Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2623 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Gait Recognition | SUSTech1K 3D LiDAR → 2D Camera | 14 | Jun 2, 2026 | ||
| Long-context language understanding | LongBench | 14 | Jun 2, 2026 | ||
| Graph-to-Text Generation | WebNLG English (test) | 14 | Jun 1, 2026 | ||
| Natural Language Generation | Merlin | 14 | Jun 1, 2026 | ||
| Natural Language Generation | BIMCV | 14 | Jun 1, 2026 | ||
| Medical Image Classification | BIMCV (test) | 14 | Jun 1, 2026 | ||
| Natural language generation | Inspect | 14 | Jun 1, 2026 | ||
| Fine-grained Captioning | Inspect | 14 | Jun 1, 2026 | ||
| Medical Report Generation | Merlin (test) | 14 | Jun 1, 2026 | ||
| Medical Image Captioning | CT-Rate (test) | 14 | Jun 1, 2026 | ||
| Medical Report Generation | BIMCV n=1,505 cases (test) | 14 | Jun 1, 2026 | ||
| Classification | CT-Rate (test) | 14 | Jun 1, 2026 | ||
| RadBERT classification | Inspect n=1,000 cases | 14 | Jun 1, 2026 | ||
| RadBERT classification | Merlin dataset | 14 | Jun 1, 2026 | ||
| Robot Manipulation | Realworld Manipulation (test) | 14 | Jun 23, 2026 | ||
| Confidence Estimation | Global-MMLU (test) | 14 | Jun 1, 2026 | ||
| Confidence Estimation | MKQA (test) | 14 | Jun 1, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Suite (MATH500, Olympiad, AMC, AIME24, AIME25, GSM8K) pass@1 (test) | 14 | Jun 1, 2026 | ||
| Cross-model clustering | StackEx | 14 | Jun 1, 2026 | ||
| Cross-model clustering | 14 | Jun 1, 2026 | |||
| segmentation | m-cashew GeoBench | 14 | Jun 1, 2026 | ||
| multi-label classification | m-bigearthnet GeoBench | 14 | Jun 1, 2026 | ||
| Image-Text Retrieval | COCO 5K | 14 | Jun 1, 2026 | ||
| Downstream Policy Performance | Arena-Hard v2.0 | 14 | Jun 1, 2026 | ||
| Autonomous Software Engineering | SWE-Bench-Verified (test) | 14 | Jun 1, 2026 |