6-astra-low","status":"reported","rate":"59.20","successes":148,"episodes":250,"source_ids":["contributor-20260915","contributor-settings-20260915","robocasa-astra-contributor-250-outcomes"],"protocol_id":"contributor-target50-astra-five-seed"},{"id":"robotwin--gpt-5-5-xhigh","view_id":"robotwin","configuration_id":"gpt-5-5-xhigh","status":"reported","rate":"62.4","successes":156,"episodes":250,"source_ids":["repo-robotwin-20260915"],"protocol_id":"repo-robotwin-20260915","task_failures":58,"episode_timeouts":36},{"id":"robocasa--xiaomi-robotics-1","view_id":"robocasa","configuration_id":"xiaomi-robotics-1","status":"reported","rate":"57.4","successes":null,"episodes":null,"source_ids":["xiaomi-official-robocasa365","xiaomi-paper-v2-table-3"],"protocol_id":"xiaomi-official-robocasa365"},{"id":"robocasa-atomic-seen--xiaomi-robotics-1","view_id":"robocasa-atomic-seen","configuration_id":"xiaomi-robotics-1","status":"reported","rate":"80.2","successes":null,"episodes":null,"source_ids":["xiaomi-official-robocasa365","xiaomi-paper-v2-table-3"],"protocol_id":"xiaomi-official-robocasa365"},{"id":"robocasa-composite-seen--xiaomi-robotics-1","view_id":"robocasa-composite-seen","configuration_id":"xiaomi-robotics-1","status":"reported","rate":"57.1","successes":null,"episodes":null,"source_ids":["xiaomi-official-robocasa365","xiaomi-paper-v2-table-3"],"protocol_id":"xiaomi-official-robocasa365"},{"id":"robocasa-composite-unseen--xiaomi-robotics-1","view_id":"robocasa-composite-unseen","configuration_id":"xiaomi-robotics-1","status":"reported","rate":"32.1","successes":null,"episodes":null,"source_ids":["xiaomi-official-robocasa365","xiaomi-paper-v2-table-3"],"protocol_id":"xiaomi-official-robocasa365"},{"id":"spatial-task--aspire","view_id":"spatial-task","configuration_id":"aspire","status":"reported","rate":"60.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"spatial-swap--aspire","view_id":"spatial-swap","configuration_id":"aspire","status":"reported","rate":"51.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"object-task--aspire","view_id":"object-task","configuration_id":"aspire","status":"reported","rate":"95.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"object-swap--aspire","view_id":"object-swap","configuration_id":"aspire","status":"reported","rate":"98.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"goal-task--aspire","view_id":"goal-task","configuration_id":"aspire","status":"reported","rate":"45.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"goal-swap--aspire","view_id":"goal-swap","configuration_id":"aspire","status":"reported","rate":"81.0","successes":null,"episodes":500,"source_ids":["aspire-table-2"],"protocol_id":"aspire-held-out-50-seeds"},{"id":"long-task--aspire","view_id":"long-task","configuration_id":"aspire","status":"reported","rate":"38.3","successes":null,"episodes":500,"source_ids":["aspire-table-5"],"protocol_id":"aspire-libero90-zero-shot","evaluation_note":{"en":"Long zero-shot transfer (LIBERO-90 library)","zh":"Long 零样本迁移（LIBERO-90 技能库）"}},{"id":"long-swap--aspire","view_id":"long-swap","configuration_id":"aspire","status":"reported","rate":"22.6","successes":null,"episodes":500,"source_ids":["aspire-table-5"],"protocol_id":"aspire-libero90-zero-shot","evaluation_note":{"en":"Long zero-shot transfer (LIBERO-90 library)","zh":"Long 零样本迁移（LIBERO-90 技能库）"}},{"id":"libero-pro--aspire","view_id":"libero-pro","configuration_id":"aspire","status":"derived","rate":"61.36","successes":null,"episodes":null,"source_ids":["aspire-table-2","aspire-table-5"],"protocol_id":"aspire-eight-component-mean","derived_from":["spatial-task--aspire","spatial-swap--aspire","object-task--aspire","object-swap--aspire","goal-task--aspire","goal-swap--aspire","long-task--aspire","long-swap--aspire"],"calculation":"Unweighted arithmetic mean of the eight displayed percentages; six main-suite and two Long zero-shot results.","evaluation_note":{"en":"Eight-score arithmetic mean","zh":"八项算术平均"}},{"id":"spatial-task--rpent-flash-mode","view_id":"spatial-task","configuration_id":"rpent-flash-mode","status":"reported","rate":"79.00","successes":79,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"spatial-swap--rpent-flash-mode","view_id":"spatial-swap","configuration_id":"rpent-flash-mode","status":"reported","rate":"70.00","successes":70,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"object-task--rpent-flash-mode","view_id":"object-task","configuration_id":"rpent-flash-mode","status":"reported","rate":"86.00","successes":86,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"object-swap--rpent-flash-mode","view_id":"object-swap","configuration_id":"rpent-flash-mode","status":"reported","rate":"93.00","successes":93,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"goal-task--rpent-flash-mode","view_id":"goal-task","configuration_id":"rpent-flash-mode","status":"reported","rate":"74.00","successes":74,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"goal-swap--rpent-flash-mode","view_id":"goal-swap","configuration_id":"rpent-flash-mode","status":"reported","rate":"65.00","successes":65,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"long-task--rpent-flash-mode","view_id":"long-task","configuration_id":"rpent-flash-mode","status":"reported","rate":"60.00","successes":60,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"long-swap--rpent-flash-mode","view_id":"long-swap","configuration_id":"rpent-flash-mode","status":"reported","rate":"54.00","successes":54,"episodes":100,"source_ids":["flash-contributor-800-outcomes"],"protocol_id":"rpent-pro-flash-mode"},{"id":"robocasa-atomic-seen--gpt-6-astra-low","view_id":"robocasa-atomic-seen","configuration_id":"gpt-6-astra-low","status":"reported","rate":"87.78","successes":79,"episodes":90,"source_ids":["robocasa-astra-contributor-250-outcomes","contributor-settings-20260915"],"protocol_id":"contributor-target50-astra-five-seed"},{"id":"robocasa-composite-seen--gpt-6-astra-low","view_id":"robocasa-composite-seen","configuration_id":"gpt-6-astra-low","status":"reported","rate":"43.75","successes":35,"episodes":80,"source_ids":["robocasa-astra-contributor-250-outcomes","contributor-settings-20260915"],"protocol_id":"contributor-target50-astra-five-seed"},{"id":"robocasa-composite-unseen--gpt-6-astra-low","view_id":"robocasa-composite-unseen","configuration_id":"gpt-6-astra-low","status":"reported","rate":"42.50","successes":34,"episodes":80,"source_ids":["robocasa-astra-contributor-250-outcomes","contributor-settings-20260915"],"protocol_id":"contributor-target50-astra-five-seed"},{"id":"libero-pro--qwen3-6-27b-no-reasoning","view_id":"libero-pro","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"70.63","successes":565,"episodes":800,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"},{"id":"spatial-task--qwen3-6-27b-no-reasoning","view_id":"spatial-task","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"82.00","successes":82,"episodes":100,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"},{"id":"spatial-swap--qwen3-6-27b-no-reasoning","view_id":"spatial-swap","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"78.00","successes":78,"episodes":100,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"},{"id":"object-task--qwen3-6-27b-no-reasoning","view_id":"object-task","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"83.00","successes":83,"episodes":100,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"},{"id":"object-swap--qwen3-6-27b-no-reasoning","view_id":"object-swap","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"84.00","successes":84,"episodes":100,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"},{"id":"goal-task--qwen3-6-27b-no-reasoning","view_id":"goal-task","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"68.00","successes":68,"episodes":100,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"},{"id":"goal-swap--qwen3-6-27b-no-reasoning","view_id":"goal-swap","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"68.00","successes":68,"episodes":100,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"},{"id":"long-task--qwen3-6-27b-no-reasoning","view_id":"long-task","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"61.00","successes":61,"episodes":100,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"},{"id":"long-swap--qwen3-6-27b-no-reasoning","view_id":"long-swap","configuration_id":"qwen3-6-27b-no-reasoning","status":"reported","rate":"41.00","successes":41,"episodes":100,"source_ids":["contributor-qwen-costs-20260918"],"protocol_id":"rpent-pro-qwen-eight-suites"}],"sources":[{"id":"paper-table-2","url":"https://arxiv.org/html/2607.08448v4#S3.T2"},{"id":"paper-table-3","url":"https://arxiv.org/html/2607.08448v4#S3.T3"},{"id":"paper-table-4","url":"https://arxiv.org/html/2607.08448v4#S3.T4"},{"id":"paper-table-6","url":"https://arxiv.org/html/2607.08448v4#S3.T6"},{"id":"astra-long-20260907","report_sha256":"627d6d8a95fb1e10357961694867cd0bf0a2aa9011c96c8a33504b904cb96c80"},{"id":"astra-pro-remaining-20260913","report_sha256":"627d6d8a95fb1e10357961694867cd0bf0a2aa9011c96c8a33504b904cb96c80"},{"id":"contributor-20260915","kind":"contributor-confirmed"},{"id":"contributor-settings-20260915","kind":"contributor-confirmed"},{"id":"contributor-correction-20260916","kind":"contributor-confirmed","note":"Corrected model labels and aggregate scores; removed requested configurations. No missing suite scores inferred."},{"id":"repo-flash-mode-800","url":"https://github.com/RLinf/RPent/blob/c19727c7bbdd277cd86a985aae3f2741ba01df7a/docs/source-en/rst_source/usage/task_card.rst","note":"581 successes across all 800 LIBERO-PRO cases; missing source traces count as failures. Molmo is used for visual localization, not planning."