This repo contains the code for "MEGA-Bench Scaling Multimodal Evaluation to over 500 Real-World Tasks" [ICLR2025]
active 2024-10-11 → 2025-09-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 336 days from 2024-10-11 to 2025-09-11. Pushes: 113 total, peak 13 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 12 total, peak 1 in a day. Comments: 31 total, peak 4 in a day. Stars: 71 total, peak 7 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 |
|---|---|---|---|---|
| woodfrog | 83 | 65 | 0 | 17 |
| eric-zqwang | 26 | 26 | 0 | 0 |
| wenhuchen | 17 | 16 | 0 | 1 |
| Violettttee | 14 | 0 | 0 | 8 |
| TianhaoLiang2000 | 6 | 6 | 0 | 0 |
| shipengai | 4 | 0 | 0 | 3 |
| zjwu0522 | 2 | 0 | 0 | 1 |
| wizyoung | 2 | 0 | 0 | 1 |
| Luodian | 1 | 0 | 0 | 0 |
| Liuziyu77 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#10woodfrog2025-07-07 07:56应该看macro_mean还是micro_mean
- Issue comment#10shipengai2025-06-23 02:11应该看macro_mean还是micro_mean
- Issue comment#10shipengai2025-06-20 11:08应该看macro_mean还是micro_mean
- Issue comment#10shipengai2025-06-20 11:02应该看macro_mean还是micro_mean
- Issue comment#10woodfrog2025-06-20 09:50应该看macro_mean还是micro_mean
- Issue#10shipengai2025-06-20 08:01应该看macro_mean还是micro_mean
- Issue#2woodfrog2025-03-29 19:21Integrations into popular evaluation frameworks like lmms_eval or vlmevalkit
- Issue#9Liuziyu772025-01-20 19:18How to use GPT-4o for evaluation？
- Issue comment#8woodfrog2025-01-03 21:18Question about answer parse
- Issue comment#8Violettttee2025-01-03 12:17Question about answer parse
- Issue comment#8woodfrog2025-01-03 12:11Question about answer parse
- Issue#8Violettttee2025-01-03 09:19Question about answer parse
- Issue comment#7Violettttee2024-12-27 09:08About "Application" category score
- Issue comment#7woodfrog2024-12-27 06:28About "Application" category score
- Issue#7Violettttee2024-12-27 05:20About "Application" category score
- Issue comment#6woodfrog2024-12-26 23:14Request to evaluate O1 model series (Multimodality + API now available)
- Issue comment#5woodfrog2024-12-16 17:42Wrong aspect_ratio param in llava-onevision evaluation
- Issue comment#5woodfrog2024-12-16 17:38Wrong aspect_ratio param in llava-onevision evaluation
- Issue#5Luodian2024-12-16 09:38Wrong aspect_ratio param in llava-onevision evaluation
- Issue comment#4woodfrog2024-11-23 09:57About subsets evaluation
- Issue comment#4Violettttee2024-11-21 07:34About subsets evaluation
- Issue comment#4woodfrog2024-11-10 04:15About subsets evaluation
- Issue comment#4Violettttee2024-11-09 10:41About subsets evaluation
- Issue#4Violettttee2024-11-09 10:41About subsets evaluation
- Issue comment#4woodfrog2024-11-08 22:53About subsets evaluation
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 71 stars here means stars gained during the window, not the repo's star count.