List your company

Error Detection on FRAMES (test)

97PrecisionAYS
53.3264.667687.34Feb 4, 2026

Evaluation results

MethodLinks
AYSBase Model=Llama 3.1 8B2026.0297405764
IC-IDKBase Model=Llama 3.1 8B2026.0297122154
IC-IDKBase Model=Qwen 2.5 72B2026.0297254061
IC-IDKBase Model=Mistral 7B2026.0296375363
DBA-ABase Model=Llama 3.1 8B2026.0295929471
Ensemble-ABase Model=Llama 3.1 8B2026.0295949470
DBA-IBase Model=Llama 3.1 8B2026.0294939367
Ensemble-IBase Model=Llama 3.1 8B2026.0294969565
DBA-ABase Model=Mistral 7B2026.0293879069
AYSBase Model=Qwen3-32B2026.0293748271
DBA-ABase Model=Qwen3-32B2026.0293899173
DBA-IBase Model=Qwen 2.5 72B2026.0293899179
Ensemble-ABase Model=Mistral 7B2026.0292899166
IC-IDKBase Model=Qwen3-32B2026.0292101752
DBA-IBase Model=Qwen3-32B2026.0292949372
AYSBase Model=Mistral 7B2026.0291415756
DBA-IBase Model=Mistral 7B2026.0291909062
Ensemble-IBase Model=Mistral 7B2026.0291939261
Ensemble-ABase Model=Qwen3-32B2026.0291969368
Ensemble-IBase Model=Qwen3-32B2026.0291979469
AYSBase Model=Qwen 2.5 72B2026.0291748169
DBA-ABase Model=Qwen 2.5 72B2026.0291858872
Ensemble-ABase Model=Qwen 2.5 72B2026.0290949270
Ensemble-IBase Model=Qwen 2.5 72B2026.0290969372
DBA-ABase Model=Gemini Flash2026.0272717177
IC-IDKBase Model=Gemini Flash2026.0270122155
DBA-IBase Model=Gemini Flash2026.0269747176
DBA-ABase Model=Gemini Pro2026.0269525971
AYSBase Model=Gemini Flash2026.0268505768
Ensemble-ABase Model=Gemini Flash2026.0267867579
IC-IDKBase Model=Gemini Pro2026.02675952
Ensemble-IBase Model=Gemini Flash2026.0266837378
Ensemble-ABase Model=Gemini Pro2026.0262586072
DBA-IBase Model=Gemini Pro2026.0258585871
AYSBase Model=Gemini Pro2026.0255223157
Ensemble-IBase Model=Gemini Pro2026.0255656072