Skip to content

Pull requests: open-compass/VLMEvalKit

New pull request New
21 Open 770 Closed
21 Open 770 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

Added EmoSet118K and MMIS datasets; integrated AndesVL model.
#1311 opened Nov 11, 2025 by agent-clement Loading…
Request to add SIBench evaluation code
#1310 opened Nov 9, 2025 by song2yu Loading…
[New Benchmark] Support Video-TT
#1309 opened Nov 9, 2025 by dongyh20 Loading…
[New Model] Add support for Insight-V
#1306 opened Nov 7, 2025 by dongyh20 Loading…
[Fix] replace 'cam' with 'can' in debug message
#1303 opened Nov 7, 2025 by lzpp2598 Loading…
Add code for rbdashmm 3/3.5 78b
#1301 opened Nov 4, 2025 by Graysonicc Loading…
1
Fix: Molmo Crash - AttributeError: 'NoneType' object has no attribute 'size'
#1297 opened Oct 30, 2025 by DrishtiShrrrma Loading…
README: Pin exact transformers for LLaVA-Next to avoid “Got USER: <image>” error
#1294 opened Oct 28, 2025 by DrishtiShrrrma Loading…
Official evaluation implementation of HiPhO Benchmark
#1293 opened Oct 28, 2025 by MarkovChain-why Loading…
2
add support for internvideo, videollama, keye and llava-onevision-1.5 WIP
#1244 opened Sep 22, 2025 by FangXinyu-0913 Loading…
@FangXinyu-0913
1
[security] Use https everywhere applicable
#1232 opened Sep 11, 2025 by clayrosenthal Loading…
[major] add tsv, xlsx, json fo PRED_FORMAT and csv, json for EVAL_FORMAT
#1172 opened Jul 20, 2025 by OliverLeeXZ Loading…
[Model] Add new model provider: AI/ML API
#1093 opened Jun 19, 2025 by D1m7asis Loading…
4 tasks done
3
Moondream refactor WIP
#1076 opened Jun 13, 2025 by snowclipsed • Draft
1
[Benchmark] Add GUI grounding: OSWorld-G WIP
#1020 opened May 27, 2025 by chenjix Loading…
1
WIP: Add Capture Dataset WIP
#974 opened May 2, 2025 by bodsul Loading…
2
fix(image_mcp.py): use consistant argument (#929)
#968 opened Apr 28, 2025 by MaoSong2022 Loading…
1
2
[Minor] Align MMMU evaluation method with official Pending
#966 opened Apr 28, 2025 by FangXinyu-0913 Loading…
[Model] Add new model: Prism
#622 opened Nov 22, 2024 by Myhs-phz Loading…
[Benchmark] Support Video MCQ with TaskMeAnything-v1-video-random as an example
#359 opened Aug 5, 2024 by weikaih04 Loading…
5
[Support] multiple process parallel inference large model on multi-gpu WIP
#298 opened Jul 19, 2024 by junming-yang Loading…
ProTip! Exclude everything labeled bug with -label:bug.