Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 404 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Job Shop Scheduling | Taillard Benchmark | 48 | Apr 28, 2026 | ||
| Audio Understanding | AudioMarathon | 48 | Apr 28, 2026 | ||
| Object Detection | INRIA | 48 | Apr 27, 2026 | ||
| Table Question Answering | Financial TableQA | 48 | Apr 24, 2026 | ||
| Task Planning | BoxNet3D-OBS (test) | 48 | Apr 24, 2026 | ||
| Talking Face Generation | RAVDESS | 48 | Apr 29, 2026 | ||
| Treatment Policy Evaluation | SynSum (test) | 48 | Apr 21, 2026 | ||
| Multi-modal Reasoning | MoMentS | 48 | Apr 21, 2026 | ||
| Social Video Reasoning | VAGUE (test) | 48 | Apr 21, 2026 | ||
| Chemical Property Prediction | Fuels (10-fold cross-val) | 48 | Apr 20, 2026 | ||
| Open-ended Generation | TruthfulQA | 48 | Apr 20, 2026 | ||
| Long-form QA Factuality Detection | Long-form QA benchmark factuality target | 48 | Apr 20, 2026 | ||
| Pose Estimation | IQ1M forward motion sequences | 48 | Apr 16, 2026 | ||
| Code Generation | LCB v6 | 48 | Jun 9, 2026 | ||
| Segmentation | SKM-TEA | 48 | Apr 15, 2026 | ||
| Log anomaly detection | BGL | 48 | Jun 9, 2026 | ||
| Physics Question Answering | MMLU Phy | 48 | Apr 15, 2026 | ||
| Counting | Robotic Counting (val) | 48 | Apr 14, 2026 | ||
| Multimodal Medical Reasoning | VQA-RAD | 48 | Jul 1, 2026 | ||
| Long-context language understanding | LongBench v1 (test) | 48 | May 12, 2026 | ||
| Retinal Image Alignment | FIRE | 48 | Apr 14, 2026 | ||
| Partial Multi-Label Learning | image | 48 | Apr 13, 2026 | ||
| Partial Multi-Label Learning | birds | 48 | Apr 13, 2026 | ||
| Partial Multi-Label Learning | emotions | 48 | Apr 13, 2026 | ||
| Spatial Reasoning | RoboSpatial | 48 | Jun 30, 2026 |