DeepSeek V4 Pro high benchmark results - #27
Open
QingyunQian wants to merge 1 commit into
Open
Conversation
QingyunQian
changed the title
QingyunQian
marked this pull request as ready for review
August 13, 2026 15:17
Member
|
thanks for the nice contribution, though the model looks so-so |
Member
|
seems that luna is the option wayyy better than deepseek models (both pro and flash) in terms of time cost, money cost, intelligence and capability. very inspiring results |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds the complete DeepSeek V4 Pro (high) ORBIT-Q TensorCircuit benchmark archive and publication-ready result figures.
deepseek-v4-pro, reasoning efforthighgpt-5.6-sol, reasoning efforthigh1.8.0.dev20260726sha256:b059c5fa7f75702f9afbf94ec7866e102ac32afd59d25634ec0aca0fd56e283319fe27b83eaf668b3df32d1a68902b08cbe28585f189290769018eb16d9278950201238ec2983907e2891f5319f5fff2d00844d5The earlier DeepSeek V4 Pro campaign run with TensorCircuit 1.7 is explicitly excluded; this PR contains only the clean TC 1.8 campaign selected for reporting.
Results
The archive includes selected solutions, rewards, solver trajectories, verifier/audit details, runtime and token accounting, configs, task/image provenance, PNG/PDF/SVG figures, and reproduction/verification tools.
Validation
Verified: 12 valid outcomes, fixed task hashes, DeepSeek V4 Pro/high solver, GPT-5.6 Sol/high audit, pinned TC 1.8 image, and valid figures.