List your company

Math & physics reasoning on OlympiadBench Phys

14.41AccuracyINFUSER
10.000411.145212.2913.4348Jun 8, 2026

Evaluation results

MethodLinks
INFUSERModel Backbone=Qwen3-8B-Base2026.0614.41
R-ZeroModel Backbone=Qwen3-8B-Base2026.0613.98
AZRModel Backbone=Qwen3-8B-Base2026.0613.14
BaseModel Backbone=Qwen3-8B-Base2026.0612.29
R-ZeroModel Backbone=Qwen3-4B-Base2026.0611.44
INFUSERModel Backbone=Qwen3-4B-Base2026.0610.31
BaseModel Backbone=Qwen3-4B-Base2026.0610.17
AZRModel Backbone=Qwen3-4B-Base2026.0610.17