List your company

Mathematical Reasoning on AIME 2025 (pass@1, pass@10)

66.7Pass@1Qwen3-8B
20.21232.28144.3556.419Oct 29, 2025

Evaluation results

MethodLinks
Qwen3-8BParameters=8B2025.1066.781.3
Qwen3-4BParameters=4B2025.1051.363.3
Ouro-2.6B-Thinking-R4Parameters=2.6B, Configuration=Thinking-R42025.1050.376.7
Ouro-1.4B-Thinking-R4Parameters=1.4B, Configuration=Thinking-R42025.1046.373.3
Deepseek-Distill-Qwen-7BParameters=7B2025.103673.3
Deepseek-Distill-Qwen-1.5BParameters=1.5B2025.102343.33
Qwen3-1.7BParameters=1.7B2025.102233.3