List your company

Multi-turn interaction accuracy on Multi-turn interaction follow-ups Round 1

76.71Accuracyclaude
53.538859.554465.5771.5856Mar 28, 2025

Evaluation results

MethodLinks
claude2025.0376.71
CARG2025.0375.43
qwen2025.0367
mistral2025.0357.71
gemini2025.0356.29
llama2025.0354.43