Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 472 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Tool Retrieval | APIBank | 44 | Feb 26, 2026 | ||
| Tool Retrieval | APIGen | 44 | Feb 26, 2026 | ||
| Tool Retrieval | ToolBench | 44 | Feb 26, 2026 | ||
| Single-document retrieval | NaturalQuestions | 44 | Feb 26, 2026 | ||
| Single-document retrieval | ConditionalQA | 44 | Feb 26, 2026 | ||
| Single-document retrieval | RepLiQA | 44 | Feb 26, 2026 | ||
| Single-document retrieval | Qasper | 44 | Feb 26, 2026 | ||
| Single-document retrieval | QASA | 44 | Feb 26, 2026 | ||
| Image Denoising | CBSD68 | 44 | Jul 7, 2026 | ||
| Semantic Segmentation | Industrial-5i (test) | 44 | Feb 26, 2026 | ||
| Semantic Segmentation | Pothole-mix (test) | 44 | Feb 26, 2026 | ||
| Semantic Segmentation | Nucleus (test) | 44 | Feb 26, 2026 | ||
| Semantic Segmentation | Lung Nodule (test) | 44 | Feb 26, 2026 | ||
| Spatio-Temporal Reasoning | V-STaR | 44 | Apr 28, 2026 | ||
| Chart Understanding | CharXiv | 44 | Apr 6, 2026 | ||
| Visual Question Answering | VQAv2 (test-std) | 44 | May 7, 2026 | ||
| Action Recognition | NTU RGB+D 60 (cross-view (CV)) | 44 | Feb 26, 2026 | ||
| Unconditional image generation | FFHQ 64x64 (val) | 44 | Feb 26, 2026 | ||
| Vision-Language Tracking | TNLLT latest (test) | 44 | Jun 30, 2026 | ||
| Hallucination Assessment | AMBER (test) | 44 | Jun 11, 2026 | ||
| Mathematical Reasoning | MathVision mini (test) | 44 | May 26, 2026 | ||
| ODT reconstruction | MCD-AN (test) | 44 | Feb 26, 2026 | ||
| ODT reconstruction | MCD-AW (test) | 44 | Feb 26, 2026 | ||
| Hyperspectral Image Classification | Salinas (SA) | 44 | Jun 4, 2026 | ||
| Multi-modal Benchmark | MMBench | 44 | Apr 28, 2026 |