M2-Verify-Gen - Mathematics: leaderboard
M2-Verify (2026) is a multimodal scientific claim consistency benchmark: a model sees a figure, its caption and a claim and decides zero-shot whether the claim is supported or refuted. This board is macro-F1 in percent on the Mathematics (math) claims of the M2-Verify-Gen test set; higher is better.
Metric: Macro-F1 (%) of binary claim consistency verification on the Mathematics (math) questions of the M2-Verify-Gen test set, zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 65.4 | #1902 |
| 2 | InternVL3-8B | 61.8 | #1782 |
| 3 | Mistral Small 3.1 | 50.8 | #1706 |
| 4 | Llama 3.2 11B Vision | 48.8 | #4264 |
| 5 | Phi-4 Multimodal Instruct | 44.8 | #4154 |
| 6 | Pixtral-12B | 42.9 | #2553 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=m2-verify-gen-mathematics · How It Works · Data refreshed daily, snapshot 2026-11-21.