Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1820 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | MFNet | 18 | Jun 11, 2026 | ||
| Recommendation | LastFM | 18 | Jun 30, 2026 | ||
| Audio Understanding Robustness | MMAU Speech SNR=-10dB | 18 | May 26, 2026 | ||
| Audio Understanding Robustness | MMAU Music SNR=-10dB | 18 | May 26, 2026 | ||
| Automated Theorem Proving | MUSTARDSAUCE | 18 | May 26, 2026 | ||
| Automated Theorem Proving | miniF2F | 18 | May 26, 2026 | ||
| 3D Reconstruction | ScanNet++ | 18 | May 25, 2026 | ||
| Image Classification | CIFAR-100 LTN (IF=10, Asymmetric Noise 0.2) (test) | 18 | May 25, 2026 | ||
| Image Classification | CIFAR-100 Long-Tailed Noisy IF=10 Symmetric Noise 0.6 (test) | 18 | May 25, 2026 | ||
| Multi-class classification | CIFAR-100 (test) | 18 | May 25, 2026 | ||
| Multi-class Classification | ImageNet-LT | 18 | May 25, 2026 | ||
| Automatic Speech Recognition | Low-resource Dialectal Speech 5 languages (test) | 18 | May 25, 2026 | ||
| Language Identification | Low-resource Dialectal Speech 5 languages (test) | 18 | May 25, 2026 | ||
| Format Check | ICLEval classification | 18 | May 25, 2026 | ||
| Action Recognition | Something-Something V2 (full) | 18 | May 25, 2026 | ||
| Time Series Forecasting | BizItObs application 10S short GIFT-Eval | 18 | May 25, 2026 | ||
| Time Series Forecasting | BizItObs application 10S medium GIFT-Eval | 18 | May 25, 2026 | ||
| Time Series Forecasting | BizItObs application 10S long (GIFT-Eval) | 18 | May 25, 2026 | ||
| Audio Watermark Detection | AudioLDM2-Music generative edits (test) | 18 | May 25, 2026 | ||
| Generated Image Detection | EvalGEN | 18 | Jun 16, 2026 | ||
| Math Reasoning | AIME 25 | 18 | Jun 30, 2026 | ||
| Text-to-Image Generation | AtelierEval SDXL Backend | 18 | May 22, 2026 | ||
| Text-to-Image Generation | AtelierEval Flux Pro Backend | 18 | May 22, 2026 | ||
| Text-to-Image Generation | AtelierEval GI-1 Backend | 18 | May 22, 2026 | ||
| Text-to-Image Generation | AtelierEval nBanana Backend | 18 | May 22, 2026 |