-
Notifications
You must be signed in to change notification settings - Fork 557
Pull requests: EvolvingLMMs-Lab/lmms-eval
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix: preserve HME100k prediction case in OCRBench scoring
#1278
opened Mar 27, 2026 by
akawincent
Contributor
Loading…
Fix the incompatibility issue caused by
top_p=0 when using vllm to inference (#1265)
#1277
opened Mar 27, 2026 by
akawincent
Contributor
Loading…
feat: add MMBench static evaluation mode (no OpenAI API needed)
#1276
opened Mar 26, 2026 by
Luodian
Contributor
Loading…
3 tasks
feat: add process_results_use_image and video metadata dict support in task API
#1275
opened Mar 26, 2026 by
Luodian
Contributor
Loading…
3 tasks
fix: improve evaluation logic across 10+ existing benchmarks
#1274
opened Mar 26, 2026 by
Luodian
Contributor
Loading…
3 tasks
feat: add COVER and WM-aBench video understanding benchmarks
#1273
opened Mar 26, 2026 by
Luodian
Contributor
Loading…
4 tasks
feat: add physics reasoning benchmarks (PhysBench, ContPhy, PhysGame, PhysicsRW, PhysReason)
#1272
opened Mar 26, 2026 by
Luodian
Contributor
Loading…
4 tasks
feat: add VBench video generation evaluation benchmark
#1271
opened Mar 26, 2026 by
Luodian
Contributor
Loading…
3 tasks
feat: add MiniMax as LLM judge provider
#1263
opened Mar 22, 2026 by
octo-patch
Loading…
3 tasks done
ProTip!
Updated in the last three days: updated:>2026-04-06.