Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1457 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Code Generation | LiveCodeBench (LCB) | 21 | Apr 7, 2026 | ||
| Likes Prediction | TED Talks | 21 | Apr 7, 2026 | ||
| Regression predicting Views | TED talks dataset | 21 | Apr 7, 2026 | ||
| Vehicle Braking Control | Hardware-in-loop Out-of-distribution (test) | 21 | Apr 7, 2026 | ||
| Object Detection | HRSID (test) | 21 | Jul 7, 2026 | ||
| Video-level Deepfake Detection | DeepFake Detection Challenge Preview (DFDCP) (test) | 21 | Apr 7, 2026 | ||
| Image Understanding | Image benchmarks Aggregate | 21 | Apr 7, 2026 | ||
| Drift Detection | SEA 30 batches | 21 | Apr 7, 2026 | ||
| Drift Detection | SEA 20 batches | 21 | Apr 7, 2026 | ||
| Drift Detection | SEA 10 batches | 21 | Apr 7, 2026 | ||
| Data Stream Classification | Hyperplane (30 batches) | 21 | Apr 7, 2026 | ||
| Data Stream Classification | Hyperplane (20 batches) | 21 | Apr 7, 2026 | ||
| Data Stream Classification | Hyperplane (10 batches) | 21 | Apr 7, 2026 | ||
| Drift Detection | Elec2 (Batch 30) | 21 | Apr 7, 2026 | ||
| Drift Detection | Elec2 (Batch 20) | 21 | Apr 7, 2026 | ||
| Drift Detection | Elec2 (Batch 10) | 21 | Apr 7, 2026 | ||
| Drift Detection | Ozone (Batch 30) | 21 | Apr 7, 2026 | ||
| Drift Detection | Ozone (Batch 20) | 21 | Apr 7, 2026 | ||
| Drift Detection | Ozone (Batch 10) | 21 | Apr 7, 2026 | ||
| Video Retrieval | ActivityNet Captions (eval) | 21 | Apr 7, 2026 | ||
| Common-sense reasoning | Phy OOD Large Shift | 21 | Jul 3, 2026 | ||
| Common-sense reasoning | ARC-E OOD Small Shift | 21 | Jul 3, 2026 | ||
| Common-sense reasoning | BoolQ In-Distribution | 21 | Jul 3, 2026 | ||
| Global SoS Estimation | Phantom 2 | 21 | Apr 7, 2026 | ||
| Global SoS Estimation | Phantom 1 | 21 | Apr 7, 2026 |