Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2167 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Spatial Reasoning | UHR-Micro (test) | 16 | May 13, 2026 | ||
| Counting | UHR-Micro (test) | 16 | May 13, 2026 | ||
| Fine-grained Understanding | UHR-Micro (test) | 16 | May 13, 2026 | ||
| Grounding | UHR-Micro (test) | 16 | May 13, 2026 | ||
| Point Cloud Classification | ModelNet40 Split2 plus Split1 v1 | 16 | May 13, 2026 | ||
| Open-set Point Cloud Classification | ScanObjectNN (Split2 plus Split1) | 16 | May 13, 2026 | ||
| Discriminative Evaluation | RuDE base | 16 | May 13, 2026 | ||
| Calibration and Measurement | 14 social science constructs (Full Dataset) | 16 | May 13, 2026 | ||
| Multimodal Reranking | ViDoRe English | 16 | May 13, 2026 | ||
| Mathematical Reasoning | MATH | 16 | May 13, 2026 | ||
| Mathematical Reasoning | GSM8K | 16 | May 13, 2026 | ||
| Mathematical Reasoning | MATH 500 | 16 | May 13, 2026 | ||
| Mathematical Reasoning | AIME 25 | 16 | May 13, 2026 | ||
| Mathematical Reasoning | AIME24 | 16 | May 13, 2026 | ||
| Agentic Tool-Use | ACEBench | 16 | Jun 1, 2026 | ||
| Agentic Tool-Use | BFCL | 16 | May 13, 2026 | ||
| Agentic Tool-Use | ToolSandbox Multi-Tool | 16 | May 13, 2026 | ||
| Scientific Question Answering | ARC Challenge | 16 | Jul 1, 2026 | ||
| Depth Estimation | YCB-Video | 16 | May 14, 2026 | ||
| Few-shot classification | BSCD-FSL 5-way 5-shot | 16 | May 13, 2026 | ||
| Cross-view Geo-localization | DenseUAV | 16 | Jun 2, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Suite Overall | 16 | May 13, 2026 | ||
| Mathematical Reasoning | HMMT 2026 | 16 | May 13, 2026 | ||
| PDE Discovery | KdV PDE | 16 | May 13, 2026 | ||
| PDE Identification | KdV PDE | 16 | May 13, 2026 |