Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 124 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Logistic Regression | Logistic regression d=50, K=20, epsilon=0.2 varying per-task sample size n (test) | 102 | Jul 7, 2026 | ||
| Local prediction error | HAR 50% (train) | 102 | Jul 7, 2026 | ||
| Out-of-Distribution Detection | CUB | 102 | Apr 24, 2026 | ||
| Multimodal Reasoning | MMStar | 102 | Jul 7, 2026 | ||
| Image Generation | Imagenet-256 latent space | 102 | Jul 9, 2026 | ||
| Image Classification | CIFAR-100 v1 (test) | 102 | Jun 18, 2026 | ||
| Instruction Following | AdvancedIF | 102 | Jul 7, 2026 | ||
| Code Reasoning | LiveCodeBench | 102 | Jun 16, 2026 | ||
| Multimodal Reward Modeling | VL-RewardBench | 102 | Apr 23, 2026 | ||
| Interactive Tool-Use Agent Performance | tau2-Bench | 102 | Mar 4, 2026 | ||
| Image Editing | GEdit-Bench | 102 | Apr 28, 2026 | ||
| Image Retrieval | Cars-196 | 102 | Jun 16, 2026 | ||
| Counting | CountBench | 102 | Apr 29, 2026 | ||
| Question Answering | OpenBookQA | 102 | Apr 10, 2026 | ||
| Zero-shot Evaluation | PIQA, WinoGrande, HellaSwag, ARC (Easy and Challenge), LAMBADA (test) | 102 | Jul 9, 2026 | ||
| Mathematical Reasoning | GSM8K | 102 | Feb 26, 2026 | ||
| Multivariate Time Series Anomaly Detection | SWaT | 102 | Jun 18, 2026 | ||
| Survival prediction | KIRC TCGA | 102 | Jun 4, 2026 | ||
| Base-to-New Generalization | Avg over 11 datasets | 102 | May 19, 2026 | ||
| Class-conditional Image Generation | ImageNet 512x512 (val) | 102 | Jun 1, 2026 | ||
| Few-shot Classification | ModelNet40 5-way 20-shot | 102 | May 6, 2026 | ||
| Few-shot Classification | ModelNet40 5-way 10-shot | 102 | May 6, 2026 | ||
| Audio Classification | AudioSet 2M | 102 | Jun 9, 2026 | ||
| Image Classification | Country211 | 102 | Mar 4, 2026 | ||
| Unconditional Generation | CIFAR-10 (test) | 102 | Feb 26, 2026 |