| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TruthfulQA | PEAR | Accuracy91.5 | 145 | 1mo ago | |
| BIOS | PROXIMALByte | Factuality56 | 28 | 4mo ago | |
| MMLU | GPT-4 | EM82.4 | 16 | 4mo ago | |
| NQ-Swap | CoDA | Science Category Score43.7 | 12 | 4mo ago | |
| SelfAware | Base Model | Score0.372 | 10 | 4mo ago | |
| SimpleVQA | LoMo | Factuality Score43.51 | 8 | 1mo ago | |
| SimpleQA | Kimi-K2 | Factuality Score35.3 | 7 | 4mo ago | |
| TruthfulQA gen | FGD | BLEU Acc42 | 5 | 4mo ago | |
| TruthfulQA | Factuality Score55.6 | 4 | 4mo ago | ||
| TruthfulQA | Otrue | Quality Score99.5 | 2 | 29d ago |