Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 933 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Future State Prediction | Spring-GS (test) | 28 | May 22, 2026 | ||
| Coding | HumanEval | 28 | May 22, 2026 | ||
| Causal Faithfulness Evaluation | HaluEval Adversarial | 28 | May 22, 2026 | ||
| Causal Faithfulness Evaluation | Edgar Domain | 28 | May 22, 2026 | ||
| Causal Faithfulness Evaluation | FineWeb Temporal | 28 | May 22, 2026 | ||
| Door Open | Meta-World | 28 | Jun 11, 2026 | ||
| Diagnostic group separation analysis of hippocampal subfield volumes | ADNI3 cohort | 28 | May 22, 2026 | ||
| Area Localization | instances 1024 x 1024 | 28 | May 22, 2026 | ||
| Data Ranking | Insecure code | 28 | May 21, 2026 | ||
| Data Ranking | Mistake medical | 28 | May 21, 2026 | ||
| Semantic Segmentation | Med JASCL-Disjoint Session 2: BCV | 28 | May 21, 2026 | ||
| Semantic Segmentation | Med JASCL-Disjoint Session 1: AMOS | 28 | May 21, 2026 | ||
| Semantic Segmentation | Med JASCL-Disjoint Session 0: TS | 28 | May 21, 2026 | ||
| Continual Segmentation | Med JASCL Disjoint | 28 | May 21, 2026 | ||
| Timing Efficiency | Median per-dataset (test) | 28 | May 21, 2026 | ||
| Vision-Language Understanding | MVista | 28 | Jun 17, 2026 | ||
| Video Understanding | VideoMME | 28 | Jul 1, 2026 | ||
| Open-vocabulary Part Segmentation | PARS Ad-hoc Concepts | 28 | May 20, 2026 | ||
| Global Weather Forecasting | ERA5 V10 | 28 | May 20, 2026 | ||
| Global Weather Forecasting | ERA5 U10 | 28 | May 20, 2026 | ||
| Global Weather Forecasting | ERA5 T2m | 28 | May 20, 2026 | ||
| Global Weather Forecasting | ERA5 T850 | 28 | May 20, 2026 | ||
| Global Weather Forecasting | ERA5 Z500 | 28 | May 20, 2026 | ||
| Image Retrieval | ImageNet 1K (full) | 28 | May 20, 2026 | ||
| Audio Classification Attribution | VGG-Sound (val) | 28 | May 20, 2026 |