Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2468 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-Agent Reinforcement Learning | SMAC 5m_vs_6m v2 | 15 | Mar 4, 2026 | ||
| Multi-Agent Reinforcement Learning | SMAC 3s5z vs 3s6z v2 | 15 | Mar 4, 2026 | ||
| user-engage binary classification | rel-stack (test) | 15 | Jun 16, 2026 | ||
| Traveling Salesperson Problem | TSPLIB pcb3038 | 15 | Mar 24, 2026 | ||
| Traveling Salesperson Problem | TSPLIB u2152 | 15 | Mar 24, 2026 | ||
| Traveling Salesperson Problem | TSPLIB fl1577 | 15 | Mar 24, 2026 | ||
| ADHD Diagnosis | ADHD-200 (test) | 15 | Mar 4, 2026 | ||
| Open-ended Generation (CHAIR Metric) | MSCOCO (Subset) | 15 | Mar 4, 2026 | ||
| Question Answering | GPQA (val) | 15 | Mar 4, 2026 | ||
| Discriminative Ranking | Amazon Beauty | 15 | Mar 12, 2026 | ||
| Discriminative Ranking | Industrial Dataset | 15 | Mar 12, 2026 | ||
| Few-Shot Class-Incremental Learning | CIFAR100 | 15 | Mar 4, 2026 | ||
| Forward PDE solving | Navier-Stokes | 15 | May 26, 2026 | ||
| Mobility Prediction | CA Foursquare Gowalla (test) | 15 | Mar 4, 2026 | ||
| Toxic text prevention | LDNOOBW source prompts 2020 | 15 | Mar 4, 2026 | ||
| Novel View Synthesis | ScanNet 4 views | 15 | Mar 25, 2026 | ||
| Novel View Synthesis | RE10K 4 views | 15 | Mar 25, 2026 | ||
| Counterfactual explanation generation | highD subsets | 15 | Mar 4, 2026 | ||
| Musicality Evaluation | CMI-Pref | 15 | Mar 4, 2026 | ||
| Musicality Evaluation | Music Arena | 15 | Mar 4, 2026 | ||
| Single-reference novel object pose estimation | YCB-V | 15 | Mar 4, 2026 | ||
| Single-reference novel object pose estimation | TUD-L | 15 | Mar 4, 2026 | ||
| Single-reference novel object pose estimation | LM-O | 15 | Mar 4, 2026 | ||
| Perception | MME total perception score | 15 | Mar 4, 2026 | ||
| Central Apnea Detection | SHHS | 15 | Mar 4, 2026 |