gemini-3.7-flash vs gpt-5.6-luna for tool calling
As of September 8, 2026, gpt-5.6-luna measures 0.979 on agentic tool use vs 0.915 for gemini-3.7-flash (+0.064), and it is also the cheaper option ($0.8768 vs $3.58 per 1K requests).
same suite, same items, same scoring — frontier v5, measured 2026-09-08 · method
| model | vendor | measured quality | $ / 1K requests | p95 latency |
|---|---|---|---|---|
| gemini-3.7-flash | 0.915 | $3.58 | 11236 ms | |
| gpt-5.6-luna | openai | 0.979 | $0.8768 | 14859 ms |
Agent stacks live or die on tool calls: the right function, the right arguments, the discipline not to invent either. The measured suite scores tool-call validity deterministically. Whole-journey agent completion — plan, call, read, recover — is measured separately, because call-level scores can all look healthy while the journey fails.
These two are part of a larger measured frontier — what is the best model for tool calling 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.
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.