},{"id":"repo-robotwin-20260915","url":"https://github.com/RLinf/RPent/blob/849143bf740a562367345cec0de9ef4657dafd73/docs/source-en/rst_source/usage/robotwin.rst"},{"id":"xiaomi-official-robocasa365","url":"https://robocasa.ai/leaderboard.html","submission_url":"https://github.com/robocasa-benchmark/leaderboard/blob/main/submissions_md/Xiaomi-Robotics_2026_07_08.md","checked_at":"2026-09-16","environment_split":"pretrain","note":"Published 50-task benchmark scores. Displayed alongside RPent by request; protocol equivalence has not been verified. Episode counts for this reported batch are unspecified here."},{"id":"xiaomi-paper-v2-table-3","url":"https://arxiv.org/html/2607.15330v2#S3.T3"},{"id":"aspire-table-2","url":"https://arxiv.org/html/2607.00272v1#A2.T2","note":"Table 2 main LIBERO-Pro results; Pos maps to Swap, Task maps to Task. Ten tasks and seeds 1-50 per suite. Published rounded rates are preserved, not converted to integer successes. Six-item Overall 72% is not an eight-suite Overall."},{"id":"aspire-table-5","url":"https://arxiv.org/html/2607.00272v1#A3.T5","note":"Table 5, N=90 zero-shot library transfer: Task 0.383, Pos 0.226. A different evaluation regime from the six main suites; no combined Overall is inferred."},{"id":"flash-published-family-counts","url":"https://github.com/RLinf/misc/blob/main/rpent/task_card/task_card_libero_pro_performance_time.png","note":"Exact printed titles: Spatial 149/200, Object 179/200, Goal 139/200, Long 114/200. Sum 581/800. Cross-check only; independent Task/Swap scores come from contributor outcome records, not digitized bar heights."},{"id":"molmo2-model-card","url":"https://huggingface.co/allenai/Molmo2-8B","note":"Official model identity. RPent uses Molmo2-8B for visual localization only."},{"id":"flash-contributor-800-outcomes","type":"contributor_archive","artifact":"task_card.zip","sha256":"a997e5a0f823abf2402e1374e22a068c43dfecc35a778a185d0274efd45e31e2","note":"Eight Task/Swap aggregates from 800 unique contributor result.json cases, checked against summary.json and published family totals. Each component includes all 100 expected cases (task IDs 0–9, seeds 0–9). The 20 no-card cases remain in the denominator and are not counted as successes.","aggregates":{"spatial_task":{"successes":79,"episodes":100,"outcomes":{"success":79,"failure":21},"rate":"79.00"},"spatial_swap":{"successes":70,"episodes":100,"outcomes":{"success":70,"failure":30},"rate":"70.00"},"object_task":{"successes":86,"episodes":100,"outcomes":{"success":86,"failure":14},"rate":"86.00"},"object_swap":{"successes":93,"episodes":100,"outcomes":{"success":93,"failure":7},"rate":"93.00"},"goal_task":{"successes":74,"episodes":100,"outcomes":{"failure":26,"success":74},"rate":"74.00"},"goal_swap":{"successes":65,"episodes":100,"outcomes":{"no_card":10,"failure":25,"success":65},"rate":"65.00"},"long_task":{"successes":60,"episodes":100,"outcomes":{"success":60,"failure":40},"rate":"60.00"},"long_swap":{"successes":54,"episodes":100,"outcomes":{"success":54,"failure":36,"no_card":10},"rate":"54.00"}}},{"id":"robocasa-astra-contributor-250-outcomes","kind":"contributor_archive","artifact":"robocasa_astra.zip","sha256":"3ee89135bb69f0e6d29770f6103f4b53429481f9efde619ca6e7360597ce702c","environment_split":"target","tasks":50,"seeds":[1,2,3,4,5],"episodes":250,"successes":148,"groups":{"atomic":{"tasks":18,"successes":79,"episodes":90,"failures":11,"rate":"87.78"},"composite_seen":{"tasks":16,"successes":35,"episodes":80,"failures":45,"rate":"43.75"},"composite_unseen":{"tasks":16,"successes":34,"episodes":80,"failures":46,"rate":"42.50"}},"note":"250 unique contributor result.json outcomes match summary.json and final trace terminated flags. Five seeds per task make task-weighted Overall equal to 148/250. This corrects the previously assumed 340-case denominator; no missing cases are inferred. Model settings retain contributor confirmation."},{"id":"contributor-qwen-costs-20260918","type":"contributor_report","note":"Contributor-provided Qwen eight-suite counts and cost table. Mean elapsed time includes all evaluation episodes (success, failure, and timeout); tokens count evaluation-stage output only. No unreported planner, hardware, or token accounting details are inferred."}],"astra":{"completed":800,"successes":741,"failures":59,"overall_rate":"92.63","memory_batches":[{"campaign_id":"libero_long_gpt6_astra_20260907","suites":["long-task","long-swap"]},{"campaign_id":"libero_pro_remaining_gpt6_astra_20260913","suites":["spatial-task","spatial-swap","object-task","object-swap","goal-task","goal-swap"],"manifest_sha256":"f08702d7c13d9b40a3127b64765ad4d336d022be028396d5f873d7fc4c4c4928"}],"suites":[{"view_id":"spatial-task","suite":"Spatial Task","dataset":"libero_spatial_task","completed":100,"planned":100,"successes":100,"failures":0,"remaining":0,"rate":"100.00","status":"complete"},{"view_id":"spatial-swap","suite":"Spatial Swap","dataset":"libero_spatial_swap","completed":100,"planned":100,"successes":98,"failures":2,"remaining":0,"rate":"98.00","status":"complete"},{"view_id":"object-task","suite":"Object