ZMIME
Comparison · 2 models · Updated Oct 4, 2026

GPT-6 Luna vs Gemini 3.8 Flash

GPT-6 Luna comes out ahead, 78 to 73 on our weighted score, and it is the cheaper option too.

  1. Our pick

    OpenAI

    GPT-6 Luna

    Released Sep 22, 2026

    78/100
    • ECI—
    • Price$0.10 / $0.50
    • Context1.05M
    Full specs Remove GPT-6 Luna

  2. Google

    Gemini 3.8 Flash

    Released Sep 2, 2026

    73/100
    • ECI156.9
    • Price$0.75 / $3.75
    • Context1.05M
    Full specs Remove Gemini 3.8 Flash

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

GPT-6 Luna is our pick

GPT-6 Luna is the better all-round choice, scoring 78/100 against Gemini 3.8 Flash (73). It leads on price. Gemini 3.8 Flash wins on capability and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified), because GPT-6 Luna has no Capabilities Index score yet.

  • CapabilityGemini 3.8 FlashShared benchmarks: Gemini 3.8 Flash 83.1% · GPT-6 Luna 77.4%
  • Lowest priceGPT-6 LunaGPT-6 Luna $0.20 · Gemini 3.8 Flash $1.50 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameGPT-6 Luna 1,050,000 · Gemini 3.8 Flash 1,048,576 tokens
  • Widest inputsGemini 3.8 FlashGPT-6 Luna: Text, Images, PDFs · Gemini 3.8 Flash: Text, Images, PDFs, Audio, Video
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightGPT-6 LunaGemini 3.8 Flash
CapabilityShared benchmarks50%7783
Price25%8342
Inputs & features15%80100
Context window10%6161
Overall100%78/10073/100
02 — Side by side

Every spec in one table

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

GPT-6 Luna vs Gemini 3.8 Flash specifications side by side
SpecificationGPT-6 LunaOpenAIGemini 3.8 FlashGoogle
Capability
Capabilities Index (ECI)—156.9
ECI rank—#15 of 148
GPQA DiamondGraduate-level science questions90.5%95.4% (best)
FrontierMath Tiers 1–3Research-level mathematics79.0% (best)68.4%
OTIS Mock AIME 2024–2025Competition mathematics98.9%98.9%
SimpleQA VerifiedShort factual questions41.4%69.7% (best)
Price per million tokens
Input$0.10 (best)$0.75
Output$0.50 (best)$3.75
Cached input$0.01 (best)$0.075
Blended (3:1)$0.20 (best)$1.50
Long-context rateOver 272K: $0.20 / $0.75Same rate
Price sourceOfficial OpenAI APIOfficial Google API
Limits
Context window1,050,000 tokens (best)1,048,576 tokens
Max output128,000 tokens (best)65,536 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsYesYes
AudioNoYes
VideoNoYes
ReasoningYeslow · medium · high · xhigh · maxYeslow · medium · high
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model IDgpt-6-lunagemini-3.8-flash
API providers24 (best)21
ReleasedSep 22, 2026Sep 2, 2026
Knowledge cutoffMay 18, 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.

  • GPT-6 Luna$2.00
  • Gemini 3.8 Flash$15.00
04 — Questions

Which should you choose?

Which is better: GPT-6 Luna or Gemini 3.8 Flash?

GPT-6 Luna is the better all-round choice, scoring 78/100 against Gemini 3.8 Flash (73). It leads on price. Gemini 3.8 Flash wins on capability and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified), because GPT-6 Luna has no Capabilities Index score yet.

Which is cheaper, GPT-6 Luna or Gemini 3.8 Flash?

GPT-6 Luna is cheaper at $0.10 input / $0.50 output per million tokens (official OpenAI API price). Gemini 3.8 Flash costs $0.75 input / $3.75 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for GPT-6 Luna versus $1.50 for Gemini 3.8 Flash (7.5× as much).

Which scores higher on benchmarks?

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond, FrontierMath Tiers 1–3, OTIS Mock AIME 2024–2025 and SimpleQA Verified): Gemini 3.8 Flash 83.1% and GPT-6 Luna 77.4%. On individual benchmarks: GPQA Diamond — Gemini 3.8 Flash 95.4%, GPT-6 Luna 90.5%; FrontierMath Tiers 1–3 — GPT-6 Luna 79.0%, Gemini 3.8 Flash 68.4%; OTIS Mock AIME 2024–2025 — GPT-6 Luna 98.9%, Gemini 3.8 Flash 98.9%; SimpleQA Verified — Gemini 3.8 Flash 69.7%, GPT-6 Luna 41.4%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-6 Luna and Gemini 3.8 Flash yet, so there is no like-for-like coding score. On overall capability, Gemini 3.8 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?

Their context windows are effectively the same size: GPT-6 Luna 1,050,000 and Gemini 3.8 Flash 1,048,576 tokens. Maximum output per response: GPT-6 Luna up to 128,000, Gemini 3.8 Flash up to 65,536 tokens.

Which can read images, PDFs, audio or video?

GPT-6 Luna accepts text, images and PDFs; Gemini 3.8 Flash accepts text, images, PDFs, audio and video. Gemini 3.8 Flash handles the widest range of inputs.

Are any of these open source?

No. GPT-6 Luna and Gemini 3.8 Flash are proprietary and only available through APIs and apps.

Which is newer?

GPT-6 Luna is the newest, released Sep 22, 2026. Gemini 3.8 Flash came out Sep 2, 2026. Knowledge cutoff: GPT-6 Luna May 18, 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