List your company

Math Reasoning on AIME 2024 (Acc, ∆Tok)

90AccuracyQwen3-Next-80B
-0.16823.24146.6570.059Oct 1, 2025

Evaluation results

MethodLinks
Qwen3-Next-80BBackbone=Qwen3-Next-80B, Decoding Strategy=Base2025.1090—
Qwen3-Next-80B + THINKBRAKEBackbone=Qwen3-Next-80B, Decoding Strategy=THINKBRAKE2025.1086.7-24.3
Qwen3-14B + THINKBRAKEBackbone=Qwen3-14B, Decoding Strategy=THINKBRAKE2025.1077.9-7.4
Qwen3-4B-ThinkingBackbone=Qwen3-4B-Thinking, Decoding Strategy=Base2025.1077.1—
Qwen3-32B + THINKBRAKEBackbone=Qwen3-32B, Decoding Strategy=THINKBRAKE2025.1077.1-6.2
Qwen3-32BBackbone=Qwen3-32B, Decoding Strategy=Base2025.1075.8—
Phi-4-Reasoning + THINKBRAKEBackbone=Phi-4-Reasoning, Decoding Strategy=THINKBRAKE2025.1073.3-6.4
Qwen3-14BBackbone=Qwen3-14B, Decoding Strategy=Base2025.1071.7—
Qwen3-14B + NoWaitBackbone=Qwen3-14B, Decoding Strategy=NoWait2025.1070-19.8
Qwen3-4BBackbone=Qwen3-4B, Decoding Strategy=Base2025.1068.8—
Phi-4-ReasoningBackbone=Phi-4-Reasoning, Decoding Strategy=Base2025.1067.5—
Qwen3-4B-Thinking + THINKBRAKEBackbone=Qwen3-4B-Thinking, Decoding Strategy=THINKBRAKE2025.1067.2-33.5
Qwen3-4B-Thinking + NoWaitBackbone=Qwen3-4B-Thinking, Decoding Strategy=NoWait2025.1066.7-30.5
Qwen3-32B + NoWaitBackbone=Qwen3-32B, Decoding Strategy=NoWait2025.1066.7-12
Qwen3-4B + THINKBRAKEBackbone=Qwen3-4B, Decoding Strategy=THINKBRAKE2025.1064.6-12.7
Qwen3-4B-Thinking + DEERBackbone=Qwen3-4B-Thinking, Decoding Strategy=DEER2025.1063.3-34.3
Qwen3-4B-Thinking + Dynasor-CoTBackbone=Qwen3-4B-Thinking, Decoding Strategy=Dynasor-CoT2025.1063.3-28.8
Phi-4-Reasoning + NoWaitBackbone=Phi-4-Reasoning, Decoding Strategy=NoWait2025.1063.3-9.4
Qwen3-4B + NoWaitBackbone=Qwen3-4B, Decoding Strategy=NoWait2025.1056.7-16.6
DeepSeek-R1-7B + DEERBackbone=DeepSeek-R1-7B, Decoding Strategy=DEER2025.1050-28.2
DeepSeek-R1-7BBackbone=DeepSeek-R1-7B, Decoding Strategy=Base2025.1049.5—
DeepSeek-R1-7B + THINKBRAKEBackbone=DeepSeek-R1-7B, Decoding Strategy=THINKBRAKE2025.1045.2-25
DeepSeek-R1-7B + NoWaitBackbone=DeepSeek-R1-7B, Decoding Strategy=NoWait2025.1040-32.4
Phi-4-Reasoning + THINKBRAKE-pBackbone=Phi-4-Reasoning, Decoding Strategy=THINKBRAKE-p2025.1039.6-63.1
Qwen3-32B + THINKBRAKE-pBackbone=Qwen3-32B, Decoding Strategy=THINKBRAKE-p2025.1039.2-61.5
Qwen3-14B + THINKBRAKE-pBackbone=Qwen3-14B, Decoding Strategy=THINKBRAKE-p2025.1038.8-68
Phi-4-Reasoning + ThinkLessBackbone=Phi-4-Reasoning, Decoding Strategy=ThinkLess2025.1036.7-100
Qwen3-4B-Thinking + THINKBRAKE-pBackbone=Qwen3-4B-Thinking, Decoding Strategy=THINKBRAKE-p2025.1035-72.6
DeepSeek-R1-7B + Dynasor-CoTBackbone=DeepSeek-R1-7B, Decoding Strategy=Dynasor-CoT2025.1033.4-31.8
Qwen3-4B + THINKBRAKE-pBackbone=Qwen3-4B, Decoding Strategy=THINKBRAKE-p2025.1029.2-64.5
DeepSeek-R1-7B + THINKBRAKE-pBackbone=DeepSeek-R1-7B, Decoding Strategy=THINKBRAKE-p2025.1025.4-71.4
Qwen3-4B + ThinkLessBackbone=Qwen3-4B, Decoding Strategy=ThinkLess2025.1023.3-100
Qwen3-14B + ThinkLessBackbone=Qwen3-14B, Decoding Strategy=ThinkLess2025.1023.3-100
Qwen3-32B + ThinkLessBackbone=Qwen3-32B, Decoding Strategy=ThinkLess2025.1023.3-100
DeepSeek-R1-7B + ThinkLessBackbone=DeepSeek-R1-7B, Decoding Strategy=ThinkLess2025.1016.7-100
Qwen3-4B-Thinking + ThinkLessBackbone=Qwen3-4B-Thinking, Decoding Strategy=ThinkLess2025.103.3-100