Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1493 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Robot Manipulation | LIBERO OpenVLA-OFT | 21 | Mar 31, 2026 | ||
| Single-hop Question Answering | NQ (Natural Questions) (test) | 21 | Feb 26, 2026 | ||
| Job Shop Scheduling Problem | JSSP | 21 | Feb 26, 2026 | ||
| Minimum Vertex Cover | MVC | 21 | Feb 26, 2026 | ||
| Maximum Independent Set | MIS | 21 | Feb 26, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP | 21 | Feb 26, 2026 | ||
| Orienteering Problem | OP | 21 | Feb 26, 2026 | ||
| Traveling Salesperson Problem | TSP | 21 | Feb 26, 2026 | ||
| Adversarial Robustness | GCG | 21 | Feb 26, 2026 | ||
| Safety | WildJailbreak | 21 | Feb 26, 2026 | ||
| Embodied Agentic | PDDL | 21 | Feb 26, 2026 | ||
| Embodied Agentic | GAIA | 21 | Feb 26, 2026 | ||
| Embodied Agentic | SciWorld | 21 | Feb 26, 2026 | ||
| Multi-modal hate speech detection | MMHS11K (test) | 21 | Feb 26, 2026 | ||
| Mathematics | Erdős’ minimum overlap problem | 21 | Jun 12, 2026 | ||
| Binding Affinity Prediction | CASF 2016 (test) | 21 | Jun 23, 2026 | ||
| Sycophancy | FaithfulQA | 21 | Feb 26, 2026 | ||
| Refusal | SaladBench | 21 | Feb 26, 2026 | ||
| Reasoning | Reasoning Domain Game | 21 | Feb 26, 2026 | ||
| Reasoning | Reasoning Domain Logic | 21 | Feb 26, 2026 | ||
| Reasoning | Reasoning Domain Arithmetic | 21 | Feb 26, 2026 | ||
| Reasoning | Reasoning Domain Social | 21 | Feb 26, 2026 | ||
| Reasoning | Reasoning Domain Code | 21 | Feb 26, 2026 | ||
| Question Answering | WTQ | 21 | Mar 18, 2026 | ||
| Masked Entity Prediction | ICEWS05-15 standard (test) | 21 | Feb 26, 2026 |