List your company

Science Reasoning on GPQA-D (Acc, ∆Tok)

76.3AccuracyQwen3-Next-80B
28.4640.8853.365.72Oct 1, 2025Nov 9, 2025Dec 18, 2025Jan 27, 2026Mar 7, 2026Apr 15, 2026May 25, 2026

Evaluation results

MethodLinks
Qwen3-Next-80BBackbone=Qwen3-Next-80B, Decoding Strategy=Base2025.1076.3—
Qwen3-Next-80B + THINKBRAKEBackbone=Qwen3-Next-80B, Decoding Strategy=THINKBRAKE2025.1072.7-25.6
Qwen3-4B-Thinking + NoWaitBackbone=Qwen3-4B-Thinking, Decoding Strategy=NoWait2025.1068.2-19.6
Qwen3-4B-Thinking + DEERBackbone=Qwen3-4B-Thinking, Decoding Strategy=DEER2025.1068.2-1.3
Phi-4-Reasoning + THINKBRAKEBackbone=Phi-4-Reasoning, Decoding Strategy=THINKBRAKE2025.1067.7-1.1
Qwen3-32B + THINKBRAKEBackbone=Qwen3-32B, Decoding Strategy=THINKBRAKE2025.1065.7-19.9
Qwen3-32BBackbone=Qwen3-32B, Decoding Strategy=Base2025.1065.2—
Qwen3-4B-ThinkingBackbone=Qwen3-4B-Thinking, Decoding Strategy=Base2025.1064.1—
Phi-4-Reasoning + NoWaitBackbone=Phi-4-Reasoning, Decoding Strategy=NoWait2025.1063.1-19.1
Qwen3-4B-Thinking + Dynasor-CoTBackbone=Qwen3-4B-Thinking, Decoding Strategy=Dynasor-CoT2025.1062.6-22.6
Qwen3-4B-Thinking + THINKBRAKEBackbone=Qwen3-4B-Thinking, Decoding Strategy=THINKBRAKE2025.1062.6-32.7
Phi-4-ReasoningBackbone=Phi-4-Reasoning, Decoding Strategy=Base2025.1062.6—
Qwen3-14B + NoWaitBackbone=Qwen3-14B, Decoding Strategy=NoWait2025.1062.1-20.5
Qwen3-14B + THINKBRAKEBackbone=Qwen3-14B, Decoding Strategy=THINKBRAKE2025.1061.1-39.9
Qwen3-14BBackbone=Qwen3-14B, Decoding Strategy=Base2025.1060.6—
Qwen3-32B + NoWaitBackbone=Qwen3-32B, Decoding Strategy=NoWait2025.1060.1-12.4
Phi-4-Reasoning + THINKBRAKE-pBackbone=Phi-4-Reasoning, Decoding Strategy=THINKBRAKE-p2025.1059.1-62.8
Qwen3-4B + NoWaitBackbone=Qwen3-4B, Decoding Strategy=NoWait2025.1057.6-26.6
Qwen3-14B + THINKBRAKE-pBackbone=Qwen3-14B, Decoding Strategy=THINKBRAKE-p2025.1057.6-66.4
Qwen3-4B + THINKBRAKEBackbone=Qwen3-4B, Decoding Strategy=THINKBRAKE2025.1055.6-29.7
Qwen3-32B + ThinkLessBackbone=Qwen3-32B, Decoding Strategy=ThinkLess2025.1054.5-100
Phi-4-Reasoning + ThinkLessBackbone=Phi-4-Reasoning, Decoding Strategy=ThinkLess2025.1054-100
Qwen3-32B + THINKBRAKE-pBackbone=Qwen3-32B, Decoding Strategy=THINKBRAKE-p2025.1053.5-51
MCPO-DAPOBackbone=Qwen3-8B2026.0552.44—
Qwen3-4BBackbone=Qwen3-4B, Decoding Strategy=Base2025.1051—
MCPO-GRPOBackbone=Qwen3-8B2026.0550.57—
MGSBackbone=Qwen3-8B2026.0550.25—
DAPOBackbone=Qwen3-8B2026.0550.11—
Qwen3-4B-Thinking + ThinkLessBackbone=Qwen3-4B-Thinking, Decoding Strategy=ThinkLess2025.1050-100
MT-GRPOBackbone=Qwen3-8B2026.0549.89—
CLIPOBackbone=Qwen3-8B2026.0549.83—
Qwen3-14B + ThinkLessBackbone=Qwen3-14B, Decoding Strategy=ThinkLess2025.1049.5-100
MCPO-DAPOBackbone=Qwen3-4B2026.0549.13—
MCPO-GRPOBackbone=Qwen3-4B2026.0548.81—
GRPOBackbone=Qwen3-8B2026.0548.44—
DeepSeek-R1-7BBackbone=DeepSeek-R1-7B, Decoding Strategy=Base2025.1048—
Qwen3-4B + THINKBRAKE-pBackbone=Qwen3-4B, Decoding Strategy=THINKBRAKE-p2025.1047.5-54.2
Qwen3-4B-Thinking + THINKBRAKE-pBackbone=Qwen3-4B-Thinking, Decoding Strategy=THINKBRAKE-p2025.1047-67.5
DAPOBackbone=Qwen3-4B2026.0546.37—
Qwen3-4B + ThinkLessBackbone=Qwen3-4B, Decoding Strategy=ThinkLess2025.1046-100
DeepSeek-R1-7B + THINKBRAKEBackbone=DeepSeek-R1-7B, Decoding Strategy=THINKBRAKE2025.1045.5-51.5
MGSBackbone=Qwen3-4B2026.0545.4—
MT-GRPOBackbone=Qwen3-4B2026.0544.06—
GRPOBackbone=Qwen3-4B2026.0543.95—
DeepSeek-R1-7B + DEERBackbone=DeepSeek-R1-7B, Decoding Strategy=DEER2025.1043.9-16.7
DeepSeek-R1-7B + NoWaitBackbone=DeepSeek-R1-7B, Decoding Strategy=NoWait2025.1043.4-35.5
CLIPOBackbone=Qwen3-4B2026.0542.68—
Base ModelBackbone=Qwen3-8B2026.0542.07—
DeepSeek-R1-7B + THINKBRAKE-pBackbone=DeepSeek-R1-7B, Decoding Strategy=THINKBRAKE-p2025.1036.4-76.8
Base ModelBackbone=Qwen3-4B2026.0535.45—
DeepSeek-R1-7B + Dynasor-CoTBackbone=DeepSeek-R1-7B, Decoding Strategy=Dynasor-CoT2025.1032.3-71.2
DeepSeek-R1-7B + ThinkLessBackbone=DeepSeek-R1-7B, Decoding Strategy=ThinkLess2025.1030.3-100