OmniMatBench - QA - Structural and Engineering Materials: leaderboard

OmniMatBench (2026) poses 3,171 expert-curated multimodal materials-science problems, open-ended questions graded against expert key points and calculations graded slot by slot, across 19 subfields. This board is the QA macro-F1 on the Structural and Engineering Materials group, 0 to 100; higher is better.

Metric: QA macro-F1 (0-100): F1 between the response and the expert key points (precision and recall judged by Gemini 2.5 Flash), macro-averaged over subfields, times 100, over the QA questions of the Structural and Engineering Materials group on OmniMatBench (3,171 expert-curated multimodal materials-science problems in 19 subfields: 1,261 open-ended QA and 1,910 calculation questions); higher is better. Source: arxiv.org. Saturation forecast: Around August 2028. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1O345#237
2Claude Opus 4.744.4#85
3Grok 4.344#342
4Gemini 3.1 Pro (Preview)43.4#99
5GPT-5.540.4#54
6Qwen 3.6 Plus37.2#238
7O4 Mini35.3#368
8Qwen 3 VL 235B A22B33.6#485
9Gemma 4 31B33#382
10GPT-4o32.6#751
11Intern-S1-Pro31.8#585
12GLM-4.6V30.9#710
13Llama 4 Maverick28.7#1110

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=omnimatbench-qa-structural-and-engineering-materials · How It Works · Data refreshed daily, snapshot 2026-11-21.