List your company

General Knowledge on MMLU Redux

92.9Exact MatchOpenAI-o1-1217
86.45288.12689.891.474Jan 22, 2025

Evaluation results

MethodLinks
OpenAI-o1-12172025.0192.9
DeepSeek-R1Architecture=MoE, Activated Params=37B, Total Params=671B2025.0192.9
DeepSeek-V3Architecture=MoE, Activated Params=37B, Total Params=671B2025.0189.1
Claude-3.5-Sonnet-10222025.0188.9
GPT-4o-05132025.0188
OpenAI-o1-mini2025.0186.7