List your company

Utterance Classification on Architecture Deliberation 19 turns Phase 3 (Overall)

85F1 ScoreClaude Sonnet 4
65.2470.3775.580.63May 13, 2026

Evaluation results

MethodLinks
Claude Sonnet 4Condition=Definitions condition only, Runs=52026.058563
GPT-4oCondition=Definitions condition only, Runs=52026.058065
Qwen2.5-7B-InstructCondition=Definitions condition only, Runs=52026.057561
Llama-3.1-8B-InstructCondition=Definitions condition only, Runs=52026.056633