Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1530 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| IBS Estimation | SEER brain | 20 | Jun 30, 2026 | ||
| IBS Estimation | MIMIC IV | 20 | Jun 30, 2026 | ||
| IBS Estimation | Employee | 20 | Jun 30, 2026 | ||
| IBS Estimation | SUPPORT | 20 | Jun 30, 2026 | ||
| IBS Estimation | FLCHAIN | 20 | Jun 30, 2026 | ||
| IBS Estimation | NACD | 20 | Jun 30, 2026 | ||
| IBS Estimation | GBSG | 20 | Jun 30, 2026 | ||
| IBS Estimation | Churn | 20 | Jun 30, 2026 | ||
| IBS Estimation | METABRIC | 20 | Jun 30, 2026 | ||
| IBS Estimation | WHAS | 20 | Jun 30, 2026 | ||
| Metric alignment with human understandability judgements | Human SRT BSL | 20 | Jun 30, 2026 | ||
| Metric alignment with human overall quality judgements | Synthetics BSL | 20 | Jun 30, 2026 | ||
| Metric alignment with human understandability judgements | Synthetics BSL | 20 | Jun 30, 2026 | ||
| Metric alignment with human understandability judgements | Known Corruptions BSL | 20 | Jun 30, 2026 | ||
| Cooperative Planning | PARTNR Dialog | 20 | Jun 29, 2026 | ||
| Boolean Network Discovery | Fission 10 variables, 24 rules | 20 | Jun 29, 2026 | ||
| Boolean Network Discovery | Mammalian 10 variables, 23 rules | 20 | Jun 29, 2026 | ||
| Generative Text Steganography | XHS | 20 | Jun 29, 2026 | ||
| Remote physiological measurement | EquiPleth | 20 | Jun 29, 2026 | ||
| Remote physiological measurement | PhysDrive | 20 | Jun 29, 2026 | ||
| Clock-time recognition | Clock-Time | 20 | Jun 29, 2026 | ||
| Mathematical reasoning | SVAMP (full set) | 20 | Jun 29, 2026 | ||
| Arithmetic Calculation | DeepMind-Math | 20 | Jun 29, 2026 | ||
| Harmful Responses | Experiment 1 (Evaluation Set) | 20 | Jun 29, 2026 | ||
| Jailbreak Success | Experiment 1 (Evaluation) | 20 | Jun 29, 2026 |