Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1561 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical reasoning | GSM8K | 20 | May 15, 2026 | ||
| Code generation | HumanEval | 20 | May 15, 2026 | ||
| Multi-turn dialogue | MT-Bench | 20 | May 15, 2026 | ||
| Bioacoustic Analysis | Vocal Repertoire | 20 | May 15, 2026 | ||
| Bioacoustic Identification | Individual ID | 20 | May 15, 2026 | ||
| Bioacoustic Detection | BEANS Detection | 20 | May 15, 2026 | ||
| Bioacoustic Classification | BEANS | 20 | May 15, 2026 | ||
| Semantic Segmentation | PST900 (50%) | 20 | May 15, 2026 | ||
| Semantic Segmentation | SemanticRT (5%) | 20 | May 15, 2026 | ||
| Offline-to-Online Reinforcement Learning | D4RL Antmaze | 20 | May 15, 2026 | ||
| Synthetic Image Detection | WildRF | 20 | Jul 8, 2026 | ||
| Visual Question Answering | LRS-VQA | 20 | May 15, 2026 | ||
| Remote Sensing Image Understanding | XLRS-Bench | 20 | May 15, 2026 | ||
| Remote Sensing Image Understanding | RSHR-Bench | 20 | May 15, 2026 | ||
| Hallucination Detection | BioASQ (test) | 20 | May 15, 2026 | ||
| Vector Quantization | Contriever1M D = 768 (test) | 20 | May 15, 2026 | ||
| Vector Quantization | FB-ssnpp1M D = 256 (test) | 20 | May 15, 2026 | ||
| Commonsense Reasoning and Question Answering | ACC benchmark ARC-e, ARC-c, Winogrande, BoolQ, PIQA, HellaSwag, OpenBookQA, HeadQA | 20 | May 15, 2026 | ||
| Question Answering | CosmosQA (test) | 20 | May 15, 2026 | ||
| Class-Incremental Learning | Food | 20 | May 14, 2026 | ||
| Class-Incremental Learning | SUN | 20 | May 14, 2026 | ||
| Class-Incremental Learning | UCF | 20 | May 14, 2026 | ||
| Class-Incremental Learning | Cars | 20 | May 14, 2026 | ||
| Binding affinity regression | MISATO (structure split) | 20 | May 14, 2026 | ||
| Enzyme Commission depth-1 function prediction | MISATO (structure) | 20 | May 14, 2026 |