List your company

Distortion Diagnosis on ReMMDBench (500-sample split)

44.73PrecisionReMMD-Agent
37.678839.509441.3443.1706Jun 23, 2026

Evaluation results

MethodLinks
ReMMD-AgentBackbone=Qwen3.6-27B2026.0644.7339.241.110.8
ReMMD-AgentBackbone=Qwen3.5-9B2026.0644.5850.8846.9710
ReMMD-AgentBackbone=GPT-5.22026.0644.3147.0145.155
ManusBackbone=proprietary2026.0643.6942.3242.757.6
ReMMD-AgentBackbone=Gemma4-31B2026.0643.6741.3142.277.8
MMD-AgentBackbone=Qwen3.5-4B2026.0643.0832.734.457.2
ReMMD-AgentBackbone=Qwen3.5-4B2026.0642.5942.8941.946
MMD-AgentBackbone=GPT-5.22026.0642.2448.8341.982
T2-AgentBackbone=GPT-5.22026.0642.1547.1542.682.6
ChatGPTBackbone=proprietary2026.0641.7147.5643.633
T2-AgentBackbone=Qwen3.6-27B2026.0641.6327.0927.744.2
MMD-AgentBackbone=Qwen3.6-27B2026.0641.5938.6137.944.8
T2-AgentBackbone=Gemma4-31B2026.0641.1638.7338.737.6
MMD-AgentBackbone=Gemma4-31B2026.0640.9442.1140.825.2
MMD-AgentBackbone=Qwen3.5-9B2026.0640.140.3138.155.8
T2-AgentBackbone=Qwen3.5-9B2026.0638.8327.1428.583.2
T2-AgentBackbone=Qwen3.5-4B2026.0637.9527.2628.51.8