Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2106 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | DeepMath-103K (test) | 16 | Jul 7, 2026 | ||
| Question Answering | HotpotQA (test) | 16 | Jul 7, 2026 | ||
| Unlearning | SciQ-WMDP-Bio (test) | 16 | Jul 7, 2026 | ||
| Object Detection | M3FD (Challenge) | 16 | Jul 7, 2026 | ||
| Object Detection | M3FD (Day) | 16 | Jul 7, 2026 | ||
| Domain Adaptation | PACS (test) | 16 | Jul 7, 2026 | ||
| Inference Latency | ImageNet-1K 1.0 (val) | 16 | Jul 7, 2026 | ||
| Image Restoration (Deblurring) | FFHQ | 16 | Jul 7, 2026 | ||
| Graph Classification | GOOD-PCBA size | 16 | Jul 7, 2026 | ||
| Graph Classification | GOOD-PCBA scaffold | 16 | Jul 7, 2026 | ||
| Explanation Generation | TrendFact (test) | 16 | Jul 7, 2026 | ||
| LiDAR Semantic Segmentation | FLARE (test) | 16 | Jul 7, 2026 | ||
| Global Source Attribution | MLAAD Few-Shot Open-Set (test) | 16 | Jul 7, 2026 | ||
| Code | LCB | 16 | Jul 7, 2026 | ||
| Math | AIME 24 | 16 | Jul 7, 2026 | ||
| Element-specific Counting | PubChem-STM (test) | 16 | Jul 7, 2026 | ||
| Text-to-Image Generation | Pick-a-Pic | 16 | Jul 7, 2026 | ||
| Semantic Segmentation | ADE20K | 16 | Jul 7, 2026 | ||
| Long-horizon behavior prediction | OminiBehavior (Overall) | 16 | Jul 7, 2026 | ||
| Long-horizon behavior prediction | OminiBehavior E-commerce scenario | 16 | Jul 7, 2026 | ||
| Long-horizon behavior prediction | OminiBehavior Ads | 16 | Jul 7, 2026 | ||
| Long-horizon behavior prediction | OminiBehavior (Live scenario) | 16 | Jul 7, 2026 | ||
| Long-horizon behavior prediction | OminiBehavior Video | 16 | Jul 7, 2026 | ||
| Closed-loop Autonomous Driving Planning | Bench2Drive (test) | 16 | Jul 7, 2026 | ||
| Robotic Manipulation | DynaGrasp-32 | 16 | Jul 7, 2026 |