Skip to content

Pull requests: EvolvingLMMs-Lab/lmms-eval

New pull request New
10 Open 753 Closed
10 Open 753 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

fix: handle internvl_hf video-only inputs and enable frame sampling
#1279 opened Mar 28, 2026 by akawincent Loading…
2
fix: preserve HME100k prediction case in OCRBench scoring
#1278 opened Mar 27, 2026 by akawincent Loading…
1
Fix the incompatibility issue caused by top_p=0 when using vllm to inference (#1265)
#1277 opened Mar 27, 2026 by akawincent Loading…
1
feat: add MMBench static evaluation mode (no OpenAI API needed)
#1276 opened Mar 26, 2026 by Luodian Loading…
3 tasks
feat: add process_results_use_image and video metadata dict support in task API
#1275 opened Mar 26, 2026 by Luodian Loading…
3 tasks
fix: improve evaluation logic across 10+ existing benchmarks
#1274 opened Mar 26, 2026 by Luodian Loading…
3 tasks
feat: add COVER and WM-aBench video understanding benchmarks
#1273 opened Mar 26, 2026 by Luodian Loading…
4 tasks
feat: add physics reasoning benchmarks (PhysBench, ContPhy, PhysGame, PhysicsRW, PhysReason)
#1272 opened Mar 26, 2026 by Luodian Loading…
4 tasks
feat: add VBench video generation evaluation benchmark
#1271 opened Mar 26, 2026 by Luodian Loading…
3 tasks
feat: add MiniMax as LLM judge provider
#1263 opened Mar 22, 2026 by octo-patch Loading…
3 tasks done
1
ProTip! Follow long discussions with comments:>50.