List your company

Multiple Choice Question Answering on Diet-QA 1.0 (test)

72.9Remember AccuracyQwen-2-72B-Instruct
62.565.267.970.6Jan 28, 2026

Evaluation results

MethodLinks
Qwen-2-72B-Instructinference_mode=Zero-shot2026.0172.957.464.959.863.8
GPT-4o-Miniinference_mode=Zero-shot2026.017056.165.361.563.2
Kimi-K2inference_mode=Zero-shot2026.0169.161.267.769.566.9
GPT-4oinference_mode=Zero-shot2026.0165.7606260.662.1
Qwen-2.5-72Binference_mode=Zero-shot2026.0165.755.858.354.558.6
Mixtral-8x7Binference_mode=Zero-shot2026.0164.849.257.148.855
DeepSeek-V3inference_mode=Zero-shot2026.0164.658.66158.560.7
Llama-3-70Binference_mode=Zero-shot2026.0162.952.359.554.757.4