M2-Verify-Gen: 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-Gen test set, figures and captions from 16 arXiv categories with negated claims; higher is better.

Metric: Macro-F1 (%) of binary claim consistency verification (supported or refuted) on the M2-Verify-Gen test set (figures and captions from 16 arXiv categories, negation-perturbed claims), zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 2.5 VL 7B Instruct68.1#1919
2InternVL3-8B63.8#1795
3Mistral Small 3.163.1#1734
4GPT-5 Mini59.9#373
5GPT-4o Mini56.6#1680
6Llama 3.2 11B Vision53.8#4281
7Phi-4 Multimodal Instruct45.7#4155
8Pixtral-12B41.9#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 · How It Works · Data refreshed daily, snapshot 2026-11-22.