Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1468 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video Question Answering | UrbanVideo and VSI-Bench Clean | 21 | Mar 12, 2026 | ||
| Video Reasoning Quality Assessment | PVRBench | 21 | Mar 12, 2026 | ||
| Video Question Answering | PVRBench | 21 | Mar 12, 2026 | ||
| Depth Completion | VOID | 21 | May 13, 2026 | ||
| Geolocation | WanderBench Country level | 21 | Mar 12, 2026 | ||
| Geolocation | WanderBench City level | 21 | Mar 12, 2026 | ||
| Geolocation | WanderBench Street level | 21 | Mar 12, 2026 | ||
| Geolocation | WanderBench Overall | 21 | Mar 12, 2026 | ||
| Quadruped Robot Design Specification | Quadruped Robots Comparison | 21 | Mar 24, 2026 | ||
| Science Question Answering | ARC-C | 21 | Mar 12, 2026 | ||
| Language Understanding | MMLU | 21 | Mar 12, 2026 | ||
| Multimodal Reasoning | MME | 21 | Apr 14, 2026 | ||
| Spatial Reasoning | MMSI | 21 | Jun 11, 2026 | ||
| Truthfulness Classification | TruthfulQA (held-out evaluation) | 21 | Mar 12, 2026 | ||
| Mathematical Reasoning | MATH | 21 | Mar 11, 2026 | ||
| Joint Tri-Modal Medical Image Fusion and Super-Resolution | Harvard dataset (test) | 21 | Mar 11, 2026 | ||
| Mesh Reconstruction | Replica (Room 0) | 21 | Jun 2, 2026 | ||
| 3D MRI Super-Resolution | MSD (test) | 21 | Mar 11, 2026 | ||
| Region-level Classification | RRSIS-D | 21 | Mar 11, 2026 | ||
| Region-level Classification | NWPU-VHR-10 | 21 | Mar 11, 2026 | ||
| Fine-grained Understanding | CHOICE img | 21 | Mar 11, 2026 | ||
| Fine-grained Understanding | CHOICE ins | 21 | Mar 11, 2026 | ||
| Fine-grained Understanding | RRSIS-HR | 21 | Mar 11, 2026 | ||
| Multimodal Generation | GenEval | 21 | Mar 31, 2026 | ||
| Common Sense | OpenBookQA | 21 | Mar 11, 2026 |