Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2307 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Node Classification | Pubmed ADD-0.5 (test) | 16 | Feb 26, 2026 | ||
| Node classification | Pubmed Dele-0.5 (test) | 16 | Feb 26, 2026 | ||
| Node classification | Pubmed Dele-0.2 (test) | 16 | Feb 26, 2026 | ||
| Dense Captioning | VG V1.0 | 16 | Feb 26, 2026 | ||
| Text-to-Video Retrieval | ActivityNet (ANet) zero-shot | 16 | Feb 26, 2026 | ||
| Semantic Segmentation | A-150 (test) | 16 | Feb 26, 2026 | ||
| Question Answering | bAbI | 16 | Mar 17, 2026 | ||
| REC | RefCOCOg | 16 | Feb 26, 2026 | ||
| REC | RefCOCO+ | 16 | Feb 26, 2026 | ||
| Multi-label image recognition | MS COCO | 16 | Feb 26, 2026 | ||
| Video Compression | HEVC Class D (All frames) | 16 | Jun 4, 2026 | ||
| Video Compression | HEVC Class B (All frames) | 16 | Jun 4, 2026 | ||
| Video Compression | UVG (All frames) | 16 | Jun 4, 2026 | ||
| Edge Detection | PASCAL-Context (test) | 16 | Feb 26, 2026 | ||
| Edge Detection | NYUD v2 (test) | 16 | Feb 26, 2026 | ||
| Machine Translation | WMT en→zh (test) | 16 | Feb 26, 2026 | ||
| Machine Translation | WMT de-en | 16 | Feb 26, 2026 | ||
| Image-Text Retrieval | CBVS-20K (test) | 16 | Feb 26, 2026 | ||
| Language Generation | WikiText-2 (test) | 16 | Apr 23, 2026 | ||
| Cloze Test | CHID | 16 | Feb 26, 2026 | ||
| BEV Segmentation | nuScenes (val) | 16 | Jun 19, 2026 | ||
| Language Model Inference | Mobile and IoT Device Latency Benchmark llama.cpp (inference evaluation) | 16 | Feb 26, 2026 | ||
| Reranking | Natural Questions (test) | 16 | Feb 26, 2026 | ||
| Image Quality Assessment | LIVE Challenge 1.1K (test) | 16 | Feb 26, 2026 | ||
| Image Quality Assessment | SPAQ 11K (test) | 16 | Feb 26, 2026 |