Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 306 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Real-world Question Answering | RealWorldQA | 58 | Mar 24, 2026 | ||
| Machine Reading Comprehension | SQuAD | 58 | Feb 26, 2026 | ||
| Semantic Segmentation | UAVid (test) | 58 | Apr 30, 2026 | ||
| Image Classification | Pets (test) | 58 | May 15, 2026 | ||
| Chat | AlpacaEval 2.0 (test) | 58 | May 19, 2026 | ||
| Instruction Following and Helpfulness Evaluation | AlpacaEval 2.0 | 58 | Feb 26, 2026 | ||
| Text-to-image synthesis | COCO | 57 | Jul 9, 2026 | ||
| Image Denoising | Set12 Parrot (test) | 57 | Jun 5, 2026 | ||
| Image Denoising | Set12 Monarch (test) | 57 | Jun 5, 2026 | ||
| Symbolic Regression | SRBench Feynman (test) | 57 | May 27, 2026 | ||
| Open-Vocabulary Object Detection | OV-LVIS (val) | 57 | Jun 9, 2026 | ||
| Continual Learning | Standard CL benchmark (Yelp, Amazon, DBpedia, Yahoo, AG News) latest (test) | 57 | May 22, 2026 | ||
| Spatial Relationship Reasoning | SPAR-Bench | 57 | Jul 2, 2026 | ||
| Perioperative infection prediction | INSPIRE cohort (test) | 57 | May 19, 2026 | ||
| Unplanned ICU admission prediction | INSPIRE cohort Supplementary (test) | 57 | May 19, 2026 | ||
| Prolonged hospital stay prediction | INSPIRE cohort (test) | 57 | May 19, 2026 | ||
| In-hospital mortality prediction | INSPIRE cohort Supplementary Table 26 (test) | 57 | May 19, 2026 | ||
| Herb-Herb Interaction (HHI) Prediction | ITCM (TCMM) | 57 | May 19, 2026 | ||
| Commonsense QA | Commonsense QA (ARC-E, ARC-C, HellaS, WinoG, BoolQ, OBQA, RTE, CoPa, Race) zero-shot | 57 | May 18, 2026 | ||
| Efficiency Benchmarking | Qwen3-8B Single-layer forward+backward setup | 57 | May 18, 2026 | ||
| Code Generation | MBPP 3-shot | 57 | Jun 9, 2026 | ||
| Multi-label bioacoustic classification | BirdSet HSN | 57 | Jun 1, 2026 | ||
| Multi-label bioacoustic classification | BirdSet PER | 57 | Jun 1, 2026 | ||
| Multi-label bioacoustic classification | BirdSet POW | 57 | Jun 1, 2026 | ||
| Long-context Management | LoCoMo | 57 | May 12, 2026 |