List your company

Error Detection on CRAG multi-hop subset (train)

92PrecisionAYS
62.8870.447885.56Feb 4, 2026

Evaluation results

MethodLinks
AYSBase Model=Mistral 7B2026.0292203358
IC-IDKBase Model=Llama 3.1 8B2026.0291254059
AYSBase Model=Qwen 2.5 72B2026.0291728078
DBA-ABase Model=Qwen 2.5 72B2026.0291838783
IC-IDKBase Model=Mistral 7B2026.0290516567
AYSBase Model=Qwen3-32B2026.0290617271
DBA-IBase Model=Qwen3-32B2026.0290868880
DBA-IBase Model=Qwen 2.5 72B2026.0290818581
Ensemble-ABase Model=Mistral 7B2026.0289848776
DBA-IBase Model=Llama 3.1 8B2026.0289878879
DBA-ABase Model=Qwen3-32B2026.0289878879
DBA-ABase Model=Mistral 7B2026.0288818475
DBA-ABase Model=Llama 3.1 8B2026.0288848676
DBA-IBase Model=Mistral 7B2026.0287858673
Ensemble-ABase Model=Qwen 2.5 72B2026.0287878780
Ensemble-IBase Model=Mistral 7B2026.0286858671
AYSBase Model=Llama 3.1 8B2026.0286546666
IC-IDKBase Model=Qwen3-32B2026.0286324658
Ensemble-IBase Model=Qwen3-32B2026.0286918874
Ensemble-IBase Model=Qwen 2.5 72B2026.0286888778
Ensemble-ABase Model=Qwen3-32B2026.0285898774
AYSBase Model=Gemini Flash2026.0285677580
Ensemble-ABase Model=Llama 3.1 8B2026.0284888671
Ensemble-IBase Model=Llama 3.1 8B2026.0284918771
IC-IDKBase Model=Qwen 2.5 72B2026.0284476064
AYSBase Model=Gemini Pro2026.0280566674
DBA-ABase Model=Gemini Flash2026.0277576574
IC-IDKBase Model=Gemini Pro2026.0277304362
Ensemble-ABase Model=Gemini Pro2026.0276707379
Ensemble-ABase Model=Gemini Flash2026.0275827883
Ensemble-IBase Model=Gemini Pro2026.0275687177
DBA-IBase Model=Gemini Flash2026.0273576473
Ensemble-IBase Model=Gemini Flash2026.0272827782
DBA-ABase Model=Gemini Pro2026.0270334563
DBA-IBase Model=Gemini Pro2026.0265304161
IC-IDKBase Model=Gemini Flash2026.0264283959