Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2148 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| LLM Agent Security and Utility Evaluation | DTAP-150 | 16 | May 29, 2026 | ||
| Class-Incremental Learning | ImageNet-R B100 Inc20 | 16 | Jun 25, 2026 | ||
| Search | MM Search | 16 | May 28, 2026 | ||
| Search | HR-MM Search | 16 | May 28, 2026 | ||
| Perception | HRBen 8K | 16 | May 28, 2026 | ||
| Perception | HRBen 4K | 16 | May 28, 2026 | ||
| Perception | Visual Probe | 16 | May 28, 2026 | ||
| Reasoning | V* | 16 | May 28, 2026 | ||
| Reasoning | Math-VR | 16 | May 28, 2026 | ||
| Reasoning | Dyna Math | 16 | May 28, 2026 | ||
| Reasoning | Math Vision | 16 | May 28, 2026 | ||
| Search | MM Search | 16 | May 28, 2026 | ||
| Search | HR-MM Search | 16 | May 28, 2026 | ||
| Perception | HRBen 8K | 16 | May 28, 2026 | ||
| Perception | Visual Probe | 16 | May 28, 2026 | ||
| Perception | V* | 16 | May 28, 2026 | ||
| General Assistant Tasks | GAIA | 16 | May 28, 2026 | ||
| Compositional Text-to-Image Generation | T2I-CompBench | 16 | May 28, 2026 | ||
| Agentic Planning and Ideation | MUTATE (test) | 16 | May 28, 2026 | ||
| Medical VQA | In-house (Held-out) | 16 | May 28, 2026 | ||
| Visual Grounding QA | GEMeX RMCoT | 16 | May 28, 2026 | ||
| Medical VQA | BiomedParse In-Domain (test) | 16 | May 28, 2026 | ||
| Medical VQA | MSD In-Domain (test) | 16 | May 28, 2026 | ||
| General Multimodal Evaluation | MMVet turbo | 16 | May 28, 2026 | ||
| Local Feature Importance Evaluation | 12 Real-World Datasets Aggregate (test) | 16 | May 28, 2026 |