Skip to content

Add Coder Eval to 5a · Eval frameworks & harnesses #61

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
uipreliga wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add Coder Eval to 5a · Eval frameworks & harnesses #61

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,6 +165,7 @@ Most "awesome" lists are link dumps. This one is **annotated and verified**: eve
- **[UpTrain](https://github.com/uptrain-ai/uptrain)** — <https://github.com/uptrain-ai/uptrain> — 20+ preconfigured checks + root-cause analysis on failures.
- **[HF `evaluate`](https://github.com/huggingface/evaluate)** — <https://github.com/huggingface/evaluate> — classic metrics library, ⚠️ maintenance mode (use lighteval for LLMs).
- **[Harbor](https://github.com/harbor-framework/harbor)** — harbor-framework (Laude Institute / Stanford) — <https://github.com/harbor-framework/harbor> — 🆕 framework for running agent evals + creating/using RL environments; powers Terminal-Bench 2.0. ~2.7k★. ⚠️ name overloaded (cf. `av/harbor` local-LLM toolkit).
- **[Coder Eval](https://github.com/UiPath/coder_eval)** — UiPath — <https://github.com/UiPath/coder_eval> · <https://coder-eval.com/docs> — 🆕 runs a real coding agent (Claude Code / Codex / Gemini) in a sandbox against declarative YAML tasks and grades the artifacts *and* the trajectory it produced: 14 criterion types, weighted 0.0–1.0 credit, per-tool token/USD telemetry, and a 5-layer A/B variant resolver so model-vs-model or skill-on-vs-off runs share one task set. Its distinguishing primitive is treating **skill activation as a measurable variable** — a `skill_triggered` criterion fanned over a labelled dataset yields suite-level precision/recall/F1 thresholds, catching the silent retrieval regressions that outcome-only scoring charges to the model (cf. §3). Harness-level, not leaderboard-level: the suite is your own tasks and skills. ~0.1k★.

### 5b · TypeScript/JS-native eval runners
- **[evalite](https://github.com/mattpocock/evalite)** — Matt Pocock — <https://github.com/mattpocock/evalite> — 🆕 local-first eval runner on Vitest; `.eval.ts` files, web UI, cost-aware.
Expand Down
Loading