This repo contains fork designed for Personal.ai Agent Training. Its the evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
active 2023-11-28 → 2026-06-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 917 days from 2023-11-28 to 2026-06-01. Pushes: 81 total, peak 4 in a day. Pull requests: 37 total, peak 8 in a day. Issues: 109 total, peak 9 in a day. Comments: 152 total, peak 6 in a day. Stars: 450 total, peak 34 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| NipElement | 94 | 57 | 6 | 22 |
| xiangyue9607 | 72 | 11 | 9 | 23 |
| drogozhang | 63 | 12 | 0 | 36 |
| Zheng0428 | 32 | 1 | 17 | 14 |
| insafim | 20 | 0 | 0 | 9 |
| Qzy568 | 6 | 0 | 0 | 3 |
| teasgen | 5 | 0 | 0 | 3 |
| Rubics-Xuan | 5 | 0 | 0 | 5 |
| Makefunof | 5 | 0 | 0 | 3 |
| wvangansbeke | 5 | 0 | 0 | 4 |
| XiongweiWu | 5 | 0 | 0 | 1 |
| mckinziebrandon | 5 | 0 | 0 | 1 |
| SweetGUOguo | 3 | 0 | 0 | 1 |
| Xiaolong-RRL | 3 | 0 | 0 | 1 |
| fxmeng | 3 | 0 | 0 | 1 |
| lucasmgomez | 3 | 0 | 0 | 1 |
| shannany0606 | 3 | 0 | 0 | 1 |
| ycszen | 3 | 0 | 1 | 2 |
| dchichkov | 2 | 0 | 0 | 1 |
| beichenzbc | 2 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#82NipElement2026-05-10 19:52Question about leaderboard settings
- Issue#82llsj142026-05-10 11:00Question about leaderboard settings
- Issue#80NipElement2026-04-07 19:53dataset overlap
- Issue comment#80manglu0972026-04-07 14:10dataset overlap
- Issue comment#80NipElement2026-04-06 22:02dataset overlap
- Issue#79NipElement2026-02-12 10:00EvalAI提交评测
- Issue comment#79NipElement2026-02-11 10:25EvalAI提交评测
- Issue comment#78NipElement2026-01-23 06:34EvalAI leaderboard提交后一直在submited
- Issue#78drogozhang2026-01-21 03:53EvalAI leaderboard提交后一直在submited
- Issue#77drogozhang2025-09-26 17:42Need help evaluating...
- Issue#77blazgocompany2025-07-25 13:55Need help evaluating...
- Issue comment#76drogozhang2025-05-19 16:12Batch 支持
- Issue comment#76remember000002025-05-19 15:37Batch 支持
- Issue comment#74drogozhang2025-05-19 14:56Key error
- Issue#74drogozhang2025-05-19 14:56Key error
- Issue comment#76drogozhang2025-05-19 14:55Batch 支持
- Issue#76drogozhang2025-05-19 14:55Batch 支持
- Issue#76remember000002025-05-19 08:25Batch 支持
- Issue comment#75drogozhang2025-05-12 00:37Does MMU support scoring based on image categories?
- Issue#75drogozhang2025-05-12 00:37Does MMU support scoring based on image categories?
- Issue comment#75drogozhang2025-05-06 20:28Does MMU support scoring based on image categories?
- Issue comment#74drogozhang2025-05-06 20:26Key error
- Issue#75Blissy-322025-05-06 07:18Does MMU support scoring based on image categories?
- Issue#74manglu0972025-05-02 09:36Key error
- Issue comment#73Zheng04282025-04-15 03:12🤗 Transformers multimodal models eval on MMMU_Pro
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 450 stars here means stars gained during the window, not the repo's star count.