Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2154 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Utility Evaluation | MMLU, GSM8K | 16 | May 26, 2026 | ||
| Utility Retention | Utility MMLU and GSM8K | 16 | May 26, 2026 | ||
| Planning and Control | maze2d-umaze v1 (100 episodes, 300 steps/ep) | 16 | May 26, 2026 | ||
| Multi-turn Reasoning | DRIFT-BENCH (test) | 16 | May 26, 2026 | ||
| Open Vocabulary Segmentation | Mapillary CS | 16 | May 26, 2026 | ||
| Open Vocabulary Segmentation | ADE CS | 16 | May 26, 2026 | ||
| Open Vocabulary Segmentation | COCO CS | 16 | May 26, 2026 | ||
| General Perception | GQA | 16 | May 25, 2026 | ||
| General Perception | MMSTAR | 16 | May 25, 2026 | ||
| Vision-Centric Perception | RealWorldQA | 16 | May 25, 2026 | ||
| Vision-Centric / 3D | CV-Bench 2D | 16 | May 25, 2026 | ||
| Relational Reasoning | VSR | 16 | May 25, 2026 | ||
| Relational Reasoning | W-UP | 16 | May 25, 2026 | ||
| Compliance Classification | CompliVision Average across 3 Domains (test) | 16 | May 25, 2026 | ||
| Heart Rate Estimation | MMPD trained on PURE (test) | 16 | Jul 1, 2026 | ||
| Action Recognition | Ego-Exo4D Bike Repair | 16 | May 25, 2026 | ||
| Transferability estimation | PACS v1 (test) | 16 | May 25, 2026 | ||
| Transferability estimation | OfficeHome v1 (test) | 16 | May 25, 2026 | ||
| Transferability estimation | DomainNet v1 (test) | 16 | May 25, 2026 | ||
| Transferability Prediction | PACS | 16 | May 25, 2026 | ||
| Transferability Prediction | OfficeHome | 16 | May 25, 2026 | ||
| Transferability Estimation | ImageNet-C Severity 3 1.0 | 16 | May 25, 2026 | ||
| Transferability Estimation | ImageNet-C Severity 1 1.0 | 16 | May 25, 2026 | ||
| Sentiment Analysis | Amazon Reviews 31 | 16 | May 25, 2026 | ||
| Sentiment Analysis | EuroEval 34 | 16 | May 25, 2026 |