Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 358 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | ImageNet-1K | 52 | Jun 1, 2026 | ||
| Object Identification | Object Folder Real | 52 | Jun 11, 2026 | ||
| Image Classification | Seq-CIFAR-100 | 52 | Mar 10, 2026 | ||
| Image Classification | CIFAR-10 Seq | 52 | Mar 10, 2026 | ||
| Spatial Reasoning | Ego3D-Bench | 52 | Mar 9, 2026 | ||
| Node Classification | Arxiv | 52 | Mar 6, 2026 | ||
| Image Generation | ImageNet 50k samples | 52 | Apr 30, 2026 | ||
| Anomaly Detection | MVTec 3D-AD | 52 | Jun 25, 2026 | ||
| Fake Image Detection | UniversalFakeDetect (test) | 52 | May 21, 2026 | ||
| Nudity Erasure | I2P | 52 | Jun 30, 2026 | ||
| Multiple Choice Question Answering | WinoG | 52 | Jun 29, 2026 | ||
| Multi-label Classification | VOC 2007 | 52 | Jun 12, 2026 | ||
| Jailbreak Attack | GPTFuzz (test) | 52 | Mar 4, 2026 | ||
| Graph Classification | HIV | 52 | Mar 4, 2026 | ||
| Point cloud classification | ModelNet10 | 52 | May 19, 2026 | ||
| C-IGDP | C-IGDP | 52 | Feb 26, 2026 | ||
| Multi-modal Embedding | MMEB 1.0 (test) | 52 | Mar 4, 2026 | ||
| Harmful Prompt Refusal | HarmBench | 52 | Jul 3, 2026 | ||
| Voice Classification | HC/PD/ALS Voice Cohort Cross-Cohort (External) | 52 | Feb 26, 2026 | ||
| Voice Classification | HC/PD/ALS Voice Cohort (Internal) | 52 | Feb 26, 2026 | ||
| 3D Reconstruction | Tanks&Temples | 52 | May 29, 2026 | ||
| Reward Modeling | RewardBench Average 2 | 52 | Feb 26, 2026 | ||
| Reward Modeling | RewardBench Math 2 | 52 | Feb 26, 2026 | ||
| Image Classification | VWW | 52 | Jun 19, 2026 | ||
| Time Series Forecasting | ETTm1 (5% train) | 52 | May 14, 2026 |