Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2147 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Task and Motion Planning | Franka Assigned Simulated | 16 | May 29, 2026 | ||
| Cross-Resolution Person Re-identification | MLR-Market-1501 | 16 | May 29, 2026 | ||
| Tool Calling | BFCL Live | 16 | May 29, 2026 | ||
| Tool Calling | BFCL Non-live | 16 | May 29, 2026 | ||
| Tool-calling | Stable Toolbench I3-Inst | 16 | May 29, 2026 | ||
| Tool-calling | Stable Toolbench I2-Cat | 16 | May 29, 2026 | ||
| Tool-calling | Stable Toolbench I2-Inst | 16 | May 29, 2026 | ||
| Tool-calling | Stable Toolbench I1-Tool | 16 | May 29, 2026 | ||
| Tool-calling | Stable Toolbench I1-Cat | 16 | May 29, 2026 | ||
| Tool-calling | Stable Toolbench I1-Inst | 16 | May 29, 2026 | ||
| Mobile GUI Task Execution | A3 | 16 | May 29, 2026 | ||
| GUI Agent Interaction | OSWorld | 16 | Jun 24, 2026 | ||
| Locomotion | D4RL Walker2d medium-replay v2 | 16 | Jun 16, 2026 | ||
| Package Hallucination Evaluation | SO_AT | 16 | May 29, 2026 | ||
| Package Hallucination Evaluation | SO_LY | 16 | May 29, 2026 | ||
| Package Hallucination Evaluation | LLM_AT | 16 | May 29, 2026 | ||
| Package Hallucination Evaluation | LLM_LY | 16 | May 29, 2026 | ||
| Mathematical Reasoning | MATH500, AMC23, GSM8K (test) | 16 | May 29, 2026 | ||
| CTR Prediction | Amazon Electronics | 16 | May 29, 2026 | ||
| Trade Ordering for Price Stability | Simulated Trade Workloads 100 trials | 16 | May 29, 2026 | ||
| Multi-hop Question Answering | Bamboogle | 16 | May 29, 2026 | ||
| Multi-hop Question Answering | MuSiQue | 16 | May 29, 2026 | ||
| Multi-hop Question Answering | 2Wiki | 16 | May 29, 2026 | ||
| Image Classification | ImageNet | 16 | May 29, 2026 | ||
| LLM Agent Security and Utility Evaluation | AgentTrap | 16 | May 29, 2026 |