in the loop

Claude Fable 5.1
#5 of 274 scored.

AnthropicSep 1, 2026Closed

Capabilities Index

Range 161.6–168.8

164.7

Context

Takes text, image, file

1M

Input

Per 1M tokens

$10

Output

Per 1M tokens

$50

Benchmarks

How it scores.

  • FrontierMath90.2%

    4th of 81

  • ARC-AGI-290.0%

    6th of 79

  • Humanity's Last Exam43.8%

    2nd of 40

  • SimpleQA Verified70.8%

    5th of 77

  • Mock AIME100%

    1st of 176

Everything else Epoch has for it

  • ProofBench100%
  • ARC-AGI97.5%
  • DTBench96.0%
  • WeirdML92.9%
  • FrontierMath-Tier-4-v2-Private87.8%
  • LMCA77.0%
  • MirrorCode73.3%
  • APEX-Agents68.6%
  • EBR-bench57.1%
  • Furniture Assembly57.1%
  • FrontierSWE56.3%
  • Mystery Game Puzzles53.7%
  • FrontierCode50.9%
  • Chess Puzzles44.2%
  • Remote Labor Index17.9%

On the index

Around it.

  1. #2GPT-6 AstraOpenAI · $10 in166.4
  2. #3GPT-6.1 SolOpenAI · $2.00 in166.1
  3. #4Claude Sonnet 5.5Anthropic · $2.00 in165.0
  4. #5Claude Fable 5.1Anthropic · $10 in164.7
  5. #6Claude Opus 5Anthropic · $5.00 in162.8
  6. #7GPT-6 SolOpenAI · $2.00 in162.7
  7. #8GPT-5.5 ProOpenAI · $30 in162.1

Sources