| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMStar | Seed 1.5-VL | Score77.8 | 35 | 1mo ago | |
| SimpleVQA | OpenSearch-VL-32B | Pass@176.2 | 33 | 27d ago | |
| RealWorldQA | Bee-8B | Score73.1 | 20 | 1mo ago | |
| MMBench-EN (test) | STEP3-VL-10B | Accuracy92.05 | 19 | 3mo ago | |
| RealWorldQA | BARD-VL | Accuracy71.9 | 16 | 4d ago | |
| MMStar 2024b | InternVL2.5-MPO | Accuracy65.3 | 14 | 3mo ago | |
| MMVet 2024b | InternVL2.5-MPO | Score66.8 | 13 | 3mo ago | |
| SEED-Bench IMG 2023a | InternVL2.5 | Accuracy77 | 13 | 3mo ago | |
| MME 2023 | InternVL2.5 | Total Score2,339 | 13 | 3mo ago | |
| MMMU 2024 (val) | InternVL2.5-MPO | Accuracy52.8 | 13 | 3mo ago | |
| MMBench 2024c (dev) | InternVL2.5-MPO | Accuracy83.3 | 13 | 3mo ago | |
| BLINK (val) | Score68 | 12 | 2mo ago | ||
| MME-P | SigLIP2 | Rescaled Score1,284 | 10 | 1mo ago | |
| GQA | GenLIP | Accuracy45.5 | 10 | 1mo ago | |
| VQA v2 | SigLIP2 | Accuracy50.1 | 10 | 1mo ago | |
| MMBench En (dev) | Keye-VL | Overall Score91.5 | 10 | 2mo ago | |
| MM-Vet | Accuracy69.1 | 10 | 3mo ago | ||
| MMBench v1.1 | Accuracy82.2 | 9 | 3mo ago | ||
| MegaBench | Score54.2 | 8 | 3mo ago | ||
| HallusionBench | Pass@163.7 | 7 | 3mo ago | ||
| MMBench cn | Pass@189.7 | 7 | 3mo ago | ||
| MMBench en | Pass@190.1 | 7 | 3mo ago | ||
| RealWorldQA | Seed 1.5-VL | Pass@178.4 | 7 | 3mo ago | |
| MMVet turbo | Qwen2.5-VL | Score76.2 | 7 | 3mo ago | |
| RealWorldQA (avg) | InternVL2.5 | Score0.787 | 7 | 3mo ago |