Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1170 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text Classification | Yahoo! Answers | 24 | Jun 5, 2026 | ||
| Classification | Yahoo | 24 | Jun 5, 2026 | ||
| Denoising | PM-25 sigma=0.5 | 24 | Jun 5, 2026 | ||
| Denoising | SST | 24 | Jun 5, 2026 | ||
| Posterior Sampling | Linear Gaussian n=400 | 24 | Jun 5, 2026 | ||
| Posterior Sampling | Linear Gaussian n=80 | 24 | Jun 5, 2026 | ||
| Posterior Sampling | Linear Gaussian n=2 | 24 | Jun 5, 2026 | ||
| Generative Task | Alpaca random subset of 1,000 samples | 24 | Jun 5, 2026 | ||
| Signal Reconstruction | Real DSC-MRI dataset | 24 | Jun 5, 2026 | ||
| Recommendation Tasks | ML 20% 20M (test) | 24 | Jun 5, 2026 | ||
| Recommendation Tasks | ML 20% 10M (test) | 24 | Jun 5, 2026 | ||
| Multi-phase Image Segmentation | Synthetic Image | 24 | Jun 5, 2026 | ||
| Image Mesh Representation | Lena | 24 | Jun 5, 2026 | ||
| Audio Deepfake Detection | xTTS v2 | 24 | Jun 4, 2026 | ||
| Audio Deepfake Detection | Kokoro-82M | 24 | Jun 4, 2026 | ||
| Audio Deepfake Detection | VITS | 24 | Jun 4, 2026 | ||
| Report Generation | BreastStage MRI | 24 | Jun 4, 2026 | ||
| Visual Question Answering | BreastStage-Bench Open-ended | 24 | Jun 4, 2026 | ||
| Visual Question Answering | BreastStage-Bench Closed-ended | 24 | Jun 4, 2026 | ||
| Automatic Speech Recognition | TALCS (test) | 24 | Jun 4, 2026 | ||
| Automatic Speech Recognition | VCTK noisy | 24 | Jun 4, 2026 | ||
| LLM Decoding Throughput | NOSA-8B 32K context length | 24 | Jun 4, 2026 | ||
| LLM Decoding Throughput | MiniCPM4.1-8B 32K context length | 24 | Jun 4, 2026 | ||
| Simulator selection | Measles | 24 | Jun 4, 2026 | ||
| Simulator selection | Supply Chain | 24 | Jun 4, 2026 |