Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1450 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Safety Alignment | Safety Benchmarks (Sorry-bench, StrongREJECT, WildJailbreak, JBB-PAIR, JBB-GCG) | 21 | Apr 27, 2026 | ||
| Video Object Segmentation | ReasonVOS | 21 | May 19, 2026 | ||
| Out-of-Distribution Detection | ImageNet1K OpenOOD | 21 | Apr 24, 2026 | ||
| Visual Active Tracking | UnrealCV Parking Lot scene | 21 | Apr 24, 2026 | ||
| Visible-to-Infrared Person Re-Identification | HITSZ-VCM (test) | 21 | Apr 24, 2026 | ||
| Infrared-to-Visible Person Re-Identification | HITSZ-VCM (test) | 21 | Apr 24, 2026 | ||
| Overall Performance | LiC Overall | 21 | Apr 24, 2026 | ||
| Actions | LiC Actions | 21 | Apr 24, 2026 | ||
| Database | LiC | 21 | Apr 24, 2026 | ||
| Code | LiC Code | 21 | Apr 24, 2026 | ||
| Math | LiC Math | 21 | Apr 24, 2026 | ||
| Math Reasoning | HMMT25 | 21 | May 6, 2026 | ||
| Image Classification | GTS | 21 | Apr 24, 2026 | ||
| Anomaly Recognition | ARFBench 1.0 (test) | 21 | Apr 24, 2026 | ||
| Generative tasks | 8-task generative suite | 21 | Apr 24, 2026 | ||
| Question Answering | HotPotQA | 21 | May 8, 2026 | ||
| Question Answering | Graph-Bench Medical | 21 | Apr 24, 2026 | ||
| Text-to-Image Generation | UniGenBench | 21 | Jun 9, 2026 | ||
| Functionally Diverse Response Generation | Functional Diversity Prompt Set Categories A-H 1.0 (test) | 21 | Apr 23, 2026 | ||
| General Knowledge | MMLU-Pro | 21 | Apr 23, 2026 | ||
| Video Understanding | VideoMME no subtitles (test) | 21 | Apr 23, 2026 | ||
| Multivariate Regression | ILC1 30% (test) | 21 | Apr 23, 2026 | ||
| Wound infection classification | wound infection (test) | 21 | Apr 23, 2026 | ||
| Image Classification | SVHN class-independent noise (test) | 21 | Apr 23, 2026 | ||
| Image Classification | CIFAR-10 class-independent noise (test) | 21 | Apr 23, 2026 |