Task","dataset":"libero_object_task","completed":100,"planned":100,"successes":100,"failures":0,"remaining":0,"rate":"100.00","status":"complete"},{"view_id":"object-swap","suite":"Object Swap","dataset":"libero_object_swap","completed":100,"planned":100,"successes":99,"failures":1,"remaining":0,"rate":"99.00","status":"complete"},{"view_id":"goal-task","suite":"Goal Task","dataset":"libero_goal_task","completed":100,"planned":100,"successes":88,"failures":12,"remaining":0,"rate":"88.00","status":"complete"},{"view_id":"goal-swap","suite":"Goal Swap","dataset":"libero_goal_swap","completed":100,"planned":100,"successes":99,"failures":1,"remaining":0,"rate":"99.00","status":"complete"},{"view_id":"long-task","suite":"Long Task","dataset":"libero_10_task","completed":100,"planned":100,"successes":85,"failures":15,"remaining":0,"rate":"85.00","status":"complete"},{"view_id":"long-swap","suite":"Long Swap","dataset":"libero_10_swap","completed":100,"planned":100,"successes":72,"failures":28,"remaining":0,"rate":"72.00","status":"complete"}]},"sections":[{"id":"libero-pro","name":"LIBERO-PRO","heading":{"en":"Eight-suite evaluation","zh":"八套件评测"},"summary":{"en":"Astra · low · reasoning: 92.63% (741/800)","zh":"Astra · low · reasoning：92.63%（741/800）"},"context":{"en":"GPT-6 Astra: Long Task/Swap and the other six suites use separate memory-file snapshots frozen after their respective exploration phases, with no updates during evaluation. Overall combines two non-overlapping batches: Long 157/200 plus the other suites 584/600, giving 741/800 (92.63%); the 800 episodes do not share a single memory snapshot.","zh":"GPT-6 Astra：Long Task/Swap 与其余六套件使用各自探索后冻结的 memory 文件快照，评测期间不更新。Overall 合并两个不重叠批次：Long 157/200，加上其余套件 584/600，得到 741/800（92.63%）；并非全部回合共享同一份 memory 快照。"},"default_view":"libero-pro","views":["libero-pro","spatial-task","spatial-swap","object-task","object-swap","goal-task","goal-swap","long-task","long-swap"],"notes":{"en":"ASPIRE: Long Task and Long Swap use zero-shot transfer from the LIBERO-90 skill library.","zh":"ASPIRE：Long Task 和 Long Swap 使用 LIBERO-90 技能库进行 zero-shot 迁移。"}},{"id":"standard-libero","name":"LIBERO","heading":{"en":"Four-suite evaluation","zh":"四套件评测"},"default_view":"standard-libero","views":["standard-libero","standard-spatial","standard-object","standard-goal","standard-long"]},{"id":"robocasa","name":"RoboCasa365 · Target50","heading":{"en":"50 tasks · task-weighted Overall","zh":"50 个任务 · Overall 按任务等权"},"default_view":"robocasa","views":["robocasa","robocasa-atomic-seen","robocasa-composite-seen","robocasa-composite-unseen"]},{"id":"robotwin","name":"RoboTwin","heading":{"en":"Clean → Randomized","zh":"Clean → Randomized"},"summary":{"en":"50 tasks · 250 episodes","zh":"50 个任务 · 250 回合"},"default_view":"robotwin","views":["robotwin"]}],"assets":["ellipsis.svg","download.svg","arrow-down.svg"],"cost_results":[{"id":"libero-pro--gpt-5-6-xhigh","benchmark_id":"libero-pro","configuration_id":"gpt-5-6-xhigh","mean_elapsed_seconds":529.23,"total_output_tokens":3635426,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"libero-pro--gpt-5-6-no-reasoning","benchmark_id":"libero-pro","configuration_id":"gpt-5-6-no-reasoning","mean_elapsed_seconds":344.17,"total_output_tokens":2569676,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"libero-pro--gpt-6-astra-low","benchmark_id":"libero-pro","configuration_id":"gpt-6-astra-low","mean_elapsed_seconds":412.14,"total_output_tokens":3364938,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"libero-pro--qwen3-6-27b-no-reasoning","benchmark_id":"libero-pro","configuration_id":"qwen3-6-27b-no-reasoning","mean_elapsed_seconds":626.3,"total_output_tokens":3270754,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"libero-pro--rpent-flash-mode","benchmark_id":"libero-pro","configuration_id":"rpent-flash-mode","mean_elapsed_seconds":60.19,"total_output_tokens":0,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"robocasa--gpt-5-6-xhigh","benchmark_id":"robocasa","configuration_id":"gpt-5-6-xhigh","mean_elapsed_seconds":1197.56,"total_output_tokens":5258391,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"robocasa--gpt-5-6-no-reasoning","benchmark_id":"robocasa","configuration_id":"gpt-5-6-no-reasoning","mean_elapsed_seconds":1013.21,"total_output_tokens":4792104,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"robocasa--gpt-6-astra-low","benchmark_id":"robocasa","configuration_id":"gpt-6-astra-low","mean_elapsed_seconds":1168.95,"total_output_tokens":5894436,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"robotwin--gpt-5-6-xhigh","benchmark_id":"robotwin","configuration_id":"gpt-5-6-xhigh","mean_elapsed_seconds":1828.7,"total_output_tokens":4763915,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"robotwin--gpt-5-6-no-reasoning","benchmark_id":"robotwin","configuration_id":"gpt-5-6-no-reasoning","mean_elapsed_seconds":957.4,"total_output_tokens":2456401,"source_ids":["contributor-qwen-costs-20260918"]},{"id":"robotwin--gpt-6-astra-low","benchmark_id":"robotwin","configuration_id":"gpt-6-astra-low","mean_elapsed_seconds":1078.8,"total_output_tokens":2763641,"source_ids":["contributor-qwen-costs-20260918"]}]}</script><script src="table-sort.js"></script><script src="leaderboard.js"></script></body></html>
