List your company

Evidence-Grounded Diagnostic Reasoning on CXReasonDial

99.7CoverageCXReasonAgent
98.24498.6229999.378Feb 26, 2026

Evaluation results

MethodLinks
CXReasonAgentBackbone=Qwen2.5-7B, GT Setting=With GT (w/)2026.0299.789.59095.34.680.623.1
CXReasonAgentBackbone=Qwen2.5-32B, GT Setting=Without GT (w/o)2026.0299.698.69797.62.394.261.1
CXReasonAgentBackbone=Qwen2.5-7B, GT Setting=Without GT (w/o)2026.0299.686.386.693.76.376.621.1
CXReasonAgentBackbone=Qwen2.5-1.5B, GT Setting=Without GT (w/o)2026.0299.691.692.194.75.380.431.6
CXReasonAgentBackbone=Gemini-1.5-Flash, GT Setting=Without GT (w/o)2026.0299.599.897.699.70.396.873.4
CXReasonAgentBackbone=GPT-4o mini, GT Setting=Without GT (w/o)2026.0299.599.998.299.20.896.974.8
CXReasonAgentBackbone=GPT-4o mini, GT Setting=With GT (w/)2026.0299.599.998.299.20.896.974.2
CXReasonAgentBackbone=Qwen2.5-32B, GT Setting=With GT (w/)2026.0299.59797.398.61.491.659
CXReasonAgentBackbone=Gemini-1.5-Flash, GT Setting=With GT (w/)2026.0299.499.897.699.70.396.672.2
CXReasonAgentBackbone=Llama 3.1-70B, GT Setting=Without GT (w/o)2026.0299.499.396.799.30.795.365.8
CXReasonAgentBackbone=Llama 3.1-70B, GT Setting=With GT (w/)2026.0299.499.496.999.20.895.565.2
CXReasonAgentBackbone=Qwen2.5-1.5B, GT Setting=With GT (w/)2026.0299.492.693.796.33.782.232.9
MedGemma 27BGT Setting=Without GT (w/o)2026.0298.9——53.945.446.16.1
Pixtral-LargeGT Setting=Without GT (w/o)2026.0298.8——57.941.548.65.9
Pixtral-LargeGT Setting=With GT (w/)2026.0298.8——79.820.165.46
MedGemma 27BGT Setting=With GT (w/)2026.0298.5——76.223.264.16.5
Gemini-1.5-FlashCategory=LVLM Baseline, GT Setting=Without GT (w/o)2026.0298.3——43.155.636.98.6
Gemini-1.5-FlashCategory=LVLM Baseline, GT Setting=With GT (w/)2026.0298.3——81.11869.19.8