Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1871 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Coding | HumanEval | 18 | Mar 20, 2026 | ||
| Coding | LiveCodeBench | 18 | Mar 20, 2026 | ||
| Large Language Model Inference | FinanceQA | 18 | Mar 20, 2026 | ||
| Large Language Model Inference | GPQA | 18 | Mar 20, 2026 | ||
| Video Understanding | HERBench Lite | 18 | Mar 20, 2026 | ||
| Question Answering | ∞-Bench Longbook QA English (test) | 18 | May 27, 2026 | ||
| Sentence Generation | CommonGen | 18 | Mar 20, 2026 | ||
| Multi-turn decision making | ALFWorld (val-unseen) | 18 | Mar 20, 2026 | ||
| Music Reconstruction | MUSDB | 18 | Mar 20, 2026 | ||
| Instance Segmentation | NWPU VHR-10 | 18 | Mar 20, 2026 | ||
| Zero-shot image retrieval | ForestNet-4 | 18 | Mar 20, 2026 | ||
| Zero-shot image retrieval | ForestNet-12 | 18 | Mar 20, 2026 | ||
| Zero-shot image retrieval | BigEarthNet-19 | 18 | Mar 20, 2026 | ||
| Zero-shot image retrieval | BigEarthNet 43 | 18 | Mar 20, 2026 | ||
| Quantization Detection | WildChat | 18 | Mar 20, 2026 | ||
| Jail-breaking detection | WildChat | 18 | Mar 20, 2026 | ||
| Quantization Detection | Math | 18 | Mar 20, 2026 | ||
| Action Recognition | NTU 60 (40-20 seen-unseen) | 18 | Apr 3, 2026 | ||
| Point Tracking | RGB-Stacking queried-first mode | 18 | Mar 19, 2026 | ||
| Medical Image Segmentation | Polyp Endoscopy | 18 | Apr 1, 2026 | ||
| Image Generation | LSUN 256x256 latent-space | 18 | Mar 19, 2026 | ||
| Image Classification | MNIST uniform label noise η=0.1 (7-fold CV) | 18 | Mar 19, 2026 | ||
| Beamforming Sum-Rate Maximization | Rayleigh fading realizations (M=8, K=4, Pmax=1, sigma^2=0.1) (test) | 18 | Mar 19, 2026 | ||
| Emotional video captioning | EVC Combine | 18 | Jun 9, 2026 | ||
| Emotional video captioning | EVC-MSVD | 18 | Jun 9, 2026 |