List your company

Mathematical Reasoning on GSM8K MC

95.68AccuracySC
83.855286.925189.99593.0649Mar 15, 2026

Evaluation results

MethodLinks
SCModel=Olmo-2-13B2026.0395.68
IoTModel=GPT-4o mini2026.0395
CoTModel=GPT-4o mini2026.0394.74
IoTModel=Olmo-2-13B2026.0393.1
SCModel=Llama-3.3-8B2026.0391.89
IoTModel=Olmo-2-7B2026.0391.66
CoTModel=Olmo-2-13B2026.0391.36
IoTModel=Llama-3.3-8B2026.0390.67
EoTModel=Olmo-2-13B2026.0390.14
SCModel=Olmo-2-7B2026.0389.39
CoTModel=Olmo-2-7B2026.0389.08
CoTModel=Llama-3.3-8B2026.0387.41
EoTModel=Olmo-2-7B2026.0387.06
EoTModel=Llama-3.3-8B2026.0384.31