Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1214 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sampling | DW-4 8 dimensions standard Gaussian reference | 24 | Mar 26, 2026 | ||
| Artist Success Ranking | WikiArt-Seq2Rank time series split 1.0 (test) | 24 | Mar 26, 2026 | ||
| Long-context understanding | RULER | 24 | May 11, 2026 | ||
| Input Discrimination | MNIST DeepGini subsets | 24 | Mar 25, 2026 | ||
| Mutation Killing | MN (Non-Killable) | 24 | Mar 25, 2026 | ||
| Fine-Grained Visual Recognition | Stanford Dogs (val) | 24 | Mar 25, 2026 | ||
| Fine-Grained Visual Recognition | Stanford40 (val) | 24 | Mar 25, 2026 | ||
| Fine-Grained Visual Recognition | CUB200 (val) | 24 | Mar 25, 2026 | ||
| Downstream generation | MS MARCO | 24 | Mar 25, 2026 | ||
| Downstream generation | NQ | 24 | Mar 25, 2026 | ||
| Downstream generation | HotpotQA | 24 | Mar 25, 2026 | ||
| Solving PDE | Burgers | 24 | May 12, 2026 | ||
| General Reasoning | Overall | 24 | May 26, 2026 | ||
| Robotic Manipulation | RoboCasa GR1 Tabletop | 24 | Jul 7, 2026 | ||
| Object Detection | APRICOT Untargeted | 24 | Mar 24, 2026 | ||
| Object Detection | APRICOT Targeted | 24 | Mar 24, 2026 | ||
| Model Fingerprinting | PROTEINS | 24 | Mar 24, 2026 | ||
| Binary Hate Detection | H-VLI (Overall) | 24 | Mar 24, 2026 | ||
| Binary Hate Detection | H-VLI (Hard) | 24 | Mar 24, 2026 | ||
| Binary Hate Detection | H-VLI (Normal) | 24 | Mar 24, 2026 | ||
| Binary Hate Detection | H-VLI Easy | 24 | Mar 24, 2026 | ||
| Fine-grained Hate Categorization | H-VLI | 24 | Mar 24, 2026 | ||
| Fine-grained Hate Categorization | H-VLI (Hard) | 24 | Mar 24, 2026 | ||
| Fine-grained Hate Categorization | H-VLI (Normal) | 24 | Mar 24, 2026 | ||
| Fine-grained Hate Categorization | H-VLI (Easy) | 24 | Mar 24, 2026 |