| HotpotQA | Ensemble-A | AUROC81 | | 57 | 3mo ago |
| EuroSAT | Ours | AuROC98.1 | | 48 | 2mo ago |
| Flowers102 | Ours-D | AuROC99.38 | | 46 | 2mo ago |
| Average All shifts (test) | ENS-F | AUC90.99 | | 40 | 5mo ago |
| Corruptions (test) | MDSall | AUC99.1 | | 40 | 5mo ago |
| Adversarial Attacks (test) | ENS-V | AUC89.52 | | 40 | 5mo ago |
| In-distribution (test) | MSP | AUC0.8916 | | 40 | 5mo ago |
| MuSiQue (val) | IC-IDK | Precision1 | | 36 | 5mo ago |
| Mintaka (val) | IC-IDK | Precision100 | | 36 | 5mo ago |
| HotpotQA (val) | IC-IDK | Precision100 | | 36 | 5mo ago |
| FRAMES (test) | AYS | Precision97 | | 36 | 5mo ago |
| CRAG multi-hop subset (train) | AYS | Precision92 | | 36 | 5mo ago |
| Bamboogle Full | IC-IDK | Precision100 | | 36 | 5mo ago |
| MuSiQue | Ensemble-A | F1 Score0.93 | | 36 | 5mo ago |
| Mintaka | Ensemble-A | F1 Score88 | | 36 | 5mo ago |
| FRAMES | Ensemble-I | F1 Score95 | | 36 | 5mo ago |
| CRAG | Ensemble-A | F1 Score91 | | 36 | 5mo ago |
| Bamboogle | Ensemble-A | F1 Score0.94 | | 36 | 5mo ago |
| ImageNet | | FDR47 | | 36 | 2mo ago |
| Food101 | ANTS | AuROC99.92 | | 29 | 4mo ago |
| Unanswerability hallucination detection benchmarks (Average) | COMET | AUC75.1 | | 28 | 24d ago |
| CoSPlan | CoT | Robo-VQA-E Score9.1 | | 20 | 5mo ago |
| Perturbation Benchmark 24-paper frontier | OpenAIReview | Recall0.716 | | 17 | 1mo ago |
| FCE (test) | GOPar | F0.5 Score74.1 | | 16 | 5mo ago |
| KITTI DK:test^noise noise-induced (test) | DETR | Recall96 | | 15 | 2mo ago |
