| TriviaQA (test) | ACT-ViT | AUROC87.91 | | 104 | 9d ago |
| JudgeBench (test) | Energy | AUROC71.53 | | 77 | 1mo ago |
| TriviaQA | VC | AUROC85.56 | | 77 | 16d ago |
| SciQA | Eigenscore | AUROC0.8269 | | 56 | 16d ago |
| CoQA (test) | SAR | AUROC77.3 | | 42 | 1mo ago |
| WebQA | SE + MARS | AUROC73.57 | | 30 | 1mo ago |
| NaturalQA | SE + MARS | AUROC75.5 | | 30 | 1mo ago |
| OBQA | DeepEns | AUROC88.03 | | 24 | 5d ago |
| RACE Llama-3.1-8B and Gemma-2-9B backbones (test) | ETN | AUROC91.3 | | 24 | 5d ago |
| SimpleQA, MuSiQue, and TruthfulQA Average | Internal Confidence | AUROC61 | | 24 | 1mo ago |
| TruthfulQA | Internal Confidence | AUROC63.2 | | 24 | 1mo ago |
| MuSiQue | Predictive Entropy | AUROC65.6 | | 24 | 1mo ago |
| SimpleQA | P(YES) (top right) | AUROC61.3 | | 24 | 1mo ago |
| MMLU Camel | MATU | AUROC0.7149 | | 16 | 5d ago |
| MoreHopQA Camel | MATU | AUROC65.29 | | 16 | 5d ago |
| MATH Camel | MATU | AUROC0.7354 | | 16 | 5d ago |
| MMLU AutoGen (test) | MATU | AUROC0.7315 | | 16 | 5d ago |
| MoreHopQA AutoGen (test) | MATU | AUROC63.92 | | 16 | 5d ago |
| MATH AutoGen (test) | MATU | AUROC0.7544 | | 16 | 5d ago |
| CIFAR10-C Benign Stream | SICL | ECE6.4 | | 16 | 1mo ago |
| PopQA | EigV+MCH | A183.09 | | 16 | 1mo ago |
| NQ-open | EigV+MCH | A1 Accuracy88.67 | | 16 | 1mo ago |
| Aggregate (Cola, GEmot, IMDB, News, SST5, Toxigen, YELP) | ALIEN | ECE8.4 | | 13 | 11d ago |
| HotpotQA (test) | Signatures | AUPRC72.79 | | 12 | 24d ago |
| Solar 1Y (test) | EnbPI | $Δ$ Cov-0.002 | | 8 | 1mo ago |