Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1802 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Real-World Visual Reasoning | MME-RealWorld Lite | 18 | Jun 9, 2026 | ||
| High-Resolution Fine-Grained Visual Perception | HR-Bench-8K | 18 | Jun 9, 2026 | ||
| Mathematical Reasoning | MMK12 | 18 | Jun 9, 2026 | ||
| Mathematical Reasoning | Geo3k | 18 | Jun 9, 2026 | ||
| Mathematical Reasoning | AIME24, AIME25, AMC23, MATH, Olympiad (aggregate) | 18 | Jun 9, 2026 | ||
| Mathematical Reasoning | AMC 2023 (test) | 18 | Jun 9, 2026 | ||
| Image Classification | CIFAR-100 Personalized | 18 | Jun 9, 2026 | ||
| Image Classification | CIFAR-10 Personalized | 18 | Jun 9, 2026 | ||
| Medical Image Segmentation | Fundus photography images | 18 | Jun 9, 2026 | ||
| Medical Image Segmentation | Histology nuclei | 18 | Jun 9, 2026 | ||
| Spoofing Detection | ASVspoof 5 (eval) | 18 | Jun 11, 2026 | ||
| Zero-shot Coordination | Overcooked-AI Forced Coordination | 18 | Jun 9, 2026 | ||
| Zero-shot Coordination | Overcooked-AI Counter Circuit | 18 | Jun 9, 2026 | ||
| Zero-shot Coordination | Overcooked-AI Coordination Ring | 18 | Jun 9, 2026 | ||
| Zero-shot Coordination | Overcooked-AI Cramped Room | 18 | Jun 9, 2026 | ||
| Quantum Error Correction | 3-qubit repetition code | 18 | Jun 9, 2026 | ||
| Pick-and-place | Real-world Pick-and-place Average Setting v1 | 18 | Jun 9, 2026 | ||
| Pick-and-place | Real-world Pick-and-place BG Light v1 | 18 | Jun 9, 2026 | ||
| Pick-and-place | Real-world Pick-and-place Dense v1 | 18 | Jun 9, 2026 | ||
| Pick-and-place | Real-world Pick-and-place Sparse v1 | 18 | Jun 9, 2026 | ||
| Instructional Temporal Answer Grounding in Video | VehicleVQA (test) | 18 | Jun 9, 2026 | ||
| Membership Inference Attack | NIST Arizona QImedium | 18 | Jun 9, 2026 | ||
| Membership Inference Attack | CDC Diabetes QIdemo | 18 | Jun 9, 2026 | ||
| Membership Inference Attack | Adult QIdemo | 18 | Jun 9, 2026 | ||
| Visual-Centric Reasoning | MME | 18 | Jun 9, 2026 |