Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2402 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Spatial Reasoning | SpaCE10 | 15 | May 13, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 15 | May 13, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 15 | May 13, 2026 | ||
| Classification | TabReD | 15 | May 13, 2026 | ||
| Classification | HTRU2 | 15 | Jul 7, 2026 | ||
| Reasoning | DeepSearchQA 2026 (test) | 15 | May 13, 2026 | ||
| Reasoning | PhantomWiki 2025 (test) | 15 | May 13, 2026 | ||
| Reasoning | SynthWorlds 2026 (test) | 15 | May 13, 2026 | ||
| Reasoning | DeepSearchQA | 15 | May 13, 2026 | ||
| Reasoning | PhantomWiki | 15 | May 13, 2026 | ||
| Reasoning | SynthWorlds | 15 | May 13, 2026 | ||
| OOD Detection | CIFAR-10 Sym0.8 (test) | 15 | May 21, 2026 | ||
| OOD Detection | CIFAR-10 Sym0.5 (test) | 15 | May 21, 2026 | ||
| OOD Detection | CIFAR-10 Sym0.2 (test) | 15 | May 21, 2026 | ||
| Document Retrieval | FiQA BEIR 2018 | 15 | May 13, 2026 | ||
| Document Retrieval | NFCorpus BEIR | 15 | May 13, 2026 | ||
| Text-to-Image Generation | General Prompts | 15 | May 13, 2026 | ||
| Natural Language Understanding | GLUE (test) | 15 | May 13, 2026 | ||
| Temporal language grounding | TVSum | 15 | May 13, 2026 | ||
| Temporal Language Grounding | YouTube Highlights | 15 | May 13, 2026 | ||
| Code Generation | CodeContests+ | 15 | May 13, 2026 | ||
| Mathematical Reasoning | DAPO-17k | 15 | May 13, 2026 | ||
| Alignment and Safety Evaluation | Safety | 15 | May 13, 2026 | ||
| General Reasoning | SuperGPQA | 15 | May 13, 2026 | ||
| General Knowledge Reasoning | MMLU-Pro | 15 | May 13, 2026 |