Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 588 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Reconstruction | Lena | 38 | Jun 5, 2026 | ||
| LLM Decoding | Long Context 96K | 38 | Jun 4, 2026 | ||
| Node Classification | PubMed | 38 | Jun 11, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 38 | Jun 30, 2026 | ||
| Image Classification | ImageNet-1K | 38 | Jun 2, 2026 | ||
| Image Generation | CIFAR-10 (test) | 38 | Jun 4, 2026 | ||
| Regression | ZIP Code weighted avg. 29 tasks | 38 | Jun 2, 2026 | ||
| Mathematical Reasoning | MATH-500 1 (test) | 38 | May 28, 2026 | ||
| Camouflaged Object Detection | COD10K 2026 | 38 | Jul 7, 2026 | ||
| Reasoning | Reasoning Benchmarks ARC-e, ARC-c, BoolQ, PIQA, SIQA, HellaS., OBQA, Wino. | 38 | May 26, 2026 | ||
| Graph Anomaly Detection | ACM | 38 | May 27, 2026 | ||
| Graph Anomaly Detection | CS | 38 | May 27, 2026 | ||
| Research Paper Reasoning and Comprehension | ArxivRollBench 2025a (val) | 38 | May 26, 2026 | ||
| Question Answering | Molmo2-Moment (M2M) v1 (test) | 38 | May 25, 2026 | ||
| State modeling (Task 1.2) | CLPsych Task 1 2026 | 38 | May 26, 2026 | ||
| State modeling (Task 1.1) | CLPsych Task 1 2026 | 38 | May 26, 2026 | ||
| Long-context language understanding | LongBench | 38 | May 22, 2026 | ||
| Transductive Link Prediction | 38 | Jul 7, 2026 | |||
| Language Understanding | WinoGrande | 38 | May 21, 2026 | ||
| Information Retrieval | Bing-Click (test) | 38 | May 20, 2026 | ||
| Drug-Drug Interaction Prediction | DrugMap Target (Source: ZhangDDI) 2024 | 38 | May 19, 2026 | ||
| Drug-Drug Interaction Prediction | DDInter Target (Source: ZhangDDI) 2.0 | 38 | May 19, 2026 | ||
| Deep Research | HealthBench | 38 | Jun 15, 2026 | ||
| Tabular Prediction | TabArena all 51 datasets | 38 | Jun 2, 2026 | ||
| Mathematical reasoning | OlympiadBench | 38 | Jun 11, 2026 |