Tool-call finish rate by coding agent, April 2026
Tool-call finish rate by coding agent, April 2026
Share of API calls that end with a tool_calls finish reason (the primary agentic pattern).
How do coding agent API calls end? In April 2026, Roo Code leads with 91% of calls finishing via tool_calls, the primary agentic pattern. Claude Code follows at 73%. Cline (81% stop) and Aider (87% stop) favor single-turn completions. Kilo Code shows 63% tool_calls and 28% stop, a balanced mix of agentic and single-turn patterns.
Why it mattersFinish reasons reveal fundamental architectural differences between coding agents. A high tool_calls rate indicates an agentic loop pattern where the model invokes tools (read files, write code, run tests) as part of a multi-step workflow. A high stop rate indicates single-turn generation. The industry-wide shift from stop-dominant to tool-call-dominant patterns over twelve months reflects the broader move toward autonomous coding workflows.
Key findings
- 01Roo Code: 91% tool_calls. Transitioned from 100% stop-based (early 2025) to almost entirely tool-call-based.
- 02Claude Code: 73% tool_calls, 20% stop. Heavy agentic loop with some single-turn reasoning calls.
- 03Cline: 81% stop. Primarily single-turn completions rather than multi-step tool use.
- 04Kilo Code: 63% tool_calls, 28% stop. A balanced approach between agentic and single-turn patterns.
- 05The industry has shifted from stop-dominant to tool-call-dominant patterns over twelve months.
Data
| Agent | tool_calls rate(percent) |
|---|---|
| Roo Code | 91.10% |
| OpenCode | 87.30% |
| Forge | 79.30% |
| Claude Code | 73.20% |
| Zed | 66.70% |
| Kilo Code | 62.50% |
| Cline | 16.00% |
| Aider | 12.40% |