ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Gemini 3.5 Flash vs Gemini 3.7 Flash

Gemini 3.7 Flash comes out ahead, 75 to 69 on our weighted score, and it is the cheaper option too.

  1. Google

    Gemini 3.5 Flash

    Released May 19, 2026

    69/100
    • ECI154.5
    • Price$1.50 / $9.00
    • Context1.05M
    Full specs Remove Gemini 3.5 Flash
  2. Our pick

    Google

    Gemini 3.7 Flash

    Released Aug 13, 2026

    75/100
    • ECI157.4
    • Price$0.75 / $3.75
    • Context1.05M
    Full specs Remove Gemini 3.7 Flash

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Gemini 3.7 Flash is our pick

Gemini 3.7 Flash is the better all-round choice, scoring 75/100 against Gemini 3.5 Flash (69). It leads on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGemini 3.7 FlashCapabilities Index (ECI): Gemini 3.7 Flash 157.4 · Gemini 3.5 Flash 154.5
  • Lowest priceGemini 3.7 FlashGemini 3.7 Flash $1.50 · Gemini 3.5 Flash $3.38 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameGemini 3.5 Flash 1,048,576 · Gemini 3.7 Flash 1,048,576 tokens
  • Widest inputsSame inputsGemini 3.5 Flash: Text, Images, PDFs, Audio, Video · Gemini 3.7 Flash: Text, Images, PDFs, Audio, Video
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightGemini 3.5 FlashGemini 3.7 Flash
CapabilityCapabilities Index (ECI)50%8488
Price25%2542
Inputs & features15%100100
Context window10%6161
Overall100%69/10075/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Gemini 3.5 Flash vs Gemini 3.7 Flash specifications side by side
SpecificationGemini 3.5 FlashGoogleGemini 3.7 FlashGoogle
Capability
Capabilities Index (ECI)154.5157.4 (best)
ECI rank#33 of 148#14 of 148 (best)
GPQA DiamondGraduate-level science questions92.8%94.8% (best)
FrontierMath Tiers 1–3Research-level mathematics62.8%71.6% (best)
OTIS Mock AIME 2024–2025Competition mathematics95.6%97.2% (best)
SWE-bench VerifiedFixing real GitHub issues79.3%—
SimpleQA VerifiedShort factual questions66.2%69.2% (best)
Price per million tokens
Input$1.50$0.75 (best)
Output$9.00$3.75 (best)
Cached input$0.15$0.075 (best)
Blended (3:1)$3.38$1.50 (best)
Long-context rateSame rateSame rate
Price sourceOfficial Google APIOfficial Google API
Limits
Context window1,048,576 tokens1,048,576 tokens
Max output65,536 tokens65,536 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsYesYes
AudioYesYes
VideoYesYes
ReasoningYesminimal · low · medium · highYeslow · medium · high
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model IDgemini-3.5-flashgemini-3.7-flash
API providers32 (best)24
ReleasedMay 19, 2026Aug 13, 2026
Knowledge cutoffJan 2025Mar 2026
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Gemini 3.5 Flash$33.00
  • Gemini 3.7 Flash$15.00
04 — Questions

Which should you choose?

Which is better: Gemini 3.5 Flash or Gemini 3.7 Flash?

Gemini 3.7 Flash is the better all-round choice, scoring 75/100 against Gemini 3.5 Flash (69). It leads on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Gemini 3.5 Flash or Gemini 3.7 Flash?

Gemini 3.7 Flash is cheaper at $0.75 input / $3.75 output per million tokens (official Google API price). Gemini 3.5 Flash costs $1.50 input / $9.00 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $1.50 per million tokens for Gemini 3.7 Flash versus $3.38 for Gemini 3.5 Flash (2.3× as much).

Which scores higher on benchmarks?

Gemini 3.7 Flash scores higher on the Capabilities Index (ECI): Gemini 3.7 Flash 157.4 (#14 of 148) and Gemini 3.5 Flash 154.5 (#33 of 148). The confidence ranges of the top two overlap (155.4–160.1 vs 152.5–156.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3.7 Flash 94.8%, Gemini 3.5 Flash 92.8%; FrontierMath Tiers 1–3 — Gemini 3.7 Flash 71.6%, Gemini 3.5 Flash 62.8%; OTIS Mock AIME 2024–2025 — Gemini 3.7 Flash 97.2%, Gemini 3.5 Flash 95.6%; SimpleQA Verified — Gemini 3.7 Flash 69.2%, Gemini 3.5 Flash 66.2%.

Which is better for coding?

There are no published SWE-bench Verified results for Gemini 3.7 Flash yet, so there is no like-for-like coding score. On overall capability, Gemini 3.7 Flash leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

Gemini 3.5 Flash and Gemini 3.7 Flash share the same 1,048,576-token context window. Maximum output per response: Gemini 3.5 Flash up to 65,536, Gemini 3.7 Flash up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Gemini 3.5 Flash accepts text, images, PDFs, audio and video; Gemini 3.7 Flash accepts text, images, PDFs, audio and video. They handle the same number of input types.

Are any of these open source?

No. Gemini 3.5 Flash and Gemini 3.7 Flash are proprietary and only available through APIs and apps.

Which is newer?

Gemini 3.7 Flash is the newest, released Aug 13, 2026. Gemini 3.5 Flash came out May 19, 2026. Knowledge cutoff: Gemini 3.5 Flash Jan 2025, Gemini 3.7 Flash Mar 2026.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons