Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2710 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Vision-Language Navigation | VLN-CE (test) | 14 | Mar 19, 2026 | ||
| Visual Question Answering | RealWorld | 14 | Jun 15, 2026 | ||
| Automatic Speech Recognition | ATCOSIM | 14 | Jun 18, 2026 | ||
| Mathematical Reasoning | MATH500 | 14 | Mar 19, 2026 | ||
| Coding | Codeforces (CF) | 14 | Mar 19, 2026 | ||
| Coding | LiveCodeBench | 14 | Mar 19, 2026 | ||
| General Reasoning | LB V2 | 14 | Mar 19, 2026 | ||
| General Reasoning | LB V1 | 14 | Mar 19, 2026 | ||
| Robot Manipulation | Simulation held-out environments | 14 | May 5, 2026 | ||
| Gaussian Deblurring | ImageNet Gaussian Blur sigma=12 | 14 | Mar 18, 2026 | ||
| Gaussian Deblurring | ImageNet Gaussian Blur sigma=3 | 14 | Mar 18, 2026 | ||
| Super Resolution | ImageNet 16x scale | 14 | Mar 18, 2026 | ||
| Super Resolution | ImageNet 4x scale | 14 | Mar 18, 2026 | ||
| Gaussian Deblur 12 | Cats | 14 | Mar 18, 2026 | ||
| Gaussian Deblur 3 | Cats | 14 | Mar 18, 2026 | ||
| Super Resolution 16x | Cats | 14 | Mar 18, 2026 | ||
| Super Resolution 4x | Cats | 14 | Mar 18, 2026 | ||
| Inpainting | Cats | 14 | Mar 18, 2026 | ||
| Class-conditional generation | ImageNet | 14 | Mar 18, 2026 | ||
| Multi-disease IOS diagnosis | IOSVQA (test) | 14 | Mar 18, 2026 | ||
| Step Execution | GUI-Odyssey | 14 | Mar 18, 2026 | ||
| Compositional Zero-Shot Learning | MIT-States Open-world (test) | 14 | Mar 18, 2026 | ||
| Classification | Magic (test) | 14 | Jul 1, 2026 | ||
| Multimodal Reward Modeling | MM-RLHF-Reward Bench | 14 | Mar 18, 2026 | ||
| Open-Vocabulary Fine-Grained Emotion Recognition | OV-MERD | 14 | Mar 18, 2026 |