| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TruthfulQA MCQ | STAR-1 | MCQ Accuracy39.33 | 18 | 3mo ago | |
| SampleQA | VRPO | Accuracy3.21 | 8 | 1mo ago | |
| HaluEval General | Domain-Grounded Tiered Retrieval | Baseline Wins30 | 2 | 4mo ago | |
| TruthfulQA | Domain-Grounded Tiered Retrieval | Baseline Wins12 | 2 | 4mo ago | |
| FreshQA v2 | Domain-Grounded Tiered Retrieval | Baseline Wins16 | 2 | 4mo ago | |
| MMLU Global Facts | Domain-Grounded Tiered Retrieval | Baseline Wins3 | 2 | 4mo ago | |
| TimeQA v2 | Domain-Grounded Tiered Retrieval | Baseline Wins4 | 2 | 4mo ago |