List your company

Mathematical Reasoning on AIME 2025 (Pass@k and Voting Metrics)

95.4Pass@1Qwen3-235B-A22B-Thinking-2507
36.84852.04967.2582.451Dec 11, 2025

Evaluation results

MethodLinks
Qwen3-235B-A22B-Thinking-2507Policy=Qwen3-235B-A22B-Thinking-25072025.1295.496.797.998.3100
gpt-oss-120bPolicy=gpt-oss-120b2025.1292.393.395.196.796.7
DeepSeek-R1-0528Policy=DeepSeek-R1-05282025.1287.188.387.590.896.7
QwQ-32BPolicy=QwQ-32B2025.127078.376.28083.3
DeepSeek-R1-Distill-Qwen-32BPolicy=DeepSeek-R1-Distill-Qwen-32B2025.1255.963.866.66876.7
DeepSeek-R1-Distill-Llama-70BPolicy=DeepSeek-R1-Distill-Llama-70B2025.12445056.157.870
DeepSeek-R1-Distill-Qwen-7BPolicy=DeepSeek-R1-Distill-Qwen-7B2025.1239.149.256.355.466.7