Model vs model

Gemini 3.8 Flash vs GPT-6 Luna

Free to try, no account needed. You see each answer’s cost and speed.

At a glance

Longer bar means the bigger number.

Open or closed · can you download the model and run it yourself?

Gemini 3.8 FlashClosed · only through Google’s API or a cloud that resells it
GPT-6 LunaClosed · only through OpenAI’s API or a cloud that resells it

Blended price · per 1M tokens, lower is better

Gemini 3.8 Flash$1.50
GPT-6 Luna$0.20

Intelligence Index · Artificial Analysis, higher is better

Gemini 3.8 Flash40.9
GPT-6 Luna38.1

Where they sit among all 47 models

Gemini 3.8 Flash ranks 11th of the 38 models with an Intelligence Index, GPT-6 Luna 15th. Up and to the left is smarter for less money. Hover or tap a dot for its numbers, then click it to compare that model with Gemini 3.8 Flash.

Show
Rank by
Intelligence: the Artificial Analysis Intelligence Index. Price: blended per 1M tokens, 3 parts input to 1 part output. Lines at $2 blended and the median score (38.1). The dashed line joins the best value models: nothing cheaper scores higher.

Which one to pick

Pick Gemini 3.8 Flash if

  • you want the higher overall score (40.9 vs 38.1)
  • you care about Humanity's Last Exam (hard reasoning): 47.8 vs 38.5
  • you care about Terminal-Bench 4.0 (terminal tasks): 19.7 vs 12.6
  • you need to send video and audio

Pick GPT-6 Luna if

  • you want the lower bill ($0.20 vs $1.50 per 1M tokens blended)

See how they answer your prompt

Same prompt, both models

We send the same short tests to every model several times. These are the ones where Gemini 3.8 Flash and GPT-6 Luna answered differently, from our run on October 18, 2026. Long answers are cut short.

Best AI model

“Which AI model is the best right now? Reply with one model name only.”

Gemini 3.8 Flash

“claude 35 sonnet” 2 of 3 times

Claude 3.5 Sonnet

$0.0014 · 3.9s

GPT-6 Luna

3 different answers in 3 tries

GPT-4.1

$0.0001 · 3.0s

Name a smart-umbrella startup

“Invent a name for a startup that sells smart umbrellas. Reply with the name only.”

Gemini 3.8 Flash

“pluvio” 2 of 5 times

Pluvio

$0.0034 · 8.2s

GPT-6 Luna

“nimbusiq” 4 of 5 times

NimbusIQ

under $0.0001 · 1.0s

Run your own test on both

Asked to draw the same picture

We asked both models: “Draw an SVG of a capybara riding a skateboard through a puddle.” They had to answer with SVG code alone, with no image tools.

Gemini 3.8 Flash's SVG drawing of a capybara riding a skateboard through a puddle

Gemini 3.8 Flash

GPT-6 Luna's SVG drawing of a capybara riding a skateboard through a puddle

GPT-6 Luna

Each model’s first drawing, exactly as it wrote the SVG. Nothing was picked or retouched.

Ask both for your own drawing

How smart is each one?

Of the 16 scores both models have, Gemini 3.8 Flash is ahead on 12 and GPT-6 Luna on 3, and one is within a point.

Every intelligence score we have

Out of 100, higher is better. Gemini 3.8 Flash GPT-6 Luna

Overall

  • Intelligence Index

By area

  • Coding

    GPT-6 Luna: not scored yet

  • Agentic work

    GPT-6 Luna: not scored yet

By field of work

  • Finance & accounting

  • Legal

  • Healthcare & medicine

  • Economics

  • Engineering

  • Strategy & operations

Benchmarks

  • Factual knowledge · SimpleQA

  • Hard reasoning · Humanity's Last Exam

  • Science · GPQA Diamond

    GPT-6 Luna: not scored yet

  • Competition math · OTIS Mock AIME

  • Research math · FrontierMath

  • Scientific coding · SciCode

  • Coding in Cursor · CursorBench 4.0

    GPT-6 Luna: not scored yet

  • Mergeable code · FrontierCode 2.0

    Gemini 3.8 Flash: not scored yet

  • Terminal tasks · Terminal-Bench 4.0

  • Tool use · τ-Bench Banking

    GPT-6 Luna: not scored yet

  • Long documents · AA-LCR

  • Uncensored · UGI

    GPT-6 Luna: not scored yet

Our tests

  • Hallucination test · our test, higher means it made up less

  • Next.js coding tasks · Vercel's Next.js evals, % of tasks passed

Test them on your own question

The specs

Spec Gemini 3.8 Flash GPT-6 Luna
Input price$0.75 per 1M$0.10 per 1M
Output price$3.75 per 1M$0.50 per 1M
Cost per test task$1.24$0.0678
Context window1.05M1.05M
Max output66K128K
AcceptsText, Image, Video, Audio, PDFText, Image, PDF
Open weightsNoNo
LabGoogleOpenAI
ReleasedSep 2026Sep 2026
Knowledge cutoffNot publishedMay 2026

Blended price weighs 3 parts input to 1 part output. List prices from models.dev. Cost per test task from Artificial Analysis.

Questions

Is Gemini 3.8 Flash or GPT-6 Luna cheaper?

GPT-6 Luna is cheaper. It charges $0.10 per 1M input tokens and $0.50 per 1M output tokens, against $0.75 and $3.75 for Gemini 3.8 Flash. Blended 3 parts input to 1 part output, that is $0.20 against $1.50 per 1M tokens.

Are Gemini 3.8 Flash and GPT-6 Luna open source?

No. Both are closed models: the weights aren't published, so you can only use them through an API, from Google and OpenAI or a cloud that resells them.

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

Gemini 3.8 Flash scores higher on the Artificial Analysis Intelligence Index, 40.9 against 38.1 for GPT-6 Luna. The biggest differences are on Humanity's Last Exam (47.8 vs 38.5) and Terminal-Bench 4.0 (19.7 vs 12.6).

Which has the longer context window?

Both accept about 1.05M tokens.

Can I compare Gemini 3.8 Flash and GPT-6 Luna on my own prompt?

Yes. ModelCompare sends one prompt to both models at once and shows each answer side by side with what it cost. You can try it free without an account.

Still deciding? Send one prompt to both and read the answers side by side, with what each one cost. Compare Gemini 3.8 Flash and GPT-6 Luna →

Where the numbers come from

Intelligence Index and benchmark scores are from Artificial Analysis, at each model’s highest effort, except the Epoch Capabilities Index, SimpleQA, OTIS Mock AIME and FrontierMath, which are from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard, and CursorBench, which is from Cursor, and FrontierCode, which is from Cognition at each model’s best-scoring effort. The hallucination test is ours: questions with one exact answer, fake evidence pushed against right answers and requests that tempt a model to name packages that don’t exist. Prices are list prices from models.dev. Example answers come from our own test runs. Updated November 18, 2026.