Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1188 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | Olympiad | 24 | May 13, 2026 | ||
| Mathematical Reasoning | MINERVA | 24 | May 13, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 24 | May 13, 2026 | ||
| Generative Recommendation | Instrument | 24 | May 13, 2026 | ||
| Vulnerable Agent Identification | Vicsek environment | 24 | May 13, 2026 | ||
| Vulnerable Agent Identification | Taxi environment | 24 | May 13, 2026 | ||
| Narrative Fair Play Evaluation | Fair Play in Narrative Generated Stories | 24 | May 13, 2026 | ||
| Offline Black-Box Optimization | Overall Task Suite SuperC, Ant, D’Kitty, LLM-DM, TF8, TF10 | 24 | May 13, 2026 | ||
| Gender Classification | COCO 95% spurious correlation | 24 | May 13, 2026 | ||
| Mathematical Reasoning | Olympiad | 24 | May 13, 2026 | ||
| Mathematical Reasoning | Minerva | 24 | May 13, 2026 | ||
| Mathematical Reasoning | AMC23 | 24 | May 13, 2026 | ||
| Future frame extrapolation | Dynamic Indoor Scene Dataset | 24 | May 12, 2026 | ||
| Classification | DPI-FDA (ratio 1:10) | 24 | May 12, 2026 | ||
| Unconditional Text Generation | LM1B | 24 | May 12, 2026 | ||
| Classification | MNIST-SVHN Backward 50 | 24 | May 12, 2026 | ||
| Classification | MNIST-SVHN Backward 10 | 24 | May 12, 2026 | ||
| Classification | MNIST-SVHN Uniform | 24 | May 12, 2026 | ||
| Classification | MNIST-SVHN Forward 10 | 24 | May 12, 2026 | ||
| Mathematical Reasoning | GSM8K | 24 | May 12, 2026 | ||
| Question Answering | RULER QA | 24 | May 12, 2026 | ||
| Question Answering with Abstention | TriviaQA | 24 | May 12, 2026 | ||
| Question Answering with Abstention | SimpleQA | 24 | May 12, 2026 | ||
| Multiple Choice Classification | When2Call | 24 | May 12, 2026 | ||
| Ordinal Regression | STSB | 24 | May 12, 2026 |