List your company
ResearchFormerly WizWand

General Reasoning on MMLU-Pro (ACC, A.Tok, epsilon^3)

49.54ACCJET
20.097627.741335.38543.0287May 10, 2026
Updated 5mo ago

Evaluation results

MethodLinks
JETBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0549.543,916.3563
VPG-EABackbone=DeepSeek-R1-Distill-Qwen-7B, Trained with same data and RL paradigm=True2026.0548.773,342.4471
AdaptThinkBackbone=DeepSeek-R1-Distill-Qwen-7B, Trained with same data and RL paradigm=True2026.0548.463,696.7864
Original ModelBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0547.534,115.2755
AutoThinkBackbone=DeepSeek-R1-Distill-Qwen-7B, Trained with same data and RL paradigm=True2026.0544.774,270.0447
R1-VeriThinkerBackbone=DeepSeek-R1-Distill-Qwen-7B2026.0543.854,156.9346
LaserBackbone=DeepSeek-R1-Distill-Qwen-7B, Trained with same data and RL paradigm=True2026.0543.074,029.9946
ThinklessBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0531.083,342.2929
LaserBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Trained with same data and RL paradigm=True2026.0525.382,242.3129
VPG-EABackbone=DeepSeek-R1-Distill-Qwen-1.5B, Trained with same data and RL paradigm=True2026.0525.233,030.3521
JETBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0525.082,928.3421
Original ModelBackbone=DeepSeek-R1-Distill-Qwen-1.5B2026.0524.764,168.4715
AdaptThinkBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Trained with same data and RL paradigm=True2026.0523.233,022.7718
AutoThinkBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Trained with same data and RL paradigm=True2026.0521.233,544.6613