Multi-step tool-calling agent tasks
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Agentic Tool Use | Multi-step tool-calling agent tasks Aggregate over 4 models: Nova 2 Lite, Nova 2 Pro, Claude 3.5 Haiku, Claude Sonnet 4.6 (test) | Success Rate99 | 5 |
Showing 1 of 1 rows