Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 691 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Object Detection | Waymo Open Dataset Level 2 | 35 | Feb 26, 2026 | ||
| Predicate Classification (PredCls) | 3DSSG | 35 | Jun 16, 2026 | ||
| 3D Lane Detection | ApolloSim Visual Variations | 35 | Jul 1, 2026 | ||
| Event Classification | OntoEvent (test) | 35 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K V2 (val) | 35 | Feb 26, 2026 | ||
| Node Classification | Cora (10 different splits) | 35 | Feb 26, 2026 | ||
| Mirror Detection | PMD | 35 | Feb 26, 2026 | ||
| Map Segmentation | nuScenes (val) | 35 | Jul 7, 2026 | ||
| Offline Reinforcement Learning | D4RL halfcheetah-random v2 | 35 | Jun 2, 2026 | ||
| Offline Reinforcement Learning | D4RL walker2d-random v2 | 35 | Jun 2, 2026 | ||
| Offline Reinforcement Learning | D4RL hopper-random v2 | 35 | Jun 2, 2026 | ||
| Video Classification | Kinetics-400 v1 (val) | 35 | Feb 26, 2026 | ||
| Autonomous Driving | Longest6 | 35 | Feb 26, 2026 | ||
| Commonsense Reasoning | aNLI | 35 | Mar 18, 2026 | ||
| Video Summarization | SumMe (various) | 35 | Feb 26, 2026 | ||
| Spatial-temporal Time Series Forecasting | PEMS03 | 35 | Feb 26, 2026 | ||
| Object Detection | LVIS 1.0 (minival) | 35 | Mar 10, 2026 | ||
| Task-incremental Learning | Mini-Imagenet (test) | 35 | Feb 26, 2026 | ||
| Class-incremental Learning | CIFAR100 (test) | 35 | May 20, 2026 | ||
| Image Classification | CIFAR-100 (IF=50) long-tail (test) | 35 | Jun 2, 2026 | ||
| Action Recognition | UCF-101 fine-tuning protocol | 35 | Feb 26, 2026 | ||
| Masked Language Modeling | C4 (val) | 35 | Feb 26, 2026 | ||
| Language Modeling | Wiki-40B (val) | 35 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Hopper Medium | 35 | Feb 26, 2026 | ||
| Semantic Segmentation | Synthia 4D (test) | 35 | Apr 14, 2026 |