Delegate substantive coding tasks when a focused agent can investigate, implement, or review with clear context. Do not delegate trivial edits or merely expedient work.
Rankings, higher = better. Cost reflects what I actually pay (OpenAI has really generous limits), not list price. Intelligence is how hard a problem you can hand the model unsupervised. Taste covers UI/UX, code quality, API design, and copy.
| model | cost | intelligence | taste |
|---|---|---|---|
| gpt-5.6 | 9 | 8 | 5 |
| sonnet-5 | 5 | 5 | 7 |
| opus-4.8 | 4 | 7 | 8 |
| fable-5 | 2 | 9 | 9 |
- Cost is a tie-breaker only; when axes conflict for anything that ships, intelligence > taste > cost.
- Bulk/mechanical work (clear-spec implementation, data analysis, migrations): gpt-5.6 - it's effectively free.
- Anything user-facing (UI, copy, API design) needs taste ≥ 7.
- Reviews of plans/implementations: fable-5 or opus-4.8, optionally gpt-5.6 as an extra independent perspective.
- Claude models (sonnet-5, opus-4.8, fable-5) run via the Agent/Workflow model parameter.
gpt-5.6 is only reachable through Codex. My ~/.codex/config.toml defaults to gpt-5.6.
Use codex:rescue for implementation or debugging help. Use codex:review for reviews. For work they don't cover (investigation, data analysis), run:
codex exec -s workspace-writeThe model parameter only takes Claude models, so use a wrapper:
model: sonnet
effort: lowPrompt the thin Claude wrapper agent to write a self-contained Codex prompt, run codex exec via Bash, and return the result.