| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SEED-Bench | Accuracy74.74 | 50 | 1mo ago | ||
| MME | MME Score2,498 | 36 | 2mo ago | ||
| MMBench | Vanilla | MMB Score69.3 | 19 | 4mo ago | |
| MME Leaderboard (full) | HALC | Existence Score138.33 | 18 | 5mo ago | |
| MME (test) | BLIVA | Communication Score136.43 | 17 | 4mo ago | |
| CV-Bench | VLSI-2B | Accuracy90.1 | 17 | 5mo ago | |
| MMStar | CGC-8B | Average Score72.6 | 16 | 3mo ago | |
| MME full | GIFT | MME Score2,418.5 | 16 | 1mo ago | |
| OckBench | Datology | Tokens per Correct Answer47 | 14 | 1mo ago | |
| VIEScore | Gemini 2.5 Flash | CV (CIG-SC)1.32 | 7 | 5mo ago | |
| LLaVA-Wilder | Phantom-7B | Accuracy83.7 | 7 | 5mo ago | |
| MM-Vet | DSCA | Overall Score57.8 | 4 | 3mo ago | |
| MMBench-CN | Score50.17 | 4 | 5mo ago | ||
| Vision-language benchmark | Location Accuracy82.2 | 2 | 5mo ago |