Gemma 4 31B.

Among the lowest scores.

Google · Open weights · Released 2 April 2026
Data from 13 November 2026.

  • Score54th of 58

    4

    Artificial Analysis's Intelligence Index. The median is 27.

  • Cost

    No data

    Artificial Analysis does not publish it.

  • Time

    No data

    Artificial Analysis does not publish it.

  • Context43rd of 55

    262 thousand

    Tokens it reads at once, as 4 others do.

In short

It scores 4 on Artificial Analysis's Intelligence Index, 54th of the 58 models it scores. The median is 27.

Artificial Analysis does not publish what each task costs it or how long it takes.

Google does not sell it per token, and it reads up to 262 thousand tokens at once.

Its weights are published, so it can run on your own servers.

Its data

Maker
Google
Weights
Open
Effort measured
Its only one
Price per million tokens
No data
Context
262 thousand tokens
Released
2 Apr 2026

The score, the cost and the time per task and its tests from Artificial Analysis, read on 13 November 2026 at its highest effort. The price, the context and the release date from Google's page. The table of the 58.

Its tests

Coding

  • FrontierCode 2.0 Changes to real open-⁠source projects. 51st of 58.0.0%
  • Terminal-⁠Bench 4.0 Complex work in the terminal, on its own. 48th of 58.0.0%

Reasoning

  • HLE Diamond Expert-⁠level questions. 46th of 58.7.2%
  • CritPt v2, hard subset Physics research problems. 46th of 58.4.0%

Questions.

  • How much does Gemma 4 31B cost?

    Google does not sell it per token.

  • How much text does it read at once?

    Up to 262 thousand tokens, according to Google.

  • Can it run on your own servers?

    Yes. Its weights are published, so it can be downloaded and run on your own servers.

  • Which one for your company's software?

    It depends on the job. We cover it in “Which AI Model to Use to Build Your Company's Software”.

Let's talk.

Tell us what you need and one of the partners who write the code gets back to you.