| Average of 6 datasets | Dissimilarity + beamsearch | PRR65 | | 120 | 4mo ago |
| NQ | Clustered Self-Assessment | AUROC85.1 | | 98 | 1mo ago |
| TQA | Clustered Self-Assessment | AUROC93.3 | | 98 | 1mo ago |
| XSum | Clustered Self-Assessment | AUROC0.806 | | 98 | 1mo ago |
| NQ 16 additional samples (test) | Clustered Self-Assessment | AUROC85.6 | | 98 | 1mo ago |
| TQA 16 additional samples (test) | Clustered Self-Assessment | AUROC94.1 | | 98 | 1mo ago |
| NQ 4 additional samples (test) | Clustered Self-Assessment | AUROC85.3 | | 98 | 1mo ago |
| TQA 4 additional samples (test) | Clustered Self-Assessment | AUROC0.937 | | 98 | 1mo ago |
| Aggregated Experimental Datasets (XSum, SamSum, CNN, WMT19, MedQUAD, TruthfulQA, CoQA, SciQ, TriviaQA, MMLU, GSM8k) (test) | TAD | Mean Rank1 | | 88 | 2mo ago |
| SVHN (test) | SR | Accuracy100 | | 80 | 2mo ago |
| OKVQA, VizWiz, VQA-RAD, and AdVQA (Average) | VIG-TUQ | AUROC0.691 | | 70 | 1mo ago |
| Musique 500 randomly sampled queries (test) | R2C | AUROC0.8322 | | 70 | 4mo ago |
| HotpotQA 500 randomly sampled queries (test) | R2C | AUROC83.25 | | 70 | 4mo ago |
| PopQA 500 randomly sampled queries (test) | R2C | AUROC0.8709 | | 70 | 4mo ago |
| OKVQA | VSE | AUROC79.9 | | 62 | 24d ago |
| Aggregate All 11 Datasets | TAD | Mean PRR55.7 | | 44 | 2mo ago |
| InfoSeek (val) | PE | Accuracy14.7 | | 42 | 1mo ago |
| Encyclopedic VQA (EVQA) (test) | PE | Accuracy16.9 | | 42 | 1mo ago |
| ImageNet 10 | lowrank-KFAC | NLL0.266 | | 42 | 3mo ago |
| CIFAR10 | lowrank-KFAC | NLL0.256 | | 42 | 3mo ago |
| FashionMNIST | lowrank-KFAC | NLL0.248 | | 42 | 3mo ago |
| Vision Datasets averaged (test) | SGPU | AUROC81.7 | | 36 | 4mo ago |
| τ2-bench Retail | | AUROC0.899 | | 32 | 1mo ago |
| τ2-bench Airline | Progress Advantage | AUROC86.5 | | 32 | 1mo ago |
| LongFact | Ecc | PCC-0.017 | | 32 | 3mo ago |