Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 752 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Fetal Head Segmentation | FetalPlanes (OOD) | 32 | Jun 16, 2026 | ||
| General Performance | Overall Aggregate (test) | 32 | Jun 16, 2026 | ||
| Multiple Choice | Multiple Choice MC Avg (test) | 32 | Jun 16, 2026 | ||
| Writing | WildBench (test) | 32 | Jun 16, 2026 | ||
| Coding | LiveCode (test) | 32 | Jun 16, 2026 | ||
| Coding | Eval+ (test) | 32 | Jun 16, 2026 | ||
| Adversarial Attack | JailbreakBench 50% stratified per-category sample (48 requests) | 32 | Jun 16, 2026 | ||
| Segmentation | Synthetic images | 32 | Jun 16, 2026 | ||
| Image Classification | STL10 LT | 32 | Jun 16, 2026 | ||
| Image Classification | CIFAR100 LT | 32 | Jun 16, 2026 | ||
| Prompt Injection Defense | Three Suites Aggregated 1.0 (test) | 32 | Jun 16, 2026 | ||
| Unsupervised Domain Adaptation | VisDA-17 | 32 | Jun 23, 2026 | ||
| Terminal-based agent interaction | Terminal-Bench 2.0 | 32 | Jun 17, 2026 | ||
| Deception Detection | Varied Deception | 32 | Jun 12, 2026 | ||
| Robustness verification | CIFAR10 | 32 | Jun 12, 2026 | ||
| Robustness Verification | MNIST Strokes | 32 | Jun 12, 2026 | ||
| 1:N search | CIFAR 100/10 (test) | 32 | Jun 12, 2026 | ||
| Financial Reasoning | DM-Simplong | 32 | Jun 11, 2026 | ||
| Node Classification Backdoor Defense | OGB-arxiv (GU) | 32 | Jun 11, 2026 | ||
| Node Classification Backdoor Defense | Flickr (GU) | 32 | Jun 11, 2026 | ||
| Node Classification Backdoor Defense | Physics (GU) | 32 | Jun 11, 2026 | ||
| Node Classification Backdoor Defense | PubMed (GU) | 32 | Jun 11, 2026 | ||
| Node Classification Backdoor Defense | CiteSeer (GU) | 32 | Jun 11, 2026 | ||
| Node Classification Backdoor Defense | Cora (GU) | 32 | Jun 11, 2026 | ||
| Single-task capability preservation | FLUX.1 (dev) | 32 | Jun 11, 2026 |