List your company

Mathematical Reasoning on AIME 2024 (p@1 and p@16)

87.92p@1LED
55.4263.857572.29580.7325Feb 2, 2026

Evaluation results

MethodLinks
LEDModel=Qwen3-30B-A3B-Thinking2026.0287.9290
DoLaModel=Qwen3-30B-A3B-Thinking2026.0287.590
CoTModel=Qwen3-30B-A3B-Thinking2026.0287.2990
ST-GModel=Qwen3-30B-A3B-Thinking2026.0286.4690
STModel=Qwen3-30B-A3B-Thinking2026.0285.6290
STModel=Qwen3-4B-Thinking2026.028090
ST-GModel=Qwen3-4B-Thinking2026.0279.3790
LEDModel=Qwen3-4B-Thinking2026.0278.3390
CoTModel=Qwen3-4B-Thinking2026.0276.4690
DoLaModel=Qwen3-4B-Thinking2026.0276.2590
DoLaModel=MiMo-7B-RL2026.0267.0883.33
LEDModel=MiMo-7B-RL2026.0266.4683.33
ST-GModel=MiMo-7B-RL2026.0265.6283.33
CoTModel=MiMo-7B-RL2026.0265.2183.33
STModel=MiMo-7B-RL2026.0256.6783.33