List your company

Error Detection on HotpotQA (val)

100PrecisionIC-IDK
60.4870.748191.26Feb 4, 2026

Evaluation results

MethodLinks
IC-IDKBase Model=Llama 3.1 8B2026.021002451
IC-IDKBase Model=Mistral 7B2026.0295101854
AYSBase Model=Qwen3-32B2026.0294486370
IC-IDKBase Model=Qwen3-32B2026.029261252
DBA-ABase Model=Llama 3.1 8B2026.0291778377
AYSBase Model=Mistral 7B2026.0290466064
IC-IDKBase Model=Qwen 2.5 72B2026.0290415766
DBA-ABase Model=Mistral 7B2026.0289607269
AYSBase Model=Llama 3.1 8B2026.0289526666
Ensemble-ABase Model=Mistral 7B2026.0288788371
DBA-IBase Model=Llama 3.1 8B2026.0288788373
Ensemble-ABase Model=Llama 3.1 8B2026.0287858674
IC-IDKBase Model=Gemini Flash2026.0287233760
Ensemble-IBase Model=Llama 3.1 8B2026.0286898873
DBA-ABase Model=Qwen3-32B2026.0286838577
IC-IDKBase Model=Gemini Pro2026.0286203259
DBA-IBase Model=Mistral 7B2026.0285556762
Ensemble-IBase Model=Mistral 7B2026.0285727865
DBA-IBase Model=Qwen3-32B2026.0285848576
Ensemble-ABase Model=Qwen3-32B2026.0285898777
Ensemble-IBase Model=Qwen3-32B2026.0284918876
AYSBase Model=Qwen 2.5 72B2026.0284697672
DBA-ABase Model=Qwen 2.5 72B2026.0284848477
DBA-IBase Model=Qwen 2.5 72B2026.0284848477
DBA-ABase Model=Gemini Pro2026.0281667379
Ensemble-ABase Model=Qwen 2.5 72B2026.0280918574
Ensemble-IBase Model=Qwen 2.5 72B2026.0280908574
Ensemble-ABase Model=Gemini Pro2026.0277677278
DBA-ABase Model=Gemini Flash2026.0274646974
AYSBase Model=Gemini Pro2026.0274223459
AYSBase Model=Gemini Flash2026.0273294261
DBA-IBase Model=Gemini Pro2026.0272596574
Ensemble-IBase Model=Gemini Pro2026.0272626674
Ensemble-ABase Model=Gemini Flash2026.0270697075
DBA-IBase Model=Gemini Flash2026.0266706873
Ensemble-IBase Model=Gemini Flash2026.0262736771