Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 32 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Science Reasoning | GPQA | 243 | Apr 15, 2026 | ||
| Face Verification | IJB-C | 243 | Jun 11, 2026 | ||
| Code Generation | MBPP+ | 243 | Jun 15, 2026 | ||
| Jailbreak Attack | JailbreakBench | 242 | May 22, 2026 | ||
| Code Generation | Code | 242 | Feb 26, 2026 | ||
| Object Detection | MS COCO (val) | 242 | Jun 29, 2026 | ||
| Reasoning | ARC Easy | 242 | Jul 9, 2026 | ||
| Mathematical Reasoning | HMMT 2025 | 241 | Jul 1, 2026 | ||
| Node classification | Photo (test) | 241 | Jun 23, 2026 | ||
| Black-box Adversarial Attack | CtrSVDD | 240 | Jun 1, 2026 | ||
| Multi-modal Evaluation | MME | 240 | Jul 9, 2026 | ||
| Augmented Capacitated Vehicle Routing Problem | ACVRP A-G and A-U (120 instances) | 240 | Feb 26, 2026 | ||
| Referring Video Object Segmentation | Ref-DAVIS 2017 (val) | 240 | Jun 8, 2026 | ||
| Image Classification | CIFAR10 | 240 | Feb 27, 2026 | ||
| Visual Speech Recognition | LRS3 (test) | 240 | Jun 2, 2026 | ||
| Video Object Segmentation | YouTube-VOS 2019 (val) | 240 | Jul 7, 2026 | ||
| Image Classification | Fashion MNIST | 240 | Mar 31, 2026 | ||
| Science Question Answering | ARC-E | 240 | May 29, 2026 | ||
| Long-term time-series forecasting | Weather (test) | 240 | Jun 11, 2026 | ||
| Visual Question Answering | A-OKVQA | 240 | Jul 2, 2026 | ||
| Mathematical Reasoning | MATH 500 | 239 | Mar 24, 2026 | ||
| Text-to-Image Generation | MJHQ-30K | 239 | May 27, 2026 | ||
| 3D object detection | nuScenes v1.0 (test) | 239 | Jul 2, 2026 | ||
| Action Recognition | NTU-120 (cross-subject (xsub)) | 239 | Apr 21, 2026 | ||
| Node Classification | Citeseer | 238 | Jun 11, 2026 |