Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 647 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Utterance Analysis | Toronto NeuroFace (Speech Videos) (test) | 36 | Feb 26, 2026 | ||
| Non-speech video assessment | Toronto NeuroFace non-speech videos (test) | 36 | Feb 26, 2026 | ||
| Robot Manipulation | LIBERO Goal | 36 | Jun 4, 2026 | ||
| Traveling Salesperson Problem | TSPLIB pr2392 | 36 | Mar 4, 2026 | ||
| Traveling Salesperson Problem | TSPLIB pr1002 | 36 | Mar 4, 2026 | ||
| Malicious Advice Defense | PoisonRAG | 36 | May 19, 2026 | ||
| Math Reasoning | OlympiadB | 36 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 long-tailed imbalance (test) | 36 | Feb 26, 2026 | ||
| Graph Generation | Tree | 36 | Apr 14, 2026 | ||
| Offline Reinforcement Learning | D4RL hopper medium v2 | 36 | Jun 2, 2026 | ||
| Data Leakage Detection | Image MLLM Evaluation Set | 36 | Feb 26, 2026 | ||
| Question Answering | GSM8K | 36 | Apr 10, 2026 | ||
| Sequence Classification | Breast Cancer dataset | 36 | Feb 26, 2026 | ||
| Recommendation | Industrial | 36 | Feb 26, 2026 | ||
| Recommendation | Software | 36 | Feb 26, 2026 | ||
| Question Answering | MathQA | 36 | Apr 27, 2026 | ||
| Image Classification | RESISC | 36 | May 22, 2026 | ||
| Time Series Imputation | Yeast | 36 | Feb 27, 2026 | ||
| Text-to-image generation | Copyrighted characters prompts (test) | 36 | Feb 26, 2026 | ||
| Function Selection | TaskBench Multimedia | 36 | Feb 26, 2026 | ||
| Function Selection | TaskBench DailyLife | 36 | Feb 26, 2026 | ||
| Linear Layer Latency Inference | Llama-3-8B decoder block | 36 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC23 | 36 | Feb 27, 2026 | ||
| Load forecasting | Australia | 36 | Feb 26, 2026 | ||
| 3D Sound Speed Field Reconstruction | SSF data | 36 | Feb 26, 2026 |