Skip to content

Pull requests: aisa-group/PostTrainBench

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

judges: migrate gpt-5.4 → gpt-5.6-terra (post-deprecation)
#74 opened Sep 7, 2026 by hrdkbhatnagar Collaborator Loading…
Add MiniMax Code agent integration
#69 opened Aug 16, 2026 by hetaoBackend Loading…
fix(harbor): keep reward output numeric
#68 opened Aug 11, 2026 by SergioHC95 Loading…
fix(harbor): keep contamination judge verifier-only
#67 opened Aug 11, 2026 by SergioHC95 Loading…
Fix BFCL default argument scoring
#63 opened Jul 23, 2026 by wise-east Contributor Loading…
Add Docker-native container image
#58 opened Jun 29, 2026 by zimuwang-real Loading…
Fix AIME 2025 numeric scoring (equality, not suffix match)
#45 opened May 20, 2026 by wise-east Contributor Loading…
Add Harbor Framework Support feature New feature or request
#8 opened Jan 13, 2026 by hrdkbhatnagar Collaborator Loading…
3 tasks
V1 Release
ProTip! Add no:assignee to see everything that’s not assigned.