{
 "description": "Benchmark and capability claims for Claude Fable 5 / Mythos 5, each traceable to Anthropic's 2026-06-09 announcement. Chart URLs are Anthropic's originals.",
 "announcement": "https://www.anthropic.com/news/claude-fable-5-mythos-5",
 "overview_chart": "https://www-cdn.anthropic.com/images/4zrzovbb/website/1e65982497d7d4891219ed0e83141625a291b860-2600x2870.png",
 "claims": [
  {
   "domain": "software_engineering",
   "claim": "Stripe: 50-million-line Ruby codebase migration completed in one day (team estimate: two months)",
   "source": "announcement"
  },
  {
   "domain": "software_engineering",
   "claim": "Highest score among frontier models on Cognition FrontierCode, at medium effort",
   "chart": "https://www-cdn.anthropic.com/images/4zrzovbb/website/d3c3efe0e8ab310856368cee2b2161439db6676a-1920x1080.png",
   "chart_2": "https://www-cdn.anthropic.com/images/4zrzovbb/website/036229d8f9be9a5a911dbbd863b3c6cc09a79a70-3840x2160.png"
  },
  {
   "domain": "knowledge_work",
   "claim": "Hebbia: first model to break 90% on core analytics benchmark \u2014 a 10-point jump over Opus; highest score on Hebbia Finance Benchmark"
  },
  {
   "domain": "knowledge_work",
   "claim": "IMC: aced trading-analysis evaluations nearly across the board"
  },
  {
   "domain": "vision",
   "claim": "Completed Pokemon FireRed vision-only with a minimal harness; rebuilds web-app source from screenshots; extracts precise numbers from scientific figures"
  },
  {
   "domain": "memory_long_context",
   "claim": "With file-based memory in Slay the Spire: performance improved 3x more than Opus 4.8; reached final act 3x more often"
  },
  {
   "domain": "physics_research",
   "claim": "Notation Capital: strongest model on frontier physics research using one third of the reasoning tokens; in 36 hours reached near GPT-5.5's four-day result"
  },
  {
   "domain": "vibe_coding",
   "claim": "Vibe: highest-performing model on ViBench, nearly saturating base use cases"
  },
  {
   "domain": "mythos_drug_design",
   "claim": "Mythos 5: ~10x acceleration on aspects of drug design; 9 of 14 protein targets yielded strong candidates",
   "chart": "https://www-cdn.anthropic.com/images/4zrzovbb/website/6a97019c4d8ea13fdd7200455f6dd9e8c267ba0b-1920x1080.png"
  },
  {
   "domain": "mythos_molecular_biology",
   "claim": "Scientists preferred Mythos hypotheses over Opus-class ~80% of the time in blinded comparisons; one E. coli mechanism hypothesis corroborated independently"
  },
  {
   "domain": "mythos_genomics",
   "claim": "Week-long autonomous run: single-cell data for millions of cells across 138 species; custom model beat a recent Science publication while 100x smaller"
  },
  {
   "domain": "mythos_biology_evals",
   "claim": "Outperformed dedicated protein language models on AAV property prediction using biological reasoning alone",
   "chart": "https://www-cdn.anthropic.com/images/4zrzovbb/website/3437ad5c0853a7bd273ed5e56289a4f38dcd9731-3840x2160.png"
  }
 ],
 "safety": [
  {
   "claim": "Safeguard classifiers (cyber, bio/chem, distillation) trigger on <5% of sessions; fallback to Opus 4.8 when triggered",
   "chart": "https://www-cdn.anthropic.com/images/4zrzovbb/website/faf941fe1ebfd09139d39b8e4ad9048121979284-3840x2160.png"
  },
  {
   "claim": "No universal jailbreaks in 1,000+ external bug-bounty hours; zero compliance with harmful single-turn requests across 30 public jailbreak techniques",
   "chart": "https://www-cdn.anthropic.com/images/4zrzovbb/website/6bede3f6101d15bd899922917ea6246adda4515b-1920x1080.png"
  },
  {
   "claim": "Mythos 5 misalignment (incl. deception) measured low, similar to Opus 4.8",
   "chart": "https://www-cdn.anthropic.com/images/4zrzovbb/website/2502a0daf85b741641cff36757d7243ef48f8be8-3840x2160.png"
  }
 ],
 "last_verified": "2026-06-10",
 "version": "1.0.0",
 "dateModified": "2026-06-10"
}