Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1616 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Regression | 2D QGP prior Set 2 (test) | 20 | Feb 26, 2026 | ||
| Regression | 2D QGP prior Set 1 (test) | 20 | Feb 26, 2026 | ||
| Regression | SRTM N47W124 (test) | 20 | Feb 26, 2026 | ||
| Regression | SRTM N45W123 (test) | 20 | Feb 26, 2026 | ||
| Regression | SRTM N43W080 (test) | 20 | Feb 26, 2026 | ||
| Regression | SRTM N17E073 (test) | 20 | Feb 26, 2026 | ||
| Classification | C3, CMNLI, CHID, BoolQ, WSC, HeSW, PIQA, CoQA, Race-M, Race-H, MMLU, CMMLU | 20 | Feb 27, 2026 | ||
| Reverse Chain-of-Thought Generation | MultiChallenge | 20 | Feb 26, 2026 | ||
| Reverse Chain-of-Thought Generation | IFEval | 20 | Feb 26, 2026 | ||
| Reverse Chain-of-Thought Generation | EQ-Bench 3 | 20 | Feb 26, 2026 | ||
| Reverse Chain-of-Thought Generation | ArenaHard | 20 | Feb 26, 2026 | ||
| Multi-Task Reinforcement Learning (LTL Instruction Following) | Warehouse Infinite Horizon | 20 | Feb 26, 2026 | ||
| OCR and Chart Understanding | OCRBench | 20 | Mar 19, 2026 | ||
| Pixel-level Forgery Localization | CocoGlide | 20 | Jun 4, 2026 | ||
| Recommendation | MovieLens latest (test) | 20 | Feb 26, 2026 | ||
| Grounding | E.T. Bench | 20 | Feb 26, 2026 | ||
| Logical Reasoning | Logical Deduction | 20 | Jun 2, 2026 | ||
| Long-term Time Series Forecasting | Solar | 20 | Feb 26, 2026 | ||
| Long-term Time Series Forecasting | Traffic | 20 | Feb 26, 2026 | ||
| Long-term Time Series Forecasting | Electricity | 20 | Feb 26, 2026 | ||
| Long-term Time Series Forecasting | ETTm1 | 20 | Feb 26, 2026 | ||
| Long-term Time Series Forecasting | ETTh2 | 20 | Feb 26, 2026 | ||
| Combinatorial optimization | CVRP (test) | 20 | Feb 26, 2026 | ||
| Surgical Smoke Removal | LSD3K (test) | 20 | Feb 26, 2026 | ||
| Semantic Segmentation | KITTI 2015 | 20 | Feb 26, 2026 |