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

Hallucination Detection on CommonsenseQA

0.7563Mean AUROC

SpikeScore

0.4887080.5581790.627650.697121Jan 27, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
0.7563
2026.01
0.7451
2026.01
0.7411
2026.01
0.7249
2026.01
0.7205
2026.01
0.7187
2026.01
0.7186
2026.01
0.7118
2026.01
0.7075
2026.01
0.7051
2026.01
0.703
2026.01
0.6988
2026.01
0.6947
2026.01
0.6911
2026.01
0.6895
2026.01
0.6864
2026.01
0.6814
2026.01
0.6725
2026.01
0.667
2026.01
0.6664
2026.01
0.6626
2026.01
0.656
2026.01
0.6528
2026.01
0.6402
2026.01
0.6385
2026.01
0.6379
2026.01
0.6378
2026.01
0.6287
2026.01
0.6283
2026.01
0.625
2026.01
0.6108
2026.01
0.5893
2026.01
0.5476
2026.01
0.5468
2026.01
0.5411
2026.01
0.5384
2026.01
0.5319
2026.01
0.5309
2026.01
0.5281
2026.01
0.5232
2026.01
0.5226
2026.01
0.5217
2026.01
0.517
2026.01
0.5164
2026.01
0.5163
2026.01
0.5157
2026.01
0.5102
2026.01
0.499