Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 276 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Task Negation | 8 Vision | 61 | May 20, 2026 | ||
| Time Series Anomaly Detection | SMAP | 61 | Jun 23, 2026 | ||
| Common Sense Reasoning | 7 common sense reasoning datasets | 61 | Feb 26, 2026 | ||
| Question Answering | TruthfulQA | 61 | Mar 26, 2026 | ||
| Vision-and-Language Navigation | R2R-CE v1.0 (val unseen) | 61 | Jun 8, 2026 | ||
| Visual Jailbreaking Attack | MaliciousInstruct | 61 | Mar 4, 2026 | ||
| Membership Inference Attack | Pile CC | 61 | Apr 1, 2026 | ||
| Medical Reasoning | MedQA | 61 | Jun 30, 2026 | ||
| Information Retrieval | TREC DL'19 | 61 | May 4, 2026 | ||
| Semantic Segmentation | City | 61 | May 20, 2026 | ||
| OCR-based Visual Question Answering | OCR-VQA | 61 | Mar 5, 2026 | ||
| Multi-modal Reasoning | EMMA | 61 | Jun 16, 2026 | ||
| End-to-end planning | NAVSIM v1 | 61 | May 28, 2026 | ||
| Visual Question Answering | VQA text | 61 | Apr 13, 2026 | ||
| LLM Inference Acceleration | GSM8K | 61 | May 27, 2026 | ||
| Code Reasoning | CRUXEval-O | 61 | Jun 1, 2026 | ||
| Visual Question Answering | InfoSeek (Full) | 61 | May 6, 2026 | ||
| Multi-hop tool use | ToolHop | 61 | Jun 16, 2026 | ||
| Image Classification | MNIST (test) | 61 | Feb 26, 2026 | ||
| Hallucination Evaluation | MME Hallucination | 61 | Jun 1, 2026 | ||
| Zero-shot Evaluation | ArcC, ArcE, HS, PiQA, WG (test val) | 61 | Feb 26, 2026 | ||
| Language Modeling | Alpaca | 61 | Mar 5, 2026 | ||
| Multimodal Question Answering | MMBench CN | 61 | Jul 3, 2026 | ||
| Mathematical Reasoning | AIME24 (test) | 61 | May 22, 2026 | ||
| Video Question Answering | VideoMME (test) | 61 | May 14, 2026 |