List your company

Math and Science Reasoning on Average

89.7AccuracyQwen3-Next-80B
45.29256.82168.3579.879Oct 1, 2025

Evaluation results

MethodLinks
Qwen3-Next-80BBackbone=Qwen3-Next-80B, Decoding Strategy=Base2025.1089.7—
Qwen3-Next-80B + THINKBRAKEBackbone=Qwen3-Next-80B, Decoding Strategy=THINKBRAKE2025.1087.6-22.3
Qwen3-4B-ThinkingBackbone=Qwen3-4B-Thinking, Decoding Strategy=Base2025.1083.7—
Qwen3-32B + THINKBRAKEBackbone=Qwen3-32B, Decoding Strategy=THINKBRAKE2025.1082.6-8.2
Qwen3-32BBackbone=Qwen3-32B, Decoding Strategy=Base2025.1082.4—
Qwen3-14B + THINKBRAKEBackbone=Qwen3-14B, Decoding Strategy=THINKBRAKE2025.1082-15.8
Qwen3-14BBackbone=Qwen3-14B, Decoding Strategy=Base2025.1081.7—
Qwen3-4B-Thinking + NoWaitBackbone=Qwen3-4B-Thinking, Decoding Strategy=NoWait2025.1080.8-19
Qwen3-4B-Thinking + THINKBRAKEBackbone=Qwen3-4B-Thinking, Decoding Strategy=THINKBRAKE2025.1079.7-26.5
Qwen3-14B + NoWaitBackbone=Qwen3-14B, Decoding Strategy=NoWait2025.1079.3-19.9
Qwen3-4B-Thinking + DEERBackbone=Qwen3-4B-Thinking, Decoding Strategy=DEER2025.1079-21.8
Qwen3-32B + NoWaitBackbone=Qwen3-32B, Decoding Strategy=NoWait2025.1077.5-11.7
Qwen3-4B + THINKBRAKEBackbone=Qwen3-4B, Decoding Strategy=THINKBRAKE2025.1077.4-18.7
Qwen3-4BBackbone=Qwen3-4B, Decoding Strategy=Base2025.1077.3—
Qwen3-4B-Thinking + Dynasor-CoTBackbone=Qwen3-4B-Thinking, Decoding Strategy=Dynasor-CoT2025.1076-23
Qwen3-4B + NoWaitBackbone=Qwen3-4B, Decoding Strategy=NoWait2025.1074.5-26.1
Phi-4-ReasoningBackbone=Phi-4-Reasoning, Decoding Strategy=Base2025.1072.8—
Phi-4-Reasoning + THINKBRAKEBackbone=Phi-4-Reasoning, Decoding Strategy=THINKBRAKE2025.1072.7-13.5
Phi-4-Reasoning + NoWaitBackbone=Phi-4-Reasoning, Decoding Strategy=NoWait2025.1070-10.7
Qwen3-14B + THINKBRAKE-pBackbone=Qwen3-14B, Decoding Strategy=THINKBRAKE-p2025.1066.9-51
Qwen3-32B + THINKBRAKE-pBackbone=Qwen3-32B, Decoding Strategy=THINKBRAKE-p2025.1066-42.2
Qwen3-4B-Thinking + THINKBRAKE-pBackbone=Qwen3-4B-Thinking, Decoding Strategy=THINKBRAKE-p2025.1065.2-57.2
DeepSeek-R1-7BBackbone=DeepSeek-R1-7B, Decoding Strategy=Base2025.1064.9—
DeepSeek-R1-7B + THINKBRAKEBackbone=DeepSeek-R1-7B, Decoding Strategy=THINKBRAKE2025.1063.2-30
Qwen3-14B + ThinkLessBackbone=Qwen3-14B, Decoding Strategy=ThinkLess2025.1062.9-100
DeepSeek-R1-7B + DEERBackbone=DeepSeek-R1-7B, Decoding Strategy=DEER2025.1062.9-28.3
Qwen3-4B + THINKBRAKE-pBackbone=Qwen3-4B, Decoding Strategy=THINKBRAKE-p2025.1062.8-48.8
Qwen3-32B + ThinkLessBackbone=Qwen3-32B, Decoding Strategy=ThinkLess2025.1062.3-100
Phi-4-Reasoning + THINKBRAKE-pBackbone=Phi-4-Reasoning, Decoding Strategy=THINKBRAKE-p2025.1062-55.8
Qwen3-4B + ThinkLessBackbone=Qwen3-4B, Decoding Strategy=ThinkLess2025.1059.7-100
DeepSeek-R1-7B + NoWaitBackbone=DeepSeek-R1-7B, Decoding Strategy=NoWait2025.1059.4-29.8
Phi-4-Reasoning + ThinkLessBackbone=Phi-4-Reasoning, Decoding Strategy=ThinkLess2025.1059.3-100
DeepSeek-R1-7B + THINKBRAKE-pBackbone=DeepSeek-R1-7B, Decoding Strategy=THINKBRAKE-p2025.1053.5-61.4
DeepSeek-R1-7B + Dynasor-CoTBackbone=DeepSeek-R1-7B, Decoding Strategy=Dynasor-CoT2025.1050.4-53
Qwen3-4B-Thinking + ThinkLessBackbone=Qwen3-4B-Thinking, Decoding Strategy=ThinkLess2025.1050-100
DeepSeek-R1-7B + ThinkLessBackbone=DeepSeek-R1-7B, Decoding Strategy=ThinkLess2025.1047-100