Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1601 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Correctness Detection | Non-MAQA | 20 | Mar 12, 2026 | ||
| Correctness Detection | MMLU Pro | 20 | Mar 12, 2026 | ||
| Continual Learning | CUB-200 (10-task split) | 20 | Jul 7, 2026 | ||
| Mug Cleanup | Robomimic MimicGen Mug Cleanup (D1) | 20 | Mar 25, 2026 | ||
| Coffee Preparation | Robomimic/MimicGen Coffee Prep. (D1) | 20 | Mar 25, 2026 | ||
| 3D Reconstruction | Real experimental neutron CT scanner dataset | 20 | Mar 12, 2026 | ||
| Long-context retrieval | Lost-in-the-Middle 30-passage contexts | 20 | Mar 12, 2026 | ||
| Single Agent Motion Forecasting | Argoverse 2 (test) | 20 | May 26, 2026 | ||
| Multi-talker Automatic Speech Recognition | Libri3Mix Clean (Eval) | 20 | Mar 31, 2026 | ||
| Mathematical reasoning | AIME 24 | 20 | Jun 9, 2026 | ||
| COVID-19 pneumonia detection | COVIDx (test) | 20 | Mar 12, 2026 | ||
| Time-series Distributional Prediction | Systems (test) | 20 | Mar 12, 2026 | ||
| Time-series Forecasting | Systems (test) | 20 | Mar 12, 2026 | ||
| Gaussian Blur | ImageNet | 20 | May 19, 2026 | ||
| Classification | MarathiSign | 20 | Mar 12, 2026 | ||
| Recommendation | CDs sparse | 20 | Mar 11, 2026 | ||
| Novel View Synthesis | CO3D Teddybear | 20 | Mar 11, 2026 | ||
| Document reading | LogicsDocBench | 20 | Mar 11, 2026 | ||
| Online Continual Learning | Split-ImageNet-S | 20 | Mar 11, 2026 | ||
| Online Continual Learning | Split-ImageNet-R | 20 | Mar 11, 2026 | ||
| Question Answering | LoCoMo Multi-Hop | 20 | Jul 3, 2026 | ||
| Node classification | ogbn-Home (test) | 20 | Mar 11, 2026 | ||
| Node classification | ogbn-Tech (test) | 20 | Mar 11, 2026 | ||
| Regression | Debutanizer | 20 | Mar 11, 2026 | ||
| Regression | Baloon | 20 | Mar 11, 2026 |