diff --git a/rpent/benchmarks/leaderboard-en-dark.png b/rpent/benchmarks/leaderboard-en-dark.png
index 20fe9ba..e581e12 100644
Binary files a/rpent/benchmarks/leaderboard-en-dark.png and b/rpent/benchmarks/leaderboard-en-dark.png differ
diff --git a/rpent/benchmarks/leaderboard-en-light.png b/rpent/benchmarks/leaderboard-en-light.png
index 1baa09d..ffe4fb9 100644
Binary files a/rpent/benchmarks/leaderboard-en-light.png and b/rpent/benchmarks/leaderboard-en-light.png differ
diff --git a/rpent/benchmarks/leaderboard-zh-dark.png b/rpent/benchmarks/leaderboard-zh-dark.png
index daa340a..e243473 100644
Binary files a/rpent/benchmarks/leaderboard-zh-dark.png and b/rpent/benchmarks/leaderboard-zh-dark.png differ
diff --git a/rpent/benchmarks/leaderboard-zh-light.png b/rpent/benchmarks/leaderboard-zh-light.png
index f6cc93b..372da02 100644
Binary files a/rpent/benchmarks/leaderboard-zh-light.png and b/rpent/benchmarks/leaderboard-zh-light.png differ
diff --git a/rpent/benchmarks/leaderboard.css b/rpent/benchmarks/leaderboard.css
index a304ac4..a1ff01a 100644
--- a/rpent/benchmarks/leaderboard.css
+++ b/rpent/benchmarks/leaderboard.css
@@ -22,8 +22,11 @@ body,button,select,input,textarea,table,code,pre,kbd{font-family:var(--serif)}
 .legend .astra{background:var(--astra)}
 .comparison-matrix>summary{font-size:20px}
 .comparison-matrix table,.comparison-matrix .matrix-label{font-size:16px}
+.cost-section{background:var(--band);border-top:4px solid var(--best);padding:30px 0 24px}.cost-section h2{font-size:27px}.cost-group{margin-top:24px}.cost-group h3{font-size:21px}.cost-group table{font-size:16px;min-width:340px;table-layout:fixed}.cost-group th{font-size:14px;white-space:normal}.cost-group th:first-child{width:42%}.cost-group th,.cost-group td{padding:10px 8px}.cost-group td:first-child{overflow-wrap:anywhere}.cost-group .table-wrap{max-width:100%}th[aria-sort=ascending]{color:var(--best)}th[aria-sort=ascending] img{opacity:1;transform:rotate(180deg)}
+@media(max-width:700px){.cost-group table{font-size:14px}.cost-section h2{font-size:23px}.cost-group h3{font-size:19px}}
 .comparison-matrix thead th{font-size:14px}
 .comparison-matrix .matrix-label small{font-size:12px}
+.cost-group .matrix-label{font-size:inherit}.cost-group .matrix-label small,.cost-method small{display:block;font-size:12px;margin-top:4px}
 footer{background:var(--band)}
 th[aria-sort=ascending]{color:var(--best)}th[aria-sort=ascending] img{opacity:1;transform:rotate(180deg)}
 footer{max-width:none;padding-left:max(var(--gutter),calc((100% - 1344px)/2));padding-right:max(var(--gutter),calc((100% - 1344px)/2))}
diff --git a/rpent/benchmarks/leaderboard.js b/rpent/benchmarks/leaderboard.js
index a9df3cf..22c8c5f 100644
--- a/rpent/benchmarks/leaderboard.js
+++ b/rpent/benchmarks/leaderboard.js
@@ -32,10 +32,12 @@
     "backTop": "Back to top ↑",
     "view": "Evaluation",
     "rate": "Success rate",
-    "method": "Method / model",
+    "method": "Method",
+    "meanTime": "Mean time / episode (s)",
+    "outputTokens": "Total output tokens",
     "unreported": "Not reported",
     "modelUnknown": "Model not reported",
-    "noReasoning": "no reasoning",
+    "noReasoning": "no-reasoning",
     "table": "Results table",
     "download": "Download CSV",
     "print": "Print page",
@@ -50,10 +52,12 @@
     "backTop": "返回顶部 ↑",
     "view": "评测范围",
     "rate": "成功率",
-    "method": "方法 / 模型",
+    "method": "方法",
+    "meanTime": "平均每回合耗时（秒）",
+    "outputTokens": "总输出 token",
     "unreported": "未报告",
     "modelUnknown": "未报告模型",
-    "noReasoning": "无推理",
+    "noReasoning": "no-reasoning",
     "table": "结果明细表",
     "download": "下载 CSV",
     "print": "打印页面",
@@ -117,7 +121,7 @@
     const rows=d.configurations.filter(c=>columns.some(v=>v.record_ids.some(id=>records.get(id).configuration_id===c.id&&records.get(id).rate!==null)));
     return `<details class="comparison-matrix" data-details="${s.id}"><summary>${t('allScores')} <span>${rows.length} ${lang==='en'?'configurations':'配置'}</span></summary><div class="table-wrap" tabindex="0" role="region" aria-label="${h(s.name+' '+t('allScores'))}"><table><thead><tr><th>${t('method')}</th>${columns.map(v=>`<th class="rate">${h(tr(v.label))}</th>`).join('')}</tr></thead><tbody>${rows.map(c=>{
       const sample=columns.flatMap(allRows).find(r=>r.configuration_id===c.id&&r.rate!==null);
-      return `<tr data-method="${c.id}"><th scope="row"><div class="matrix-label"><span>${h(label(sample))}<small>${h(detailLabel(sample))}</small></span></div></th>${columns.map(v=>{
+      return `<tr data-method="${c.id}"><th scope="row"><div class="matrix-label"><span>${h(label(sample))}<small> ${h(detailLabel(sample))}</small></span></div></th>${columns.map(v=>{
