Code generation: a model at 1/271st the price of the best scorer, at 97.8% of its quality.

gpt-4.1 vs gpt-4.1-mini for code review

the measured answer

As of August 24, 2026, gpt-4.1 measures 0.972 on code review vs 0.909 for gpt-4.1-mini (+0.063), at 6.8× the price ($3.07 vs $0.4532 per 1K requests).

same suite, same items, same scoring — frontier v4, measured 2026-08-24 · method

modelvendormeasured quality$ / 1K requestsp95 latency
gpt-4.1openai0.972$3.074656 ms
gpt-4.1-miniopenai0.909$0.45325100 ms

Code review asks a model to find what is wrong with working-looking code — a fundamentally harder measurement problem than generation, because a review is only as good as the defects it catches. The measured suite scores reviews against known injected defects with executable checks wherever the fix can be run.

These two are part of a larger measured frontier — what is the best model for code review shows every measured option for this workload, and other workloads rank these models differently: a model that wins here can lose on another kind of work, which is the whole argument for routing per workload rather than picking one model for everything.

the routed alternative

Potion routes each request to the cheapest option measured at your quality bar — including picks this public page does not name. Get an API key or read the docs.

gpt-4.1 vs gpt-4.1-mini for code review — measured · Frontier Notes