Benchmarking Agents for Lightsage
Compare coding agents across General, MCP, and CLI interfaces using the latest public custom-eval results and configured workflows.
Agent performance
0 of 6 runs pass / 0%Updated Oct 26, 2026
| Agent | Total | Lightsage Docs Agent | Quickstart | Agent Skills |
|---|---|---|---|---|
1  Claude Code / Claude Sonnet 5 | ||||
2 Claude Code / Claude Haiku 4.5 | — | — |