Claude Fable 5.2 vs Gemini 4 Carbon.

Claude Fable 5.2 scores higher, 65 against 60, but Gemini 4 Carbon is almost 5 times cheaper per task.

Anthropic and Google
Data from 13 November 2026.

Which is better?

Claude Fable 5.2 scores higher on Artificial Analysis's Intelligence Index, 65 against 60. It is 1st of the 58 models it scores, and Gemini 4 Carbon 2nd.

On the four coding and reasoning tests, Claude Fable 5.2 wins FrontierCode 2.0, HLE Diamond and CritPt v2, and Gemini 4 Carbon wins Terminal-⁠Bench 4.0.

Per task, Gemini 4 Carbon is almost 5 times cheaper and faster too, $5.48 against $26.54 and 28.4 minutes against 46.8 minutes.

Per token, Anthropic charges $8 per million input tokens and $40 per million output tokens, and Google $2 and $10. Google raises it to $4 and $20 on 1 December. They read about the same amount at once, 1 million and 1.05 million tokens.

  • Choose Claude Fable 5.2 if

    • you want the higher score, 65 against 60
    • you want it for reasoning, it wins HLE Diamond and CritPt v2
    • you want it to change code in real projects, it scores 48.8% against 40.6% on FrontierCode 2.0
  • Choose Gemini 4 Carbon if

    • the cost of each task matters, $5.48 against $26.54
    • you want it to take less time, 28.4 minutes against 46.8 per task
    • you want it for complex work in the terminal, it scores 65.2% against 59.6% on Terminal-⁠Bench 4.0

At a glance

FigureClaude Fable 5.2AnthropicGemini 4 CarbonGoogle
ScoreArtificial Analysis's index65Better1st of 58602nd of 58
Cost per task$26.5451st of 51$5.48Better43rd of 51
Time per task46.8 min46th of 5028.4 minBetter38th of 50
Input pricePer million tokens$8$2BetterFrom 1 December, $4
Output pricePer million tokens$40$10BetterFrom 1 December, $20
Context1 million1.05 million
WeightsClosedClosed
Effort measuredEach one's highestMaxHigh
Released9 Nov 202610 Nov 2026

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

Their tests

Coding

FrontierCode 2.0 Changes to real open-⁠source projects.

  • Claude Fable 5.248.8%
  • Gemini 4 Carbon40.6%

Terminal-⁠Bench 4.0 Complex work in the terminal, on its own.

  • Claude Fable 5.259.6%
  • Gemini 4 Carbon65.2%

Reasoning

HLE Diamond Expert-⁠level questions.

  • Claude Fable 5.280.2%
  • Gemini 4 Carbon69.1%

CritPt v2, hard subset Physics research problems.

  • Claude Fable 5.276.5%
  • Gemini 4 Carbon69.0%

Questions.

  • Which one is cheaper?

    Per task, Gemini 4 Carbon, with $5.48 against $26.54 on the tasks of Artificial Analysis's index. Per token, Gemini 4 Carbon, with $2 and $10 per million input and output tokens against $8 and $40.

  • Which one reads more text at once?

    They read about the same amount at once, 1 million and 1.05 million tokens.

  • Can they run on your own servers?

    No. Neither has its weights published, so they are used through Anthropic and Google or whoever offers them.

  • 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.