List your company

Math on SVAMP (Accuracy and Significance Testing)

94.2Accuracy (%)Ref. SOTA
45.94458.4727183.528Mar 26, 2026Apr 5, 2026Apr 15, 2026Apr 25, 2026May 5, 2026May 15, 2026May 26, 2026

Evaluation results

MethodLinks
Ref. SOTAModel Type=Proprietary2026.0394.2——
EcoThink2026.0392.8-1.40.068
DARTBase Model=Qwen3-0.6B2026.0581.37——
Original-SFTBase Model=Qwen3-0.6B2026.0580.9——
GRPOBase Model=Qwen3-0.6B2026.0580——
STaRBase Model=Qwen3-0.6B2026.0579.7——
BaseBase Model=Qwen3-0.6B2026.0579.03——
TESSYBase Model=Qwen3-0.6B2026.0579——
DARTBase Model=Qwen2.5-0.5B-Instruct2026.0561.45——
GRPOBase Model=Qwen2.5-0.5B-Instruct2026.0556.4——
Original-SFTBase Model=Qwen2.5-0.5B-Instruct2026.0556.17——
STaRBase Model=Qwen2.5-0.5B-Instruct2026.0555.2——
BaseBase Model=Qwen2.5-0.5B-Instruct2026.0553.95——
TESSYBase Model=Qwen2.5-0.5B-Instruct2026.0547.8——