List your company

Math Reasoning on MATH 500 (Acc, ∆Tok)

99.2AccuracyQwen3-Next-80B + THINKBRAKE
54.68866.24477.889.356Oct 1, 2025

Evaluation results

MethodLinks
Qwen3-Next-80B + THINKBRAKEBackbone=Qwen3-Next-80B, Decoding Strategy=THINKBRAKE2025.1099.2-21.6
Qwen3-Next-80BBackbone=Qwen3-Next-80B, Decoding Strategy=Base2025.1098.2—
Qwen3-32B + THINKBRAKEBackbone=Qwen3-32B, Decoding Strategy=THINKBRAKE2025.1097.2-1.4
Qwen3-32BBackbone=Qwen3-32B, Decoding Strategy=Base2025.1097—
Qwen3-14B + THINKBRAKEBackbone=Qwen3-14B, Decoding Strategy=THINKBRAKE2025.1096.9-7.7
Qwen3-14BBackbone=Qwen3-14B, Decoding Strategy=Base2025.1096.8—
Qwen3-4B-Thinking + THINKBRAKEBackbone=Qwen3-4B-Thinking, Decoding Strategy=THINKBRAKE2025.1096.6-20.4
Qwen3-4B-Thinking + NoWaitBackbone=Qwen3-4B-Thinking, Decoding Strategy=NoWait2025.1096.4-17.9
Qwen3-4BBackbone=Qwen3-4B, Decoding Strategy=Base2025.1096—
Qwen3-32B + NoWaitBackbone=Qwen3-32B, Decoding Strategy=NoWait2025.1095.8-20.6
Qwen3-4B + THINKBRAKEBackbone=Qwen3-4B, Decoding Strategy=THINKBRAKE2025.1095.4-14.4
Qwen3-4B-ThinkingBackbone=Qwen3-4B-Thinking, Decoding Strategy=Base2025.1095.3—
Qwen3-14B + NoWaitBackbone=Qwen3-14B, Decoding Strategy=NoWait2025.1095.2-25.1
Qwen3-4B + NoWaitBackbone=Qwen3-4B, Decoding Strategy=NoWait2025.1094.6-31.4
Qwen3-4B-Thinking + DEERBackbone=Qwen3-4B-Thinking, Decoding Strategy=DEER2025.1094.4-14.2
DeepSeek-R1-7BBackbone=DeepSeek-R1-7B, Decoding Strategy=Base2025.1093.8—
DeepSeek-R1-7B + THINKBRAKEBackbone=DeepSeek-R1-7B, Decoding Strategy=THINKBRAKE2025.1092-23.2
Qwen3-4B-Thinking + THINKBRAKE-pBackbone=Qwen3-4B-Thinking, Decoding Strategy=THINKBRAKE-p2025.1091.2-57.9
DeepSeek-R1-7B + NoWaitBackbone=DeepSeek-R1-7B, Decoding Strategy=NoWait2025.1091.2-31
Qwen3-32B + THINKBRAKE-pBackbone=Qwen3-32B, Decoding Strategy=THINKBRAKE-p2025.1089.6-39.4
Qwen3-14B + THINKBRAKE-pBackbone=Qwen3-14B, Decoding Strategy=THINKBRAKE-p2025.1089-49.8
Qwen3-4B + THINKBRAKE-pBackbone=Qwen3-4B, Decoding Strategy=THINKBRAKE-p2025.1088.6-51.3
Qwen3-32B + ThinkLessBackbone=Qwen3-32B, Decoding Strategy=ThinkLess2025.1087.6-100
Qwen3-4B-Thinking + Dynasor-CoTBackbone=Qwen3-4B-Thinking, Decoding Strategy=Dynasor-CoT2025.1087.2-42.1
DeepSeek-R1-7B + DEERBackbone=DeepSeek-R1-7B, Decoding Strategy=DEER2025.1087.2-44.5
Qwen3-14B + ThinkLessBackbone=Qwen3-14B, Decoding Strategy=ThinkLess2025.1086.8-100
Qwen3-4B + ThinkLessBackbone=Qwen3-4B, Decoding Strategy=ThinkLess2025.1085.4-100
DeepSeek-R1-7B + THINKBRAKE-pBackbone=DeepSeek-R1-7B, Decoding Strategy=THINKBRAKE-p2025.1081.4-60.6
DeepSeek-R1-7B + ThinkLessBackbone=DeepSeek-R1-7B, Decoding Strategy=ThinkLess2025.1078.4-100
Phi-4-ReasoningBackbone=Phi-4-Reasoning, Decoding Strategy=Base2025.1071.1—
Phi-4-Reasoning + NoWaitBackbone=Phi-4-Reasoning, Decoding Strategy=NoWait2025.1070.8-17.7
Phi-4-Reasoning + THINKBRAKEBackbone=Phi-4-Reasoning, Decoding Strategy=THINKBRAKE2025.1070.4-17.2
Phi-4-Reasoning + THINKBRAKE-pBackbone=Phi-4-Reasoning, Decoding Strategy=THINKBRAKE-p2025.1068.8-50.4
Phi-4-Reasoning + ThinkLessBackbone=Phi-4-Reasoning, Decoding Strategy=ThinkLess2025.1066.4-100
DeepSeek-R1-7B + Dynasor-CoTBackbone=DeepSeek-R1-7B, Decoding Strategy=Dynasor-CoT2025.1064.2-47.2
Qwen3-4B-Thinking + ThinkLessBackbone=Qwen3-4B-Thinking, Decoding Strategy=ThinkLess2025.1056.4-100