Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 301 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sentiment Classification | SST-2 | 58 | Apr 15, 2026 | ||
| Mathematical Reasoning | AIME 26 | 58 | May 29, 2026 | ||
| Mathematical Reasoning | GSM8K (test) | 58 | May 20, 2026 | ||
| Adversarial Attack | Yelp | 58 | May 26, 2026 | ||
| Image-to-Code Generation | STEM2Code-Eval (1k samples) | 58 | Mar 12, 2026 | ||
| Long-term forecasting | Weather | 58 | Jul 9, 2026 | ||
| General QA | PopQA | 58 | May 11, 2026 | ||
| Out-of-Distribution Detection | ImageNet Far-OOD | 58 | Apr 20, 2026 | ||
| Video Temporal Grounding | ActivityNet Grounding | 58 | Mar 9, 2026 | ||
| Micro-expression recognition | CASME II 5-class | 58 | Jun 29, 2026 | ||
| Mathematical Reasoning | DeepMath | 58 | Jun 5, 2026 | ||
| Large Language Model Evaluation | MMLU, GSM8k, HellaSwag, WinoGrande | 58 | Mar 4, 2026 | ||
| Video Frame Interpolation | Vimeo90K septuplet | 58 | Mar 4, 2026 | ||
| Omni-modal agentic tasks | OmniGAIA | 58 | Jun 15, 2026 | ||
| Reasoning | StrategyQA | 58 | Jun 30, 2026 | ||
| Diagram Understanding | AI2D 1.0 (test) | 58 | Feb 27, 2026 | ||
| Reasoning | AIME 24 | 58 | Mar 10, 2026 | ||
| Deep Research | DeepResearch Bench | 58 | Jul 2, 2026 | ||
| Image Classification | EUROSAT | 58 | May 22, 2026 | ||
| Code generation | MBPP | 58 | May 27, 2026 | ||
| Trajectory Planning | NuScenes | 58 | May 27, 2026 | ||
| Mathematical Problem Solving | MinervaMath (test) | 58 | Jun 16, 2026 | ||
| Molecule Generation | QM9 2014 (test) | 58 | Jun 1, 2026 | ||
| Time Series Forecasting | Tourism Quarterly | 58 | Apr 14, 2026 | ||
| Graph Anomaly Detection | T-Finance | 58 | May 28, 2026 |