M2-Verify-Gen - Quantitative Biology: 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 Quantitative Biology (q-bio) claims of the M2-Verify-Gen test set; higher is better.

Metric: Macro-F1 (%) of binary claim consistency verification on the Quantitative Biology (q-bio) 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

#ModelScoreOverall rank
1Qwen 2.5 VL 7B Instruct71#1919
2InternVL3-8B63.3#1795
3Mistral Small 3.153.7#1734
4Llama 3.2 11B Vision52.2#4281
5Phi-4 Multimodal Instruct46.5#4155
6Pixtral-12B41.5#2611

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-gen-quantitative-biology · How It Works · Data refreshed daily, snapshot 2026-11-22.