Research / August 22, 2026

Codex CLI cross-file navigation benchmark

A paired, end-to-end comparison on an anonymized 553-source-file TypeScript repository. This measured complete Codex CLI sessions—not estimated payload sizes.

Result

MetricCodex CLI aloneWith SpeederDifference
Average input tokens153,323100,59934.4% fewer
Average completion time50.8 seconds41.1 seconds19.0% faster
Total output tokens7,3805,33427.7% fewer
Tool calls201430.0% fewer
Quality pass rate3 / 33 / 3Equal

Across all three pairs, provider-reported input tokens fell from 459,970 to 301,798. Wall time fell from 152.302 to 123.421 seconds.

Method

Quality gate

The task required planning a rejected-RPC error-handling change in a shared function. A passing answer had to identify the implementation symbol, all six direct callers, focused test coverage, and the risk boundary around the RPC call. All six sessions passed.

Limitations

This supports a scoped claim for cross-file TypeScript navigation. It does not establish universal token, latency, or cost savings. Input tokens include cached input, which may be priced differently. Small tasks with an already-known file or assertion can be faster without structural discovery and should bypass Speeder.

Data integrity

Aggregate and per-run values are retained with the product's benchmark records. Session logs and repository source are excluded to avoid publishing prompts, local paths, or unrelated project context.