Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2748 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reward Modeling | AndroidWorld | 14 | Feb 26, 2026 | ||
| Behavior Tree Generation | LLM-based BT Generation Benchmark | 14 | Feb 26, 2026 | ||
| Semantic Segmentation | NYUD v2 (val) | 14 | May 19, 2026 | ||
| End-to-End Autonomous Driving | NAVSIM v1 | 14 | Feb 26, 2026 | ||
| StackCube | ManiSkill 2 | 14 | Feb 26, 2026 | ||
| Continual Learning | LIBERO Spatial | 14 | Jun 26, 2026 | ||
| Lift | Simulation | 14 | Jun 23, 2026 | ||
| Image Classification | CIFAR10-DVS | 14 | Mar 4, 2026 | ||
| Path Planning | UAV Benchmark 40 terrain scenarios S.I | 14 | Feb 27, 2026 | ||
| Many-objective Optimization | F4M-DTLZ2 | 14 | Feb 26, 2026 | ||
| Reinforcement Learning | LunarLander v3 | 14 | Mar 13, 2026 | ||
| Reinforcement Learning | HalfCheetah v4 | 14 | Jun 24, 2026 | ||
| GUI Automation | WindowsAgentArena | 14 | Jun 11, 2026 | ||
| Automated Peer Review | DeepReview-13K 2025 (test) | 14 | Feb 26, 2026 | ||
| Math Problem Solving | MATH | 14 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 (test) | 14 | Feb 26, 2026 | ||
| Graph Classification | Molbace size split | 14 | Feb 26, 2026 | ||
| Graph Classification | Molbbbp (size split) | 14 | Feb 26, 2026 | ||
| Graph Classification | CMNIST color GOOD | 14 | Feb 26, 2026 | ||
| Graph Classification | Motif GOOD (basis) | 14 | Feb 26, 2026 | ||
| Graph Classification | Motif GOOD size | 14 | Feb 26, 2026 | ||
| Graph Classification | MUTAG TU (unsupervised) | 14 | Feb 26, 2026 | ||
| Graph Classification | PROTEINS TU (unsupervised) | 14 | Feb 26, 2026 | ||
| Graph Classification | NCI1 TU (unsupervised) | 14 | Feb 26, 2026 | ||
| Graph Algorithmic Reasoning | CLRS (test) | 14 | Feb 26, 2026 |