Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 330 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Infrared Small Target Detection | SIRST Aug | 55 | Jul 7, 2026 | ||
| Hallucination Detection | VQA-Med 2019 (All) | 55 | May 21, 2026 | ||
| Building Change Detection | WHU-CD (test) | 55 | Jun 19, 2026 | ||
| Object Hallucination Probing | GQA Adversarial | 55 | Jun 30, 2026 | ||
| Targeted Attack | InjecAgent | 55 | Apr 28, 2026 | ||
| Text classification | AGNews, Amazon, DBPedia, Yahoo, and Yelp (test) | 55 | Feb 26, 2026 | ||
| Scientific Reasoning | GPQA | 55 | Feb 26, 2026 | ||
| Instruction Following | ReasonIF synthesized v1.0 | 55 | Feb 26, 2026 | ||
| Logical Reasoning | CounterBench (test) | 55 | Feb 26, 2026 | ||
| Calibration | NQ | 55 | Jun 4, 2026 | ||
| Image Generation | ImageNet-1K | 55 | Jun 9, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Suite (AMC, AIME 2024, AIME 2025, Minerva, MATH, Olympiad) various (test val) | 55 | Feb 26, 2026 | ||
| Commonsense Reasoning | WinoG | 55 | May 13, 2026 | ||
| Agent Performance | tau-bench | 55 | Feb 26, 2026 | ||
| Multimodal Reasoning | M3CoT (test) | 55 | May 28, 2026 | ||
| General Visual Reasoning | MMStar | 55 | Jul 2, 2026 | ||
| Open-ended VQA | MMOral-OPG | 55 | May 28, 2026 | ||
| Web navigation | WebShop | 55 | Jun 9, 2026 | ||
| Code Generation | HumanEval+ v1 (test) | 55 | May 28, 2026 | ||
| Question Answering | HQA | 55 | Mar 11, 2026 | ||
| Instruction Following | ComplexBench | 55 | Jun 16, 2026 | ||
| UAV Tracking | VisDrone 2018 | 55 | May 28, 2026 | ||
| Language Modeling | The Pile (val) | 55 | Jul 9, 2026 | ||
| Spectral Compressive Imaging Reconstruction | CAVE 10 scenes (test) | 55 | Feb 26, 2026 | ||
| Spectral Reconstruction | Simulated Scenes (test) | 55 | Feb 26, 2026 |