List your company

Multiple-choice Question Answering on ARC

86.31AccuracyGPT-4o
13.021232.048151.07570.1019Feb 23, 2026

Evaluation results

MethodLinks
GPT-4o2026.0286.31
Mistral Large2026.0272.32
Llama3-70B-InstructSize=70B, Type=Instruct2026.0267.09
Claude 3 Haiku2026.0263.89
Gemma (2B)Size=2B2026.0223.93
Qwen1.5 (1.8B)Size=1.8B2026.0215.84