List your company
ResearchFormerly WizWand

Scientific Reasoning on GPQA (test) (pass@1)

70.8Pass@1Qwen2.5-32B-Instruct
49.16854.78460.466.016Aug 19, 2025
Updated 6mo ago

Evaluation results

MethodLinks
Qwen2.5-32B-InstructDataset Size=1K, Training Method=SFT, Strategy=Majority Vote (S-D D-S R-S)2025.0870.8
Qwen2.5-32B-InstructDataset Size=1K, Training Method=SFT, Strategy=D-S2025.0870.2
Qwen2.5-32B-InstructDataset Size=1K, Training Method=SFT, Strategy=Majority Vote (S-D D-S R-R)2025.0870.2
DeepSeek-Qwen-32BDataset Size=1K, Training Method=SFT, Strategy=D-S2025.0870.2
Qwen2.5-32B-InstructDataset Size=1K, Training Method=SFT, Strategy=S-D2025.0869.7
Qwen2.5-32B-InstructDataset Size=1K, Training Method=SFT, Strategy=Merge2025.0868.7
DeepSeek-Qwen-32BDataset Size=1K, Training Method=SFT, Strategy=Majority Vote (R-S D-R S-S)2025.0868.2
DeepSeek-Qwen-32BDataset Size=1K, Training Method=SFT, Strategy=S-S2025.0867.8
DeepSeek-Qwen-32BDataset Size=1K, Training Method=SFT, Strategy=Majority Vote (D-S S-S S-S)2025.0867.8
LIMO-32BDataset Size=1k, Training Method=SFT2025.0866.7
DeepSeek-Qwen-32BDataset Size=1K, Training Method=SFT, Strategy=R-D2025.0866.2
OpenThinker2-32BDataset Size=1000K, Training Method=SFT2025.0864.1
S1.1-32BDataset Size=1k, Training Method=SFT2025.0863.6
OpenThinker-32BDataset Size=114k, Training Method=SFT2025.0863.5
S1-32BDataset Size=1k, Training Method=SFT2025.0859.6
DeepSeek-Qwen-32BDataset Size=800K, Training Method=SFT, Decoding Strategy=Greedy Decoding2025.0850