JMMMU-Pro - Overall: leaderboard
The "Overall" subtask of JMMMU-Pro. Japanese multimodal understanding benchmark extending JMMMU with image-based multidisciplinary questions.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around January 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 87.05 | #80 |
| 2 | GPT-5.2 | 83.33 | #110 |
| 3 | Qwen 2.5 VL 7B | 45 | #643 |
| 4 | aya-vision-8B | 26.74 | #1107 |
| 5 | Pangea-7B | 23.41 | #1224 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=jmmmu-pro-overall · How It Works · Data refreshed daily, snapshot 2026-10-20.