Code Agent
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Diagram Generation | Code Agent | Pass@158.15 | 17 | |
| Hallucination Detection | Code-agent (test) | Precision61.9 | 11 | |
| Agent Task Utility and Admission Integrity | Code-agent exact-effect benchmark | STC Count231 | 1 |
Showing 3 of 3 rows