Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 941 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | HellaSwag, WinoGrande, LAMBADA, PIQA, OpenBookQA, ARC-E, ARC-C | 28 | Apr 21, 2026 | ||
| Image Despeckling | texture | 28 | Apr 28, 2026 | ||
| Color image despeckling | Baboon | 28 | Apr 28, 2026 | ||
| High-Resolution Visual Reasoning | HR-Bench 8K | 28 | May 11, 2026 | ||
| Machine Learning Engineering | MLE-Bench Lite | 28 | Jun 11, 2026 | ||
| Claim Verification | SciTab-OD | 28 | Apr 21, 2026 | ||
| Classification | AID | 28 | Jun 23, 2026 | ||
| Language Modeling | CNN Daily Mail (test) | 28 | Apr 21, 2026 | ||
| Language Modeling | FineWeb 100B (val) | 28 | May 25, 2026 | ||
| Language Modeling | FineWebEdu10B | 28 | Apr 21, 2026 | ||
| Language Modeling | FineWeb 10B | 28 | Apr 21, 2026 | ||
| Image Classification | ImageNet-1K | 28 | Apr 21, 2026 | ||
| Pattern Spotting | DocExplore | 28 | Apr 21, 2026 | ||
| Data Attribution | Brain Rot Study Evaluation Suite | 28 | Apr 20, 2026 | ||
| Logical Reasoning | LogicBench | 28 | Apr 20, 2026 | ||
| Mathematical Reasoning | Average GSM8k, GSM-sym, MATH, NuminaMath, AIME | 28 | Apr 20, 2026 | ||
| Strategic Reasoning | gamma-Bench | 28 | Apr 16, 2026 | ||
| Uncertainty Calibration | QUBIQ 2021 | 28 | Apr 15, 2026 | ||
| 3D Semantic Segmentation | ScanNet200 | 28 | Jul 7, 2026 | ||
| Mathematical Reasoning | GSM8K | 28 | Apr 15, 2026 | ||
| Sentiment Analysis | SST-2 | 28 | Apr 15, 2026 | ||
| Medical Question Answering | PubMedQA | 28 | Apr 15, 2026 | ||
| Single-Hop Reasoning | LoCoMo | 28 | Apr 15, 2026 | ||
| Multi-party Dialogue Question Answering | LongDialQA | 28 | Apr 15, 2026 | ||
| OCR Benchmarking | OCRBench v2 | 28 | Jul 7, 2026 |