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

gemini-2.5-flash vs gemini-3.7-flash for classification

the measured answer

As of August 24, 2026, gemini-3.7-flash measures 1.000 on classification vs 0.988 for gemini-2.5-flash (+0.012), at 13.2× the price ($0.3580 vs $0.0270 per 1K requests).

same suite, same items, same scoring — frontier v5, measured 2026-08-24 · method

modelvendormeasured quality$ / 1K requestsp95 latency
gemini-2.5-flashgoogle0.988$0.02701080 ms
gemini-3.7-flashgoogle1.000$0.35803367 ms

Classification — routing tickets, labeling intents, applying rules to text — is the workload where model choice matters most and is judged least. The task has a right answer, so quality is measurable exactly, and the measured gap between the cheapest adequate model and a frontier model is routinely the widest of any workload. Paying frontier prices here is the most common form of silent AI overspend.

These two are part of a larger measured frontier — what is the best model for text classification 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.

gemini-2.5-flash vs gemini-3.7-flash for classification — measured · Frontier Notes