Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2666 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Pose-based Event Segmentation | F3Set Tennis 50-clip few-shot sub | 14 | Apr 28, 2026 | ||
| Long Context | Long Context benchmark | 14 | Apr 28, 2026 | ||
| Language Understanding | LLM-adapters Understanding | 14 | Apr 28, 2026 | ||
| Commonsense Reasoning | LLM-adapters Reasoning (BoolQ, PIQA, SIQA, HellaSwag, ARC-c) | 14 | Apr 28, 2026 | ||
| Question Answering | ARC C | 14 | Apr 28, 2026 | ||
| Question Answering | BioASQ | 14 | Apr 28, 2026 | ||
| Question Answering | TriviaQA | 14 | Apr 28, 2026 | ||
| Question Answering | NQ | 14 | Apr 28, 2026 | ||
| Preference Alignment | AlignX UGC | 14 | Apr 28, 2026 | ||
| Preference Alignment | AlignX PAIR | 14 | Apr 28, 2026 | ||
| Preference Alignment | AlignX (DEMO) | 14 | Apr 28, 2026 | ||
| Preference Alignment | AlignX (Arbitrary) | 14 | Apr 28, 2026 | ||
| Automatic Speech Recognition | SlideASR 1.0 (R) | 14 | Apr 28, 2026 | ||
| Automatic Speech Recognition | SlideASR S (zh) 1.0 | 14 | Apr 28, 2026 | ||
| Automatic Speech Recognition | SlideASR S (en) 1.0 | 14 | Apr 28, 2026 | ||
| Commonsense Reasoning | Commonsense Reasoning Benchmark Intra-domain Multi-task | 14 | Apr 28, 2026 | ||
| Multi-task Natural Language Processing | cross-domain multi-task NLP datasets | 14 | Apr 28, 2026 | ||
| Traffic Signal Control | Manhattan 28×7 | 14 | Apr 28, 2026 | ||
| Traffic Signal Control | Manhattan 16×3 | 14 | Apr 28, 2026 | ||
| Traffic Signal Control | Hangzhou 4×4 | 14 | Apr 28, 2026 | ||
| Image Classification | GTSRB | 14 | Apr 27, 2026 | ||
| Multi-speaker Automatic Speech Recognition | AMI SDM (test) | 14 | Jun 11, 2026 | ||
| 3D Object Localization | LERF | 14 | May 14, 2026 | ||
| Watermark Detection | HumanEval | 14 | Apr 27, 2026 | ||
| Mathematical Reasoning | GSM8K | 14 | Apr 27, 2026 |