Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Hallucination Detection on CoQA

0.8584Mean AUROC

SpikeScore

0.4724560.5726530.672850.773047Jan 27, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
0.8584
2026.01
0.854
2026.01
0.8333
2026.01
0.8205
2026.01
0.8155
2026.01
0.8116
2026.01
0.8084
2026.01
0.8074
2026.01
0.8
2026.01
0.7984
2026.01
0.7917
2026.01
0.7891
2026.01
0.7013
2026.01
0.6876
2026.01
0.6809
2026.01
0.679
2026.01
0.6787
2026.01
0.6761
2026.01
0.6615
2026.01
0.6571
2026.01
0.6538
2026.01
0.6532
2026.01
0.6468
2026.01
0.6456
2026.01
0.642
2026.01
0.6417
2026.01
0.6397
2026.01
0.6392
2026.01
0.6358
2026.01
0.6302
2026.01
0.6301
2026.01
0.6284
2026.01
0.6254
2026.01
0.6161
2026.01
0.6133
2026.01
0.612
2026.01
0.609
2026.01
0.6037
2026.01
0.5962
2026.01
0.5948
2026.01
0.54
2026.01
0.5275
2026.01
0.5221
2026.01
0.5172
2026.01
0.5164
2026.01
0.5137
2026.01
0.4984
2026.01
0.4873