Gemini 3.7 Flash (high) scores 56 at about 340 tokens/s and 1.7 minutes per task, and costs 30% less per task at Google's discounted pricing through year end.
Key takeaways · AI-distilled
Artificial Analysis measured Gemini 3.7 Flash at three reasoning levels. High reasoning scored 56 on its Intelligence Index and averaged 1.7 minutes per task; medium and low reasoning scored 53 and 51.
Gemini 3.7 Flash's reported $0.40 cost per task at high reasoning uses Google's discounted tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → prices through the end of 2026. The listed standard prices are twice those rates.
Gemini 3.7 Flash's agentic gains vary by evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition →. Artificial Analysis reports 60% pass^5 on AA-AnalystAgent and 62.7% on AutomationBench-AA, alongside a 103-point Elo increase over its predecessor on GDPval-AA v2.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
