Skip to content

Pull requests: open-compass/opencompass

New pull request New
87 Open 1,319 Closed
87 Open 1,319 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

ci: pin jlumbroso/free-disk-space to a full commit SHA
#2533 opened Jul 13, 2026 by kobihikri Loading…
@bittersweet1999
Fix wikitext ppl evaluation without references
#2532 opened Jul 13, 2026 by ssiq Collaborator Loading…
1
@bittersweet1999
Pin mmengine-lite runtime dependency
#2531 opened Jul 13, 2026 by ssiq Collaborator Loading…
3
@bittersweet1999
[Fix] Handle tokenizers with read-only pad_token_id property
#2526 opened Jul 11, 2026 by feiiiiii5 Loading…
4 of 5 tasks
1
@tonysy
feat(dataset): add CHHallu-Src v1 — Chinese history hallucination & source-attribution benchmark
#2525 opened Jul 11, 2026 by lizhuojunx86 Loading…
@tonysy
fix(MedCalc_Bench): guard calid-69 ground_truth regex match (AttributeError)
#2523 opened Jul 9, 2026 by WatchTree-19 Loading…
@acylam
fix(evaluator): guard IndexError on truncated judge choice (JudgeEvaluator/RMBEvaluator)
#2522 opened Jul 9, 2026 by WatchTree-19 Loading…
@acylam
Fix dataloader batching for None batch size
#2520 opened Jul 9, 2026 by ssiq Collaborator Loading…
1
@acylam
fix: let AIME2024 use model max output length
#2518 opened Jul 9, 2026 by ssiq Collaborator Loading…
1
@acylam
Fix MMLU Pro psot processor BUG
#2517 opened Jul 9, 2026 by ssiq Collaborator Loading…
1
@acylam
Add robust HumanEval postprocess for chat outputs
#2515 opened Jul 8, 2026 by Ding-god Loading…
3 of 6 tasks
1
Add Helium Market Resolution benchmark
#2507 opened Jul 3, 2026 by connerlambden Loading…
1 of 2 tasks
@tonysy
1
[Fix] Extract the final answer in GPQA simple-eval predictions
#2496 opened Jun 27, 2026 by Hibbert133 Contributor Loading…
4 of 6 tasks
@tonysy
1
Add BGPT REFUTE benchmark
#2471 opened Jun 5, 2026 by connerlambden Loading…
@tonysy
1
Add optional juryeval integration for LLM-as-Judge metrics
#2465 opened May 31, 2026 by py-ai-dev Loading…
@tonysy
[Fix] Combine split eval results in default summarizer
#2451 opened May 15, 2026 by yhzhu99 Contributor Loading…
1
@tonysy
Add support for extra headers in Claude SDK API
#2445 opened May 8, 2026 by SongYippee Loading…
@tonysy
1
feat: add LiteLLM as AI gateway model backend
#2441 opened Apr 22, 2026 by RheagalFire Loading…
4 of 6 tasks
2
fix: handle all test_range types in SizePartitioner.get_cost
#2438 opened Apr 20, 2026 by octo-patch Loading…
1
@bittersweet1999
[Fix] Use pre-tokenized prompts in VLLMwithChatTemplate to avoid modifying model input
#2434 opened Apr 15, 2026 by suhmily10 Loading…
1 of 2 tasks
feat: upgrade MiniMax default model to M3
#2418 opened Mar 20, 2026 by octo-patch Loading…
3 tasks done
@tonysy
[Fix] CEval ModelScope load and HF generate for causal LMs
#2416 opened Mar 19, 2026 by DeliWang Loading…
6 tasks
@acylam
1
Add support for Azure OpenAI models and managed identity auth
#2415 opened Mar 18, 2026 by jgbradley1 Loading…
2 of 6 tasks
[Fix] Fix eval stage is extremely slow
#2409 opened Mar 5, 2026 by xming521 Loading…
6 tasks
@acylam
3
fix: correct typo 'seperated' to 'separated'
#2397 opened Feb 9, 2026 by thecaptain789 Loading…
@bittersweet1999
ProTip! no:milestone will show everything without a milestone.