         const r=allRows(v).find(r=>r.configuration_id===c.id);
         return `<td class="rate"${r?` data-matrix-record="${r.id}"`:''} title="${h(tr(r?.evaluation_note)||tr(v.label))}">${r?.rate!=null?r.rate+'%':`<span class="not-reported" aria-label="${t('unreported')}">—</span>`}</td>`;
       }).join('')}</tr>`;
@@ -136,13 +140,24 @@
   function setupTables(element,key) {
     window.RPentTables.setup(element,{key,language:lang,icon:asset('arrow-down.svg'),download:asset('download.svg')});
   }
+  function renderCosts() {
+    const element=document.getElementById('time-token-costs');
+    const groups=[['libero-pro','LIBERO-PRO'],['robocasa','RoboCasa365'],['robotwin','RoboTwin']];
+    element.innerHTML=`<div class="section-inner"><h2>Time &amp; Token Costs</h2>${groups.map(([id,name])=>{
+      const rows=d.cost_results.filter(r=>r.benchmark_id===id);
+      return `<section class="cost-group" data-cost-group="${id}"><h3>${name}</h3><div class="table-wrap" tabindex="0" role="region" aria-label="${name} Time &amp; Token Costs"><table data-sort-key="costs-${id}" data-sort-direction="ascending" data-highlight-best="false"><thead><tr><th>${t('method')}</th><th class="rate">${t('meanTime')}</th><th class="rate">${t('outputTokens')}</th></tr></thead><tbody>${rows.map(r=>{
+        return `<tr data-cost-record="${r.id}" data-method="${r.configuration_id}"><td><div class="matrix-label"><span>${h(label(r))}<small> ${h(detailLabel(r))}</small></span></div></td><td class="rate" data-value="${r.mean_elapsed_seconds}">${r.mean_elapsed_seconds.toLocaleString('en-US')}</td><td class="rate" data-value="${r.total_output_tokens}">${r.total_output_tokens.toLocaleString('en-US')}</td></tr>`;
+      }).join('')}</tbody></table></div></section>`;
+    }).join('')}</div>`;
+    setupTables(element,'costs');
+  }
   function render() {
     (options.embedded?document.host:document.documentElement).lang=lang==='en'?'en':'zh-CN';
     if(!options.embedded)document.title='RPent Leaderboard';
     document.querySelectorAll('[data-i18n]').forEach(el=>el.textContent=t(el.dataset.i18n));
     const language=document.getElementById('language');language.textContent=lang==='en'?'中文':'English';language.lang=lang==='en'?'zh-CN':'en';language.setAttribute('aria-label',lang==='en'?'切换为中文':'Switch to English');
     document.getElementById('leaderboards').innerHTML=d.sections.filter(s=>!s.parent).map(s=>`<section id="${s.id}" class="benchmark-band"><div class="benchmark-shell"><h2 class="benchmark-wordmark">${h(s.name)}</h2><div id="panel-${s.id}"></div>${d.sections.filter(c=>c.parent===s.id).map(c=>`<section id="${c.id}" class="benchmark-subsection"><div id="panel-${c.id}"></div></section>`).join('')}</div></section>`).join('');
-    d.sections.forEach(renderSection);hideTooltip();
+    d.sections.forEach(renderSection);renderCosts();hideTooltip();
   }
   function downloadCSV(rows, name) {
     const keys=['record_id','benchmark','view','method','model','planner','perception_model','reasoning','effort','success_rate_percent','successes','episodes','status','evaluation_note'];
diff --git a/rpent/benchmarks/results.json b/rpent/benchmarks/results.json
index 0da2503..c7a11e1 100644
--- a/rpent/benchmarks/results.json
+++ b/rpent/benchmarks/results.json
@@ -1,6 +1,6 @@
 {
   "schema_version": 2,
-  "checked_at": "2026-09-17",
+  "checked_at": "2026-09-18",
   "paper_revision": "2607.08448v4",
   "repository_revision": "43f32aa08cba07bd4d49a4bfa5eba4ef633e9b92",
   "configurations": [
@@ -197,6 +197,30 @@
       "model": "ASPIRE",
       "reasoning": null,
       "effort": null
+    },
+    {
+      "id": "qwen3-6-27b-no-reasoning",
+      "kind": "rpent",
+      "backend": null,
+      "model": "Qwen3.6 27B",
+      "reasoning": false,
+      "effort": null
+    },
+    {
+      "id": "gpt-5-6-xhigh",
+      "kind": "rpent",
+      "backend": "Codex",
+      "model": "GPT-5.6 Sol",
+      "reasoning": true,
+      "effort": "xhigh"
+    },
+    {
+      "id": "gpt-5-6-no-reasoning",
+      "kind": "rpent",
+      "backend": "Codex",
+      "model": "GPT-5.6 Sol",
+      "reasoning": false,
+      "effort": null
     }
   ],
   "views": [
@@ -299,7 +323,8 @@
         "spatial-task--rats",
         "spatial-task--pi-rlinf",
         "spatial-task--aspire",
-        "spatial-task--rpent-flash-mode"
+        "spatial-task--rpent-flash-mode",
+        "spatial-task--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -321,7 +346,8 @@
         "spatial-swap--rats",
         "spatial-swap--pi-rlinf",
         "spatial-swap--aspire",
-        "spatial-swap--rpent-flash-mode"
+        "spatial-swap--rpent-flash-mode",
+        "spatial-swap--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -343,7 +369,8 @@
         "object-task--rats",
         "object-task--pi-rlinf",
         "object-task--aspire",
-        "object-task--rpent-flash-mode"
+        "object-task--rpent-flash-mode",
