Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

PHYBench dataset and benchmarks · SOTA2 Research

Research Datasets

PHYBench

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Video Question Answering

PhyBench

0.793Avg Score

12

Physical Reasoning

PHYBench

5.3Pass@1 Accuracy

12

PHYBench

30.06Score

10

Phybench

80Score

9

PHYBENCH

26.26PHYBench Score

9

Hypothetical Instruction-Based Image Editing

PhyBench

75.71Instruction Alignment

7

Physics Reasoning

PhyBench

26pass@16

6

Scientific Reasoning

PHYBench

30.34Accuracy

5

Popular tasks

Video Question Answering Reasoning Physical Reasoning Scientific Reasoning Knowledge

Follow for updates

Join SOTA2 Contact