Claude Fable 5.2 vs Grok 4.7.

Claude Fable 5.2 scores higher, 65 against 35, but Grok 4.7 is more than 3 times cheaper per task.

Anthropic and xAI
Data from 13 November 2026.

Which is better?

Claude Fable 5.2 scores higher on Artificial Analysis's Intelligence Index, 65 against 35. It is 1st of the 58 models it scores, and Grok 4.7 15th.

Claude Fable 5.2 wins all four coding and reasoning tests.

Per task, Grok 4.7 is more than 3 times cheaper and faster too, $7.77 against $26.54 and 27.0 minutes against 46.8 minutes.

Per token, Anthropic charges $8 per million input tokens and $40 per million output tokens, and xAI $2 and $6. Claude Fable 5.2 reads more text at once, up to 1 million tokens against 500 thousand.

  • Choose Claude Fable 5.2 if

    • you want the higher score, 65 against 35
    • you want it for coding, it wins FrontierCode 2.0 and Terminal-⁠Bench 4.0
    • you want it for reasoning, it wins HLE Diamond and CritPt v2
  • Choose Grok 4.7 if

    • the cost of each task matters, $7.77 against $26.54
    • you want it to take less time, 27.0 minutes against 46.8 per task

At a glance

FigureClaude Fable 5.2AnthropicGrok 4.7xAI
ScoreArtificial Analysis's index65Better1st of 583515th of 58
Cost per task$26.5451st of 51$7.77Better46th of 51
Time per task46.8 min46th of 5027.0 minBetter36th of 50
Input pricePer million tokens$8$2Better
Output pricePer million tokens$40$6Better
Context1 millionBetter500 thousand
WeightsClosedClosed
Effort measuredEach one's highestMaxExtra high
Released9 Nov 202621 Sept 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 xAI's pages. The table of the 58.

Their tests

Coding

FrontierCode 2.0 Changes to real open-⁠source projects.

  • Claude Fable 5.248.8%
  • Grok 4.728.7%

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

  • Claude Fable 5.259.6%
  • Grok 4.725.8%

Reasoning

HLE Diamond Expert-⁠level questions.

  • Claude Fable 5.280.2%
  • Grok 4.723.2%

CritPt v2, hard subset Physics research problems.

  • Claude Fable 5.276.5%
  • Grok 4.733.5%

Questions.

  • Which one is cheaper?

    Per task, Grok 4.7, with $7.77 against $26.54 on the tasks of Artificial Analysis's index. Per token, Grok 4.7, with $2 and $6 per million input and output tokens against $8 and $40.

  • Which one reads more text at once?

    Claude Fable 5.2 reads more text at once, up to 1 million tokens against 500 thousand.

  • Can they run on your own servers?

    No. Neither has its weights published, so they are used through Anthropic and xAI 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.