Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 318 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| final diagnosis prediction | MIMIC | 56 | Mar 31, 2026 | ||
| Graphical API Recommendation | Python 13 | 56 | Mar 30, 2026 | ||
| Crowd Counting | SHHA | 56 | Mar 27, 2026 | ||
| Crowd Counting | UCF-QNRF | 56 | Mar 27, 2026 | ||
| Spectral Unmixing | CellAtlas S.7 (test) | 56 | Mar 26, 2026 | ||
| Token-forcing loss optimization | Random targets Held-out (val) | 56 | Mar 26, 2026 | ||
| Point Cloud Classification | HeliALS (test) | 56 | Mar 25, 2026 | ||
| Time-series forecasting | Baicheng Station | 56 | Mar 25, 2026 | ||
| Time-series forecasting | Beijing Station | 56 | Mar 25, 2026 | ||
| Logical Reasoning | Stepgame k=10 | 56 | Mar 25, 2026 | ||
| Logical Reasoning | Stepgame k=4 | 56 | Mar 25, 2026 | ||
| Logical Reasoning | Stepgame k=3 | 56 | Mar 25, 2026 | ||
| Image Generation | AFHQ v1 (test) | 56 | Mar 24, 2026 | ||
| Image Generation | LSUN Bedroom v1 (test) | 56 | Mar 24, 2026 | ||
| Medical Reasoning | Professional Medicine | 56 | Mar 24, 2026 | ||
| Helpful and Harmless Preference Reasoning | HH-RLHF | 56 | Mar 24, 2026 | ||
| Multimodal Jailbreaking | VE-Safety | 56 | Mar 24, 2026 | ||
| Image Classification | Food101 | 56 | Apr 23, 2026 | ||
| Image Classification | ImageFruit | 56 | May 21, 2026 | ||
| Distributional alignment | out-of-domain (test) | 56 | Mar 17, 2026 | ||
| Distributional Alignment | in-domain (test) | 56 | Mar 17, 2026 | ||
| Person Re-identification | UnSeen Avg | 56 | Mar 23, 2026 | ||
| Long-context retrieval | Needle-in-a-Haystack (test) | 56 | Apr 2, 2026 | ||
| Trajectory Prediction | Argoverse 1 (val) | 56 | Mar 12, 2026 | ||
| Parameter Estimation | SNIC regime 1% noise 1.0 (test) | 56 | Mar 11, 2026 |