Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1114 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Temporal Knowledge Graph Entity Extrapolation | ICEWS14s (test) | 25 | May 7, 2026 | ||
| Video Understanding | Video-MME w/o sub | 25 | Jun 8, 2026 | ||
| Dynamic light field reconstruction | ImViD 300 frames per scene (test) | 25 | Apr 13, 2026 | ||
| Knowledge-Intensive Reasoning | Knowledge-Intensive Reasoning Suite 2Wiki., Bamb., HQA, MuSi., SimQA | 25 | Apr 13, 2026 | ||
| Pansharpening | WorldView-2 (WV2) Real Data Full Resolution (test) | 25 | Apr 15, 2026 | ||
| Spatial Reasoning | SAT Real | 25 | Jun 4, 2026 | ||
| Deepfake Detection | WildDeepfake | 25 | Apr 21, 2026 | ||
| Task-oriented dialogue | FnCTOD | 25 | Apr 10, 2026 | ||
| Classification | australian | 25 | Apr 10, 2026 | ||
| Retrieval | ChunQiuTR official (test) | 25 | Apr 10, 2026 | ||
| Real-world Multimodal Understanding | MME-RealWorld Lite | 25 | Apr 10, 2026 | ||
| Reasoning | MathQA | 25 | Apr 10, 2026 | ||
| Reasoning | GSM8K | 25 | Apr 10, 2026 | ||
| Reasoning | ECQA | 25 | Apr 10, 2026 | ||
| Reasoning | AQuA | 25 | Apr 10, 2026 | ||
| Image Generation | Image Generation | 25 | Apr 9, 2026 | ||
| Bias Evaluation | Task 2 Persona F | 25 | Apr 9, 2026 | ||
| Bias Evaluation | Task 2 Persona E | 25 | Apr 9, 2026 | ||
| Bias Evaluation | Task 2 Persona D | 25 | Apr 9, 2026 | ||
| Bias Evaluation | Task 2 Persona C | 25 | Apr 9, 2026 | ||
| Bias Evaluation | Task 2 Persona B | 25 | Apr 9, 2026 | ||
| Bias Evaluation | Task 2 Persona A | 25 | Apr 9, 2026 | ||
| Driver Action Recognition | Drive&Act (3-split average) | 25 | Apr 8, 2026 | ||
| Math Reasoning | AIME25 | 25 | May 20, 2026 | ||
| Long-context language generation | RepoBench-P | 25 | Apr 8, 2026 |