Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1248 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Interactive Decision-making | ScienceWorld Unseen (test) | 24 | Feb 26, 2026 | ||
| Sarcasm Detection | SemEval 2018 | 24 | Feb 26, 2026 | ||
| Sarcasm Detection | IAC V2 | 24 | Feb 26, 2026 | ||
| Sarcasm Detection | IAC V1 | 24 | Feb 26, 2026 | ||
| Confidence Calibration in Retrieval-Augmented Generation | Bamboogle k=5 OOD (test) | 24 | Feb 26, 2026 | ||
| Confidence Calibration in Retrieval-Augmented Generation | NQ k=5 OOD (test) | 24 | Feb 26, 2026 | ||
| Calibration | Average StrategyQA, HotpotQA, NQ, Bamboogle | 24 | Feb 26, 2026 | ||
| Calibration | Bamboogle | 24 | Feb 26, 2026 | ||
| Calibration | HotpotQA | 24 | Feb 26, 2026 | ||
| Calibration | StrategyQA | 24 | Feb 26, 2026 | ||
| Factuality Correction | VELI5 1.0 (test) | 24 | Feb 26, 2026 | ||
| Factuality Correction | BIO dataset | 24 | Feb 26, 2026 | ||
| Model Editing | CounterFact | 24 | Feb 26, 2026 | ||
| Scholarly Abstract Generation | LaMP Scholar | 24 | Feb 26, 2026 | ||
| Product Rating Prediction | LaMP Rating | 24 | Feb 26, 2026 | ||
| Movie Recommendation | LaMP Movie | 24 | Feb 26, 2026 | ||
| Citation Recommendation | LaMP Citation | 24 | Feb 26, 2026 | ||
| Long-context language modeling | ZeroSCROLLS (test) | 24 | Feb 26, 2026 | ||
| Concept Recognition | HoIP trained on ALD | 24 | Feb 26, 2026 | ||
| Factuality Evaluation | FActScore | 24 | Jun 2, 2026 | ||
| Binary decision task | LAPOP (test) | 24 | Feb 26, 2026 | ||
| Binary decision task | AFRO Africa (test) | 24 | Feb 26, 2026 | ||
| Binary decision task | ISD India (test) | 24 | Feb 26, 2026 | ||
| Binary decision task | CGSS China (test) | 24 | Feb 26, 2026 | ||
| Binary decision task | GSS United States (test) | 24 | Feb 26, 2026 |