List your company

User Simulation on Instruments

38.12F1 ScoreCoARS
9.322416.798724.27531.7513Apr 11, 2026

Evaluation results

MethodLinks
CoARSBackbone=Qwen3-8B2026.0438.12
iAgentBackbone=GPT-5.4-mini2026.0436.84
AFLBackbone=GPT-5.4-mini2026.0434.84
iAgentBackbone=Qwen3-8B2026.0431.46
CoARSBackbone=Qwen3-4B2026.0428.54
RecoWorldBackbone=Qwen3-8B2026.0426.64
iAgentBackbone=Qwen3-4B2026.0426.42
AFLBackbone=Qwen3-8B2026.0423.84
AFLBackbone=Qwen3-4B2026.0419.84
ReflexionBackbone=GPT-5.4-mini2026.0414.56
ReflexionBackbone=Qwen3-8B2026.0412.84
RecoWorldBackbone=Qwen3-4B2026.0412.56
ReflexionBackbone=Qwen3-4B2026.0410.43