Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 317 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Harmfulness Evaluation | DirectHarm (test) | 56 | Apr 24, 2026 | ||
| Face Attribute Editing | CelebA-HQ (test) | 56 | Apr 24, 2026 | ||
| Function Calling | BFCL | 56 | Apr 24, 2026 | ||
| Crash-outcome information retention | Held-out Crash Interaction (test) | 56 | Apr 21, 2026 | ||
| Language Modeling | FineWeb 10B (val) | 56 | May 25, 2026 | ||
| Semantic Segmentation | Hunan (test) | 56 | Apr 20, 2026 | ||
| Semantic Segmentation | DSTL (test) | 56 | Apr 20, 2026 | ||
| Visual Question Answering | LLaVA-W | 56 | Apr 16, 2026 | ||
| Classification | STPCTLS | 56 | Apr 14, 2026 | ||
| Sleep Staging | Sleep-EDFx (Target Domain I) | 56 | Apr 14, 2026 | ||
| Untargeted Attack | IITD | 56 | Apr 10, 2026 | ||
| Targeted Attack | IITD (test) | 56 | Apr 10, 2026 | ||
| Targeted Attack | Tongji (test) | 56 | Apr 10, 2026 | ||
| Untargeted Adversarial Attack | AISEC (test) | 56 | Apr 10, 2026 | ||
| Untargeted Attack | Tongji (test) | 56 | Apr 10, 2026 | ||
| Targeted Adversarial Attack | AISEC | 56 | Apr 10, 2026 | ||
| Classwise Calibration | CIFAR-10 LT | 56 | Apr 10, 2026 | ||
| Boolean Question Answering | BoolQ | 56 | Jul 1, 2026 | ||
| Classification | BANKCHURN (test) | 56 | Apr 7, 2026 | ||
| Regression | TabArena Lite | 56 | Jun 30, 2026 | ||
| Membership Inference Attack | WikiMIA length 128 | 56 | Apr 1, 2026 | ||
| Job Shop Scheduling | JSSP ft, la, abz, orb, ta instances | 56 | Mar 31, 2026 | ||
| final diagnosis prediction | MIMIC, MedCaseReasoning, ER-Reason Average | 56 | Mar 31, 2026 | ||
| final diagnosis prediction | ER-Reason | 56 | Mar 31, 2026 | ||
| final diagnosis prediction | MedCaseReasoning | 56 | Mar 31, 2026 |