
OpenCompass
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
👋 join us on Discord and WeChat
follow us on Github
OpenCompass is a platform focused on evaluation of AGI, include Large Language Model and Multi-modality Model. We aim to:
- develop high-quality libraries to reduce the difficulties in evaluation
- provide convincing leaderboards for improving the understanding of the large models
- create powerful toolchains targeting a variety of abilities and tasks
- build solid benchmarks to support the large model research
Collections
1
spaces
11
pinned
Running
31
Open LMM Reasoning Leaderboard
🥇
A Leaderboard that demonstrates LMM reasoning capabilities
pinned
Running
5
Compass Academic Leaderboard
🦀
Compass Academic Leaderboard
pinned
Running
on
CPU Upgrade
654
Open VLM Leaderboard
🌎
VLMEvalKit Evaluation Results Collection
pinned
Running
21
MMBench Leaderboard
🚀
View and filter MMBench leaderboard data
pinned
Running
101
Open VLM Video Leaderboard
🌎
VLMEvalKit Eval Results in video understanding benchmark
pinned
Sleeping
4
CompassJudger Subjective Evaluation Learderboard
🌎
CompassJudger Subjective Evaluation Learderboard
models
8

opencompass/anah-7b
Text Classification
•
Updated
•
16

opencompass/anah-20b
Text Classification
•
Updated
•
11

opencompass/anah-v2
Text Classification
•
Updated
•
99
•
3

opencompass/CompassJudger-1-14B-Instruct
Text Generation
•
Updated
•
56
•
2

opencompass/CompassJudger-1-32B-Instruct
Text Generation
•
Updated
•
1.86k
•
14

opencompass/CompassJudger-1-1.5B-Instruct
Updated
•
30
•
1

opencompass/CompassJudger-1-7B-Instruct
Updated
•
1.51k
•
8

opencompass/mixtral-8x7b-32k
Updated
•
1
datasets
9
opencompass/LiveMathBench
Viewer
•
Updated
•
283
•
881
•
4
opencompass/AIME2025
Viewer
•
Updated
•
30
•
2.23k
•
9
opencompass/mmmlu_lite
Viewer
•
Updated
•
20k
•
224
•
2
opencompass/MMBench-Video
Preview
•
Updated
•
469
•
7
opencompass/NeedleBench
Viewer
•
Updated
•
524
•
279
•
4
opencompass/anah
Viewer
•
Updated
•
783
•
133
•
2
opencompass/flames
Viewer
•
Updated
•
537
•
146
opencompass/CriticBench
Updated
•
252
•
4
opencompass/MMBench
Updated
•
39
•
1