| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| IQA-EVAL MMLU-derived (TextDavinci) | Helpfulness4.6 | 8 | 4d ago | ||
| Natural Questions | Helpfulness4.9 | 8 | 4d ago | ||
| IN3 | OursO | Ask Rate100 | 7 | 4d ago | |
| QuestBench Math | OursI | Accuracy53.9 | 7 | 4d ago | |
| AskMind | OursO | Accuracy61.7 | 7 | 4d ago | |
| AskOverconfidence | Accuracy84 | 5 | 4d ago | ||
| IQA-EVAL MMLU-derived (TextBabbage) | IQA-EVAL-GPT3.5 | Helpfulness3.87 | 4 | 4d ago |