Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1236 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AIME24 | 24 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH500 | 24 | Feb 26, 2026 | ||
| Preference Calibration | PPE | 24 | Feb 26, 2026 | ||
| Correctness Calibration | PPE (Preference Policy Evaluation) | 24 | Feb 26, 2026 | ||
| Uncertainty Calibration | RewardBench | 24 | Feb 26, 2026 | ||
| Uncertainty Calibration | JudgeBench | 24 | Feb 26, 2026 | ||
| Correctness Evaluation | PPE Correctness (test) | 24 | Mar 4, 2026 | ||
| Time-series forecasting | S&P 100 | 24 | Feb 26, 2026 | ||
| Time-series forecasting | Tech Stock 10 | 24 | Feb 26, 2026 | ||
| Time-series forecasting | ILL | 24 | Feb 26, 2026 | ||
| SQL Semantic Validation | EHRSQL | 24 | Feb 26, 2026 | ||
| SQL Semantic Validation | Spider | 24 | Feb 26, 2026 | ||
| SQL Semantic Validation | BIRD | 24 | Feb 26, 2026 | ||
| Multimodal Classification | Symile | 24 | Feb 26, 2026 | ||
| Multimodal Classification | HAIM | 24 | Feb 26, 2026 | ||
| Rubric satisfaction evaluation | ML | 24 | Feb 26, 2026 | ||
| Image Classification | Tiny-ImageNet heterogeneous (test) | 24 | Feb 26, 2026 | ||
| Image Classification | Tiny-ImageNet homogeneous (test) | 24 | Feb 26, 2026 | ||
| Biosignature flux prediction | Synthetic exoplanet spectrum dataset (test) | 24 | Feb 26, 2026 | ||
| Memory | RULER HotpotQA | 24 | Jun 2, 2026 | ||
| General Reasoning Evaluation | Reasoning Benchmarks Aggregate | 24 | Feb 26, 2026 | ||
| Multi-modal Recognition | SUN RGB-D | 24 | Feb 26, 2026 | ||
| Property Prediction | Composite | 24 | Feb 26, 2026 | ||
| Property Prediction | Nanofiber | 24 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTm2 v1 (test) | 24 | Feb 26, 2026 |