M3-VQA (Gold Section Evidence): leaderboard
M3-VQA (CASIA, 2026) is a knowledge-based visual question answering benchmark of multimodal, multi-entity, multi-hop questions that require recognizing several entities and chaining evidence from Wikipedia, scored by the overlap between predicted and gold answer sets. This board is IoU accuracy in percent with the Wikipedia sections holding the gold evidence of every hop added to the input; higher is better.
Metric: IoU accuracy (%) between the predicted and gold answer sets (exact match against Wikidata answer aliases, one-year margin for dates), averaged over the M3-VQA multi-entity, multi-hop knowledge-based visual questions, with the Wikipedia sections containing the gold evidence of every hop added to the input; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL2.5-78B | 55.16 | #1031 |
| 2 | InternVL2.5-38B | 53.95 | #1373 |
| 3 | GPT-4o | 53.07 | #751 |
| 4 | Qwen 2.5 VL 72B Instruct | 52.35 | #841 |
| 5 | Qwen 2.5 VL 32B Instruct | 50.02 | #1062 |
| 6 | InternVL2.5-26B | 45.5 | #2156 |
| 7 | LLaVA-OneVision-7B | 43.62 | #2981 |
| 8 | Qwen 2.5 VL 7B Instruct | 42.66 | #1902 |
| 9 | InternVL2.5-8B | 42.12 | #2370 |
| 10 | Qwen 2.5 VL 3B Instruct | 39.69 | #2713 |
| 11 | InternVL2.5-4B | 39.34 | #2549 |
| 12 | MiniCPM-V-2.6 | 39.11 | #3267 |
| 13 | Qwen 2 VL 7B Instruct | 38.92 | #2573 |
| 14 | DeepSeek-VL2 | 38.81 | #2927 |
| 15 | InternVL2.5-2B | 31.94 | #6468 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=m3-vqa-gold-section-evidence · How It Works · Data refreshed daily, snapshot 2026-11-21.