List your company

Science Reasoning on GPQA (Score)

81.4ScoreDeepSeek v3.2
28.98442.59256.269.808May 26, 2025Jun 29, 2025Aug 2, 2025Sep 6, 2025Oct 10, 2025Nov 13, 2025Dec 18, 2025

Evaluation results

MethodLinks
DeepSeek v3.22025.1281.4
GLM-4.62025.1278.8
DeepSeek R1 05282025.1277.5
GPT-OSSParameters=120B2025.1277.3
GLM-4.52025.1277
INTELLECT-3Parameters=100B+2025.1274.4
GLM-4.5-Air2025.1273.3
TPOModel=LLaMA-3.2-3B2025.0539
GRPOModel=LLaMA-3.2-3B2025.0538
CPOModel=LLaMA-3.2-3B2025.0535.5
KTOModel=LLaMA-3.2-3B2025.0535
TI-DPOModel=LLaMA-3.2-3B2025.0534.5
DPOModel=LLaMA-3.2-3B2025.0534
TDPOModel=LLaMA-3.2-3B2025.0534
SIMPOModel=LLaMA-3.2-3B2025.0533.5
SFTModel=LLaMA-3.2-3B2025.0533
IPOModel=LLaMA-3.2-3B2025.0531