invokeable()
← directory / models / gemini-3.7-flash

Gemini 3.7 Flash

model gemini-3.7-flash

Draft entry — numbers not yet verified against primary sources.

1M
context
66K
max output
—
input
—
output
2026-03
knowledge cutoff
1
providers

01Providers

ProviderProvider model IDIn $/MOut $/MContextStatus
Gemini API (AI Studio) gemini-3.7-flash — — 1M live

02Invoke

provider
language

  

  



03Benchmarks · vendor-reported unless verified
FrontierCode (score) score43.6




DeepSWE resolve rate65.3%




Terminal-Bench (accuracy) accuracy85.8




AutomationBench (accuracy) accuracy · private set30.4




GDP.pdf (accuracy) accuracy34




GDM-MRCR (accuracy) accuracy97




04Related
Gemini 3.5 Flash Lite2026-07Gemini 3.6 Flash2026-07Nano Banana 2 Lite2026-06Gemini 3.5 Live Translate Preview2026-06Gemini 3.5 Flash2026-05Gemini 3.1 Flash Live Preview2026-03


05Compare
vs GPT-5.6 Lunahead-to-headvs Qwen3.8 27Bhead-to-headvs Mistral Medium 3.5head-to-headvs Claude Opus 5head-to-headvs Nemotron 3.5 Lightning 30B A3Bhead-to-headvs GLM-5.3head-to-headvs North Mini Codehead-to-headvs Gemini 3.5 Flash Litehead-to-head


06Sources · where these numbers come from
  1. https://github.com/sst/models.dev
  2. https://ai.google.dev/gemini-api/docs/models
  3. https://blog.google/technology/google-deepmind/
  4. https://ai.google.dev/gemini-api/docs