List your company

Error Detection on CRAG

91F1 ScoreEnsemble-A
47.3258.667081.34Feb 4, 2026

Evaluation results

MethodLinks
Ensemble-AModel=Qwen3-8B2026.0291879567
Ensemble-IModel=Qwen3-8B2026.0291889570
Ensemble-AModel=Qwen 8B2026.0291——67
Ensemble-IModel=Qwen 8B2026.0291——70
DBA-AModel=Qwen3-8B2026.0289898973
DBA-IModel=Qwen3-8B2026.0289898973
DBA-AModel=Qwen 8B2026.0289——73
DBA-IModel=Qwen 8B2026.0289——73
Ensemble-IModel=Llama 3.3 70B2026.0277807474
Ensemble-IModel=Llama 3.3 70B2026.0277——74
IC-IDKModel=Qwen3-8B2026.0276866861
IC-IDKModel=Qwen 8B2026.0276——61
Ensemble-AModel=GPT 5.12026.0275737781
IC-IDKModel=Llama 3.3 70B2026.0275708167
AYSModel=Qwen3-8B2026.0275906468
Ensemble-AModel=GPT 5.12026.0275——81
IC-IDKModel=Llama 3.3 70B2026.0275——67
AYSModel=Qwen 8B2026.0275——68
Ensemble-IModel=GPT 5.12026.0274737580
DBA-IModel=Llama 3.3 70B2026.0274876576
Ensemble-AModel=Llama 3.3 70B2026.0274767270
Ensemble-IModel=GPT 5.12026.0274——80
DBA-IModel=Llama 3.3 70B2026.0274——76
Ensemble-AModel=Llama 3.3 70B2026.0274——70
DBA-AModel=Llama 3.3 70B2026.0271796571
DBA-AModel=Llama 3.3 70B2026.0271——71
AYSModel=GPT 5.12026.0266755974
AYSModel=GPT 5.12026.0266——74
IC-IDKModel=GPT 5.12026.0260715270
IC-IDKModel=GPT 5.12026.0260——70
DBA-AModel=GPT 5.12026.0253774067
AYSModel=Llama 3.3 70B2026.0253823964
DBA-AModel=GPT 5.12026.0253——67
AYSModel=Llama 3.3 70B2026.0253——64
DBA-IModel=GPT 5.12026.0249753765
DBA-IModel=GPT 5.12026.0249——65