+        "object-task--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -365,7 +392,8 @@
         "object-swap--rats",
         "object-swap--pi-rlinf",
         "object-swap--aspire",
-        "object-swap--rpent-flash-mode"
+        "object-swap--rpent-flash-mode",
+        "object-swap--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -387,7 +415,8 @@
         "goal-task--rats",
         "goal-task--pi-rlinf",
         "goal-task--aspire",
-        "goal-task--rpent-flash-mode"
+        "goal-task--rpent-flash-mode",
+        "goal-task--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -409,7 +438,8 @@
         "goal-swap--rats",
         "goal-swap--pi-rlinf",
         "goal-swap--aspire",
-        "goal-swap--rpent-flash-mode"
+        "goal-swap--rpent-flash-mode",
+        "goal-swap--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -429,7 +459,8 @@
         "long-task--atomvla",
         "long-task--pi-rlinf",
         "long-task--aspire",
-        "long-task--rpent-flash-mode"
+        "long-task--rpent-flash-mode",
+        "long-task--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -449,7 +480,8 @@
         "long-swap--atomvla",
         "long-swap--pi-rlinf",
         "long-swap--aspire",
-        "long-swap--rpent-flash-mode"
+        "long-swap--rpent-flash-mode",
+        "long-swap--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -470,7 +502,8 @@
         "libero-pro--pi-rlinf",
         "libero-pro--opus-4-7-reported",
         "libero-pro--rpent-flash-mode",
-        "libero-pro--aspire"
+        "libero-pro--aspire",
+        "libero-pro--qwen3-6-27b-no-reasoning"
       ]
     },
     {
@@ -2841,6 +2874,123 @@
         "contributor-settings-20260915"
       ],
       "protocol_id": "contributor-target50-astra-five-seed"
+    },
+    {
+      "id": "libero-pro--qwen3-6-27b-no-reasoning",
+      "view_id": "libero-pro",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "70.63",
+      "successes": 565,
+      "episodes": 800,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
+    },
+    {
+      "id": "spatial-task--qwen3-6-27b-no-reasoning",
+      "view_id": "spatial-task",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "82.00",
+      "successes": 82,
+      "episodes": 100,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
+    },
+    {
+      "id": "spatial-swap--qwen3-6-27b-no-reasoning",
+      "view_id": "spatial-swap",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "78.00",
+      "successes": 78,
+      "episodes": 100,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
+    },
+    {
+      "id": "object-task--qwen3-6-27b-no-reasoning",
+      "view_id": "object-task",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "83.00",
+      "successes": 83,
+      "episodes": 100,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
+    },
+    {
+      "id": "object-swap--qwen3-6-27b-no-reasoning",
+      "view_id": "object-swap",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "84.00",
+      "successes": 84,
+      "episodes": 100,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
+    },
+    {
+      "id": "goal-task--qwen3-6-27b-no-reasoning",
+      "view_id": "goal-task",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "68.00",
+      "successes": 68,
+      "episodes": 100,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
+    },
+    {
+      "id": "goal-swap--qwen3-6-27b-no-reasoning",
+      "view_id": "goal-swap",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "68.00",
+      "successes": 68,
+      "episodes": 100,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
+    },
+    {
+      "id": "long-task--qwen3-6-27b-no-reasoning",
+      "view_id": "long-task",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "61.00",
+      "successes": 61,
+      "episodes": 100,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
+    },
+    {
+      "id": "long-swap--qwen3-6-27b-no-reasoning",
+      "view_id": "long-swap",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "status": "reported",
+      "rate": "41.00",
+      "successes": 41,
+      "episodes": 100,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ],
+      "protocol_id": "rpent-pro-qwen-eight-suites"
     }
   ],
   "sources": [
@@ -3045,6 +3195,11 @@
         }
       },
       "note": "250 unique contributor result.json outcomes match summary.json and final trace terminated flags. Five seeds per task make task-weighted Overall equal to 148/250. This corrects the previously assumed 340-case denominator; no missing cases are inferred. Model settings retain contributor confirmation."
+    },
+    {
+      "id": "contributor-qwen-costs-20260918",
+      "type": "contributor_report",
+      "note": "Contributor-provided Qwen eight-suite counts and cost table. Mean elapsed time includes all evaluation episodes (success, failure, and timeout); tokens count evaluation-stage output only. No unreported planner, hardware, or token accounting details are inferred."
