AI ScoreboardFrontend & Coding Index← Back to rankings

MODEL PROFILE / EDITION 2026.09

Gemini 3.7 Flash

Interactive UI iteration and design exploration where wall-clock speed matters most

GoogleRank 12Confidence BNo prior snapshot
78.2

Balanced model evidence score; rank 12. No rank delta is shown because there is no prior numeric snapshot.

Best for

Interactive UI iteration and design exploration where wall-clock speed matters most

Price & access

Standard $0.75 in / $3.75 out per 1M through Dec 31, 2026, then $1.50/$7.50; Batch and Flex $0.375/$1.875; Priority $1.35/$6.75; introductory pricing noted in the changelog

Evidence summary

GA date, price and lifecycle are first-party; speed and context come from Artificial Analysis; both preference boards list it. Weak point is the complete absence of a software-engineering benchmark row.

Edition status

No prior snapshot. Tracked in the September 2026 baseline.

Strengths

  • Fastest measured output in the whole 30-model set (309.2 tok/s)
  • Design Arena Website 1317 is joint 6th, ahead of GLM-5.2 and Grok 4.6
  • Beats the newer 3.8 Flash on Arena WebDev Frontend (1592 vs 1569) with more votes
  • Same $0.75/$3.75 promo price and free tier as 3.8 Flash

Tradeoffs

  • No SWE-bench Pro/Verified or LiveCodeBench evidence found
  • Superseded by 3.8 Flash in Google's own lineup
  • Google does not publish context, max output or modalities for it
  • AA Intelligence 45 is mid-pack

Score profile

visual 76 · code 71 · agentic 71 · debug 70 · context 86 · speed 96 · value 92

Linked evidence

Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗Evidence source 6 ↗
Compare this model on the full scoreboard

Use the same published data, filters, and side-by-side metrics.

Open comparison view →