M2-Verify-Med: 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 M2-Verify-Med test set, PubMed figures whose claims carry expert-curated medical perturbations; higher is better.
Metric: Macro-F1 (%) of binary claim consistency verification (supported or refuted) on the M2-Verify-Med test set (PubMed figures and captions, claims with expert-curated medical perturbations), zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o Mini | 73 | #1680 |
| 2 | Mistral Small 3.1 | 71.4 | #1734 |
| 3 | Qwen 2.5 VL 7B Instruct | 70.4 | #1919 |
| 4 | InternVL3-8B | 69.6 | #1795 |
| 5 | Pixtral-12B | 69.6 | #2611 |
| 6 | Llama 3.2 11B Vision | 69.3 | #4281 |
| 7 | GPT-5 Mini | 67.2 | #373 |
| 8 | Phi-4 Multimodal Instruct | 65.8 | #4155 |
| 9 | HuatuoGPT-Vision-7B | 60 | #2178 |
| 10 | LLaVA-Med | 51.8 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=m2-verify-med · How It Works · Data refreshed daily, snapshot 2026-11-22.