ModelCompare
Compare

Model vs model

Gemma 4 26B A4B IT vs Gemma 4 31B IT

By ModelCompare ·

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?

Gemma 4 26B A4B ITOpen weights · download it, run it on your own hardware or any host
Gemma 4 31B ITOpen weights · download it, run it on your own hardware or any host

Blended price · per 1M tokens, lower is better

Gemma 4 26B A4B IT$0.26
Gemma 4 31B IT$0.21

Intelligence Index · Artificial Analysis, higher is better

Gemma 4 26B A4B IT16.7
Gemma 4 31B IT14.7

Where they sit among all 44 models

Gemma 4 26B A4B IT ranks 34th of the 43 models with an Intelligence Index, Gemma 4 31B IT 35th. 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 Gemma 4 26B A4B IT.

Show
Rank by
Intelligence: the Artificial Analysis Intelligence Index. Price: blended per 1M tokens, 3 parts input to 1 part output, on a log scale.

Which one to pick

Pick Gemma 4 26B A4B IT if

  • you want the higher overall score (16.7 vs 14.7)

Pick Gemma 4 31B IT if

  • you want the lower bill ($0.21 vs $0.26 per 1M tokens blended)
  • you care about GPQA Diamond (science): 85.7 vs 79.2
  • you care about SciCode (scientific coding): 45.5 vs 40

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 Gemma 4 26B A4B IT and Gemma 4 31B IT answered differently, from our runs on October 18, 2026 and October 25, 2026. Long answers are cut short.

Name a smart-umbrella startup

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

Gemma 4 26B A4B IT

“skyguard” 5 of 5 times

SkyGuard

under $0.0001 · 0.4s

Gemma 4 31B IT

“ombrella” 2 of 5 times

Ombrella

under $0.0001 · 0.9s

Three bullets, no letter e

“Give three tips for sleeping better. Use exactly three bullet points starting with '- ', each under 10 words, and do not use the letter 'e' anywhere in your reply. Reply with the bullets only.”

Gemma 4 26B A4B IT

Followed both rules 3 of 3 times · this answer ok

- Avoid drugs. - Nap not. - Stay calm.

under $0.0001 · 1.5s

Gemma 4 31B IT

Followed both rules 2 of 3 times · this answer used e

- Stop caffeine. - Dim light. - No naps.

under $0.0001 · 9.5s

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.

Gemma 4 26B A4B IT's SVG drawing of a capybara riding a skateboard through a puddle

Gemma 4 26B A4B IT

Gemma 4 31B IT's SVG drawing of a capybara riding a skateboard through a puddle

Gemma 4 31B IT

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 11 scores both models have, Gemma 4 31B IT is ahead on 9 and Gemma 4 26B A4B IT on 1, and one is within a point.

Every intelligence score we have

Out of 100, higher is better. Gemma 4 26B A4B IT Gemma 4 31B IT

Overall

  • Intelligence Index

By area

  • Coding

  • Agentic work

By field of work

  • Finance & accounting

    Gemma 4 26B A4B IT: not scored yet

  • Legal

    Gemma 4 26B A4B IT: not scored yet

  • Economics

  • Engineering

    Gemma 4 26B A4B IT: not scored yet

  • Strategy & operations

    Gemma 4 26B A4B IT: not scored yet

Benchmarks

  • Factual knowledge · SimpleQA

    Gemma 4 26B A4B IT: not scored yet

  • Hard reasoning · Humanity's Last Exam

  • Science · GPQA Diamond

  • Scientific coding · SciCode

  • Terminal tasks · Terminal-Bench 4.0

    Gemma 4 26B A4B IT: not scored yet

  • Tool use · τ-Bench Banking

  • Instruction following · IFBench

  • Long documents · AA-LCR

  • Uncensored · UGI

Test them on your own question

The specs

Spec Gemma 4 26B A4B IT Gemma 4 31B IT
Input price$0.15 per 1M$0.14 per 1M
Output price$0.60 per 1M$0.40 per 1M
Cost per test taskNot testedNot tested
Context window262K262K
Max output131K131K
AcceptsText, Image, PDFText, Image, PDF
Open weightsYesYes
LabGoogleGoogle
ReleasedApr 2026Apr 2026
Knowledge cutoffNot publishedJan 2025

Blended price weighs 3 parts input to 1 part output. List prices from models.dev.

Questions

Is Gemma 4 26B A4B IT or Gemma 4 31B IT cheaper?

Gemma 4 31B IT is cheaper. It charges $0.14 per 1M input tokens and $0.40 per 1M output tokens, against $0.15 and $0.60 for Gemma 4 26B A4B IT. Blended 3 parts input to 1 part output, that is $0.21 against $0.26 per 1M tokens.

Are Gemma 4 26B A4B IT and Gemma 4 31B IT open source?

Both are open-weights models: Google publishes the weights, so you can download them and run them on your own hardware, or call them through any host's API. Check each model's license before you ship it.

Which is smarter, Gemma 4 26B A4B IT or Gemma 4 31B IT?

Gemma 4 26B A4B IT scores higher on the Artificial Analysis Intelligence Index, 16.7 against 14.7 for Gemma 4 31B IT. The biggest differences are on GPQA Diamond (79.2 vs 85.7) and SciCode (40 vs 45.5).

Which has the longer context window?

Both accept 262K tokens.

Can I compare Gemma 4 26B A4B IT and Gemma 4 31B IT 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 Gemma 4 26B A4B IT and Gemma 4 31B IT →

Where the numbers come from

Intelligence Index and benchmark scores are from Artificial Analysis, at each model’s highest effort, except SimpleQA, which is from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard. 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 October 26, 2026.