Oriel — AI & technology worth noticing, every day.

Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far

Web page · https://artificialanalysis.ai/models/claude-fable-5-2

First seen by Oriel on .

AI summary

The page analyzes Claude Fable 5.2 (max) across Artificial Analysis’s intelligence, capability, token-use, cost, context-window, and performance metrics, but the extracted text provides definitions rather than model-specific results.

  • Artificial Analysis Intelligence Index v5.0.1 combines nine evaluations, including AA-Briefcase v1.1, AutomationBench-AA, FrontierCode 2.0, and Terminal-Bench 4.0.
  • The index measures knowledge work, software engineering, document reasoning, legal work, scientific research, hallucination, and other specialized capabilities.
  • Weighted task cost incorporates input, cache hit, cache write, reasoning, and answer token prices, while output-token usage is weighted across benchmark tasks.
  • Performance metrics include time per task, output speed, time to first answer token, and time to first token, using endpoint measurements collected over five days.

#llm evaluation #model pricing #model performance #benchmarks

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hacker News: 370, latest observation ; +356 over observed period since

Comments

Comment count reported by the source.

  • Hacker News: 267, latest observation ; +263 over observed period since

Aliases

SourceExternal IDURL
Hacker News50431144https://artificialanalysis.ai/models/claude-fable-5-2 Read discussion