Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1063 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text Embedding Evaluation | MTEB eng v2 (test) | 26 | Jun 25, 2026 | ||
| Multiclass classification | cleveland | 26 | Mar 12, 2026 | ||
| Classification | dermatology | 26 | Jun 4, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 26 | Apr 3, 2026 | ||
| Spoken Question Answering | TriviaQA | 26 | Jul 8, 2026 | ||
| Scene Classification | UCMerced | 26 | Jul 8, 2026 | ||
| Autonomous Driving | NAVSIM (navtest) | 26 | Apr 7, 2026 | ||
| Whole-body pose estimation | COCO-WholeBody 1.0 2017 (val) | 26 | Mar 11, 2026 | ||
| Social Reasoning | TactfulToM | 26 | Mar 11, 2026 | ||
| Social Reasoning | Hi-ToM | 26 | Mar 11, 2026 | ||
| Social Reasoning | MotiveBench | 26 | Mar 11, 2026 | ||
| Social Reasoning | EmoBench | 26 | Mar 11, 2026 | ||
| Social Reasoning | ToMBench Hard (val) | 26 | Mar 11, 2026 | ||
| Social Reasoning | ToMBench | 26 | Mar 11, 2026 | ||
| Instruction following | AlpacaEval High-Variance (Top 20%) 2.0 | 26 | Mar 10, 2026 | ||
| Multi-turn instruction following | MT-Bench High-Variance (Top 20%) | 26 | Mar 10, 2026 | ||
| Instruction following | AlpacaEval 2.0 (Overall) | 26 | Mar 10, 2026 | ||
| Zero-shot Evaluation | ARC-Challenge, ARC-Easy, BoolQ, CrowS-Pairs, OpenBookQA, PIQA, RACE, SiQA, TruthfulQA, WinoGrande zero-shot | 26 | Mar 10, 2026 | ||
| Node Classification | Cora | 26 | Mar 10, 2026 | ||
| Math & Reasoning | MathVista mini | 26 | May 12, 2026 | ||
| Machine Unlearning | ImageNet Class Forgetting 3-class average | 26 | Mar 10, 2026 | ||
| Visual Question Answering | RealWorldQA (RWQA) | 26 | Jun 5, 2026 | ||
| Question Answering | PopQA | 26 | Mar 10, 2026 | ||
| Job Shop Scheduling Problem | Taillard 30 x 15 | 26 | May 19, 2026 | ||
| Polarized Community Discovery | WikiP | 26 | Mar 10, 2026 |