Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1605 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Credit Scoring | Credit scoring (Protected attribute: Age) | 20 | Mar 6, 2026 | ||
| Binary Classification | Credit card Protected attribute: Age (test) | 20 | Mar 6, 2026 | ||
| Semantic and linguistic knowledge evaluation | ZeroSpeech | 20 | Mar 6, 2026 | ||
| GUI Interaction Control | AndroidControl (High) | 20 | Apr 27, 2026 | ||
| Temporal Action Detection | MultiThumos | 20 | Mar 6, 2026 | ||
| Low-light Image Enhancement | SDE out | 20 | Jun 30, 2026 | ||
| Multi-turn response refinement | MT-Refine | 20 | Mar 6, 2026 | ||
| Multi-turn response addition | MT-Add | 20 | Mar 6, 2026 | ||
| EEG Classification | BCIC 3 2020 | 20 | Mar 18, 2026 | ||
| Nuclei Segmentation | SegPC | 20 | Mar 6, 2026 | ||
| Nuclei Segmentation | DSB | 20 | Mar 6, 2026 | ||
| Zero-shot evaluation | Reasoning Benchmarks Zero-shot (BoolQ, PIQA, HellaSwag, WinoGrande, ARC) | 20 | Mar 6, 2026 | ||
| 500hPa Geopotential Forecasting | ERA5 | 20 | Mar 6, 2026 | ||
| 10m Wind Speed Forecasting | ERA5 | 20 | Mar 6, 2026 | ||
| 850hPa Temperature Forecasting | ERA5 | 20 | Mar 6, 2026 | ||
| 2m Temperature Forecasting | ERA5 | 20 | Mar 6, 2026 | ||
| Long Video Generation | 120, 240, 720 and 1440-frames long videos | 20 | Mar 5, 2026 | ||
| Monocular Depth Estimation | DSEC-Depth | 20 | Mar 5, 2026 | ||
| Monocular Depth Estimation | MVSEC Depth | 20 | Mar 5, 2026 | ||
| Mathematical Reasoning | GPQA D | 20 | Mar 5, 2026 | ||
| Citation and Evidence Recall | NeoQA | 20 | Mar 5, 2026 | ||
| Citation and Evidence Recall | MuSiQue | 20 | Mar 5, 2026 | ||
| Citation and Evidence Recall | BoolQ M | 20 | Mar 5, 2026 | ||
| Citation and Evidence Recall | RepliQA | 20 | Mar 5, 2026 | ||
| Question Answering | ASQA, HotpotQA, NQ, TriviaQA, POPQA, BIOASQ | 20 | Mar 5, 2026 |