OmniPhys Benchmark

What is OmniPhys?

Evaluates multimodal physics understanding, reasoning, and generation on 15,246 questions with 19,850 images from middle-school to university levels.

Released

2026-08-26

Evaluates

General AI, Multimodal, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.25398

OmniPhys paper and code

• Paper https://arxiv.org/abs/2608.25398
• Code https://github.com/ECNU-RAIL/OmniPhys-EMNLP2026

Which sources cite OmniPhys?

• OmniPhys

Related General AI, Multimodal, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-Bench
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench