List your company

Mathematical Problem Solving on MATH (Normalized Score)

97Normalized ScoreDeepSeek–R1
-2.8423.084974.92Nov 9, 2025

Evaluation results

MethodLinks
DeepSeek–R1Model Category=Reasoning Models, Assessed Version Date=2025-052025.1197
GPT-o1Model Category=Reasoning Models, Assessed Version Date=2024-092025.1196
GPT-4oModel Category=Closed-Source Models (non-reasoning), Assessed Version Date=2025-032025.1177
Qwen2.5-3B-InstructModel Category=Open-Source Models (non-reasoning)2025.1176
GPT-4o-MiniModel Category=Closed-Source Models (non-reasoning), Assessed Version Date=2024-112025.1170
GPT-3.5-TurboModel Category=Closed-Source Models (non-reasoning), Assessed Version Date=2023-112025.1143
LLaMA2-13B-ChatModel Category=Open-Source Models (non-reasoning)2025.1128
Falcon-7B-InstructModel Category=Open-Source Models (non-reasoning)2025.111