Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 256 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-modal Video Understanding | VideoMME | 64 | May 11, 2026 | ||
| EEG-to-text translation | EEG-ImageNet CVPR2017 (test) | 64 | May 28, 2026 | ||
| Frequency Estimation | Retail | 64 | Mar 18, 2026 | ||
| Frequency Estimation | Kosarak | 64 | Mar 18, 2026 | ||
| Frequency Estimation | CAIDA streaming trace | 64 | Mar 18, 2026 | ||
| Perceived risk prediction | Scenario HB (held out events) | 64 | Mar 17, 2026 | ||
| Synthetic Anomaly Generation | MVTec AD (test) | 64 | Mar 17, 2026 | ||
| Zero-shot Reasoning | Reasoning Tasks (BoolQ, PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c, OBQA) Zero-shot | 64 | Jun 23, 2026 | ||
| steady-state performance estimation | System 2 Three-station feed-forward network | 64 | Mar 13, 2026 | ||
| Video Generation | OpenVFX (test) | 64 | Mar 10, 2026 | ||
| Jailbreak Attack | Advbench-M | 64 | Apr 15, 2026 | ||
| Synthetic Text Evaluation | Yelp non-IID | 64 | Mar 10, 2026 | ||
| Web Navigation | Mind2Web Cross-Domain | 64 | Jun 30, 2026 | ||
| VMAT Treatment Planning | Intact prostate VMAT cases (val) | 64 | Mar 9, 2026 | ||
| Image Classification | UCF101 | 64 | Jul 8, 2026 | ||
| dynamic link prediction | Flights (transductive) | 64 | Jun 4, 2026 | ||
| User Churn Prediction | Amazon Rel | 64 | May 25, 2026 | ||
| Item Churn Prediction | Rel Amazon | 64 | May 25, 2026 | ||
| Knowledge Evaluation | MMLU | 64 | Jun 2, 2026 | ||
| Energy and Force Prediction | Zeolite (test) | 64 | Mar 4, 2026 | ||
| General Knowledge Reasoning | MMLU Pro | 64 | May 12, 2026 | ||
| Question Answering | CoQA | 64 | May 27, 2026 | ||
| Out-of-Distribution Detection | ImageNet-1k (ID) vs Textures (OOD) 1.0 (test) | 64 | May 27, 2026 | ||
| Image Classification | CIFAR-100 | 64 | Feb 27, 2026 | ||
| Action Anticipation | DARai Coarse | 64 | Feb 26, 2026 |