| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TruthfulQA MC2 | MC2 Accuracy56.46 | 51 | 14d ago | ||
| TruthfulQA | MARI | MC1 Score81.94 | 36 | 5d ago | |
| TruthfulQA | LLaDA | Accuracy (TruthfulQA)56.8 | 24 | 21d ago | |
| TruthfulQA f_con o=5 | Acc (Exact)100 | 18 | 3mo ago | ||
| TruthfulQA | ϵ-FTRL | Mean Per-Step Regret0.138 | 15 | 3mo ago | |
| TruthfulQA | SEA | TruthRate83 | 13 | 21d ago | |
| TruthfulQA | ZeroRL + ACTGUIDE-RL | TruthfulQA Score62.3 | 5 | 20d ago | |
| TruthfulQA | Llama | Normalized Probability Mass33.7 | 3 | 2mo ago | |
| TruthfulQA o=5 (f_clean) | Accuracy (Exact)55.5 | 3 | 3mo ago |