     }
   ],
   "astra": {
@@ -3257,5 +3412,117 @@
     "ellipsis.svg",
     "download.svg",
     "arrow-down.svg"
+  ],
+  "cost_results": [
+    {
+      "id": "libero-pro--gpt-5-6-xhigh",
+      "benchmark_id": "libero-pro",
+      "configuration_id": "gpt-5-6-xhigh",
+      "mean_elapsed_seconds": 529.23,
+      "total_output_tokens": 3635426,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "libero-pro--gpt-5-6-no-reasoning",
+      "benchmark_id": "libero-pro",
+      "configuration_id": "gpt-5-6-no-reasoning",
+      "mean_elapsed_seconds": 344.17,
+      "total_output_tokens": 2569676,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "libero-pro--gpt-6-astra-low",
+      "benchmark_id": "libero-pro",
+      "configuration_id": "gpt-6-astra-low",
+      "mean_elapsed_seconds": 412.14,
+      "total_output_tokens": 3364938,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "libero-pro--qwen3-6-27b-no-reasoning",
+      "benchmark_id": "libero-pro",
+      "configuration_id": "qwen3-6-27b-no-reasoning",
+      "mean_elapsed_seconds": 626.3,
+      "total_output_tokens": 3270754,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "libero-pro--rpent-flash-mode",
+      "benchmark_id": "libero-pro",
+      "configuration_id": "rpent-flash-mode",
+      "mean_elapsed_seconds": 60.19,
+      "total_output_tokens": 0,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "robocasa--gpt-5-6-xhigh",
+      "benchmark_id": "robocasa",
+      "configuration_id": "gpt-5-6-xhigh",
+      "mean_elapsed_seconds": 1197.56,
+      "total_output_tokens": 5258391,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "robocasa--gpt-5-6-no-reasoning",
+      "benchmark_id": "robocasa",
+      "configuration_id": "gpt-5-6-no-reasoning",
+      "mean_elapsed_seconds": 1013.21,
+      "total_output_tokens": 4792104,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "robocasa--gpt-6-astra-low",
+      "benchmark_id": "robocasa",
+      "configuration_id": "gpt-6-astra-low",
+      "mean_elapsed_seconds": 1168.95,
+      "total_output_tokens": 5894436,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "robotwin--gpt-5-6-xhigh",
+      "benchmark_id": "robotwin",
+      "configuration_id": "gpt-5-6-xhigh",
+      "mean_elapsed_seconds": 1828.7,
+      "total_output_tokens": 4763915,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "robotwin--gpt-5-6-no-reasoning",
+      "benchmark_id": "robotwin",
+      "configuration_id": "gpt-5-6-no-reasoning",
+      "mean_elapsed_seconds": 957.4,
+      "total_output_tokens": 2456401,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    },
+    {
+      "id": "robotwin--gpt-6-astra-low",
+      "benchmark_id": "robotwin",
+      "configuration_id": "gpt-6-astra-low",
+      "mean_elapsed_seconds": 1078.8,
+      "total_output_tokens": 2763641,
+      "source_ids": [
+        "contributor-qwen-costs-20260918"
+      ]
+    }
   ]
 }
diff --git a/rpent/benchmarks/table-sort.js b/rpent/benchmarks/table-sort.js
index fc139b7..8674419 100644
--- a/rpent/benchmarks/table-sort.js
+++ b/rpent/benchmarks/table-sort.js
@@ -15,21 +15,22 @@
   function sort(table, column) {
     const state=table._rpentSort;
     state.column=column;saved.set(state.key,column);
+    const ascending=column===state.idColumn||state.direction==='ascending';
     const rows=[...table.tBodies[0].rows].filter(row=>!row.dataset.total);
     rows.sort((a,b)=>{
       const av=valueOf(a.cells[column]),bv=valueOf(b.cells[column]);
       return av===null ? bv===null?collator.compare(a.dataset.sortId,b.dataset.sortId):1
-        : bv===null?-1:(column===state.idColumn?av-bv:bv-av)||collator.compare(a.dataset.sortId,b.dataset.sortId);
+        : bv===null?-1:(ascending?av-bv:bv-av)||collator.compare(a.dataset.sortId,b.dataset.sortId);
     });
     const total=table.tBodies[0].querySelector('[data-total]');
     rows.forEach(row=>table.tBodies[0].insertBefore(row,total));
     state.headers.forEach((th,i)=>{
-      if(state.columns.includes(i))th.setAttribute('aria-sort',i===column?(column===state.idColumn?'ascending':'descending'):'none');
+      if(state.columns.includes(i))th.setAttribute('aria-sort',i===column?(ascending?'ascending':'descending'):'none');
     });
     const maximum=rows.length?valueOf(rows[0].cells[column]):null;
     for(const row of rows){
       for(const cell of row.cells)cell.classList.remove('metric-best');
-      if(column!==state.idColumn&&maximum!==null&&valueOf(row.cells[column])===maximum)row.cells[column].classList.add('metric-best');
+      if(state.highlightBest&&column!==state.idColumn&&maximum!==null&&valueOf(row.cells[column])===maximum)row.cells[column].classList.add('metric-best');
     }
   }
   function exportTable(table) {
@@ -56,12 +57,13 @@
         row.dataset.sortId??=row.dataset.method??row.dataset.tableRecord??row.dataset.astraTask??row.dataset.roboTask??row.dataset.paperTasks??row.cells[0].textContent.trim()+'-'+i;
         if(/^(Total|合计)$/i.test(row.cells[0].textContent.trim()))row.dataset.total='true';
       });
-      table._rpentSort={key,columns,headers,idColumn,column:preferred.i};
+      const direction=table.dataset.sortDirection??'descending';
+      table._rpentSort={key,columns,headers,idColumn,column:preferred.i,direction,highlightBest:table.dataset.highlightBest!=='false'};
       headers.forEach((th,i)=>{
         th.dataset.label=th.textContent.trim();
         if(!columns.includes(i))return;
         const button=document.createElement('button');button.type='button';button.className='sort-heading';
-        button.textContent=th.dataset.label;button.title=(i===idColumn?(zh?'按任务 ID 升序：':'Sort task ID ascending: '):(zh?'按此列降序：':'Sort descending: '))+th.dataset.label;
+        button.textContent=th.dataset.label;button.title=(i===idColumn?(zh?'按任务 ID 升序：':'Sort task ID ascending: '):direction==='ascending'?(zh?'按此列升序：':'Sort ascending: '):(zh?'按此列降序：':'Sort descending: '))+th.dataset.label;
         const img=document.createElement('img');img.src=options.icon;img.alt='';img.width=12;img.height=12;
         button.append(img);button.addEventListener('click',()=>sort(table,i));th.replaceChildren(button);
       });