List your company

Multi-task Language Understanding on MMLU (dev)

86.4AccuracyGPT-4
65.225670.722876.2281.7172Jan 24, 2025

Evaluation results

MethodLinks
GPT-42025.0186.4
GPT-3.52025.0170
TAMA2025.0166.99
base2025.0166.04