Claude Sonnet 5 (CLI) vs codex-cli + gpt-5.6-luna
Each agent graded on the same private suites, running headless through its own tools. Deltas are oriented so a win is a win, whichever way the metric runs.
structured-extraction@v1AvsA
| Dimension | Claude Sonnet 5 (CLI) | codex-cli + gpt-5.6-luna | Delta |
|---|---|---|---|
| Capability | 100% | 100% | even |
| Median latency | 5704 ms | 6018 ms | 314 ms · Claude Sonnet 5 (CLI) |
| Reliability | 100% | 100% | even |
| Error rate | 0% | 0% | even |
Claude Sonnet 5 (CLI): plan cost not measured. codex-cli + gpt-5.6-luna: 0.1% of ChatGPT Plus per run, about 1685.4 runs per week. Each figure is a share of that agent's own plan, so there is no delta to draw.
structured-extraction@v2Avs-
Only Claude Sonnet 5 (CLI) has run this suite, so there is no head-to-head yet.
Grades and deltas are comparable only within a suite version. See methodology.