Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1065 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Offline Reinforcement Learning | D4RL AntMaze-Medium Diverse | 26 | Jun 11, 2026 | ||
| Universal Speech Enhancement | URGENT non-blind 2025 (test) | 26 | Jun 25, 2026 | ||
| Multimodal Safety Evaluation | SPA-VL | 26 | Mar 4, 2026 | ||
| Harmful Refusal | DAN | 26 | Jul 7, 2026 | ||
| Harmful Refusal | WJB | 26 | Jul 7, 2026 | ||
| Text Classification | HuffPost | 26 | Mar 4, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP N=50 | 26 | Jun 11, 2026 | ||
| Generative Modeling | CIFAR-10 posterior sampling | 26 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | 1T10S HalfCheetah (Medium-Expert) | 26 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | 1T10S Hopper (Medium-Expert) | 26 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | 1T10S Hopper (Medium-Replay) | 26 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | Hopper 1T10S (Medium) | 26 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | 1T10S Walker2D (Medium-Expert) | 26 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | 1T10S Walker2D (Medium-Replay) | 26 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | 1T10S Walker2D (Medium) | 26 | Mar 4, 2026 | ||
| Watermark Detection | C4 OPT-6.7B | 26 | Mar 17, 2026 | ||
| text-to-video generation | VBench | 26 | Mar 4, 2026 | ||
| Inpaint (box) | ImageNet | 26 | Mar 10, 2026 | ||
| Semantic Segmentation | COCO-EA | 26 | Mar 4, 2026 | ||
| Excavation operation counting | Excavation videos (test) | 26 | Mar 4, 2026 | ||
| Reasoning | Reasoning Benchmarks Zero-shot | 26 | May 26, 2026 | ||
| Binary Classification | RelBench 1.0 (test) | 26 | Apr 15, 2026 | ||
| Recommendation | MovieLens 100K | 26 | Jun 16, 2026 | ||
| Musicality Evaluation | MusicEval (test) | 26 | Jun 16, 2026 | ||
| Classification | WDBC | 26 | May 13, 2026 |