Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1318 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | MNIST | 23 | Feb 26, 2026 | ||
| Clustering | Flowers | 23 | May 13, 2026 | ||
| Trajectory Prediction | nuScenes v1.0-trainval (val) | 23 | Feb 26, 2026 | ||
| Spatial Reasoning (Multi-Image) | ERQA | 23 | May 25, 2026 | ||
| Vessel Segment Segmentation | ARCADE-VS (test) | 23 | Feb 26, 2026 | ||
| Stenosis Segmentation | ARCADE-S (test) | 23 | Feb 26, 2026 | ||
| Vision | CVBench | 23 | Apr 30, 2026 | ||
| Text Rendering | CVTG-2K (test) | 23 | Apr 29, 2026 | ||
| Jailbreak Detection | MM-SafetyBench | 23 | Jun 8, 2026 | ||
| Image Watermarking | COCO Dataset | 23 | Feb 27, 2026 | ||
| Membership Inference | TinyImageNet | 23 | Feb 26, 2026 | ||
| Prompt Injection Defense | AgentDojo New Attack 2 | 23 | Feb 26, 2026 | ||
| Prompt Injection Defense | AgentDojo New Attack 1 | 23 | Feb 26, 2026 | ||
| Prompt Injection Defense | AgentDojo Important Instructions | 23 | Feb 26, 2026 | ||
| Prompt Injection Defense | AgentDojo No Attack | 23 | Feb 26, 2026 | ||
| Mathematical Reasoning | LMB (LiveMathBench) | 23 | Feb 26, 2026 | ||
| Code Generation | HumanEval 0-shot (test) | 23 | Jun 1, 2026 | ||
| Medical Question Answering | MVME (test) | 23 | Feb 26, 2026 | ||
| Medical Question Answering | MedXpertQA (test) | 23 | Feb 26, 2026 | ||
| Mental Health Reasoning and Assessment | MentraBench 1.0 (test) | 23 | Feb 26, 2026 | ||
| Machine Translation | FLORES-200 | 23 | May 29, 2026 | ||
| Question Answering | PopQA longtail | 23 | Feb 26, 2026 | ||
| Reasoning | BBEH | 23 | May 28, 2026 | ||
| Financial Reasoning | ConvFinQA | 23 | Mar 10, 2026 | ||
| Text Embedding | MTEB Turkish (test) | 23 | Feb 26, 2026 |