Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 831 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Reconstruction | ModelNet10 | 30 | Jun 11, 2026 | ||
| Text-to-SQL | Spider Non-Seed Domains | 30 | Jun 11, 2026 | ||
| Text-to-SQL | Spider all domains | 30 | Jun 11, 2026 | ||
| Duration-Based Fine-Grained Prediction | PeMS08 | 30 | Jun 9, 2026 | ||
| Duration-Based Fine-Grained Prediction | PeMS07 | 30 | Jun 9, 2026 | ||
| Duration-Based Fine-Grained Prediction | PeMS04 | 30 | Jun 9, 2026 | ||
| Duration-Based Fine-Grained Prediction | PeMS03 | 30 | Jun 9, 2026 | ||
| Duration-Based Fine-Grained Prediction | PeMS-Bay | 30 | Jun 9, 2026 | ||
| Duration-Based Fine-Grained Prediction | METR-LA | 30 | Jun 9, 2026 | ||
| Object Detection | OD-LVIS 15 open domains (test) | 30 | Jun 9, 2026 | ||
| Social Interaction Simulation | EduMirror social interaction steps (144 steps) (test) | 30 | Jun 9, 2026 | ||
| Composed Image Retrieval | ZeroSight (test) | 30 | Jun 8, 2026 | ||
| Preference Optimization | Helpful Assistant | 30 | Jun 8, 2026 | ||
| Long-horizon Closed-loop Generation | nuScenes | 30 | Jun 5, 2026 | ||
| Code Problem Solving | LiveCodeBench v6 | 30 | Jun 26, 2026 | ||
| Trajectory Planning | AUV Trajectory Planning Scenarios 1.0 (Evaluation) | 30 | Jun 5, 2026 | ||
| Molecule Correction | ChEBI-20 | 30 | Jun 5, 2026 | ||
| Jailbreak Robustness | WJ (heldout) | 30 | Jun 5, 2026 | ||
| Multiple Choice Question Answering | HellaSwag, PIQA, ARC-Easy (ARC-E), ARC-Challenge (ARC-C) (test) | 30 | Jun 5, 2026 | ||
| Image Denoising | Set12 Starfish | 30 | Jun 5, 2026 | ||
| Image Denoising | Set12 (Peppers) | 30 | Jun 5, 2026 | ||
| Clustering | MNIST | 30 | Jun 16, 2026 | ||
| Entity Linking (RCM) | CTIConnect 691-pair subset | 30 | Jun 5, 2026 | ||
| Hyperspectral Compressed Recovery | AVARIS Moffet Field | 30 | Jun 5, 2026 | ||
| Frequency Estimation | Simulated noisy 3-D signal sampling rate 6% | 30 | Jun 5, 2026 |