Claude Mythos 5: benchmark results

Anthropic Claude Mythos 5 model for high-end reasoning, coding, agentic, and professional tasks. Provider: Anthropic. Released 2026-06-09. Access: Private.

Unified ELO 1800 ± 1, rank #5 of 1392 rated models, from 53 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
100Q-Hard Net Score42Net score (self-reported)100
AA-Omniscience Net Score58Net score (self-reported)100
ArxivMath (Fable/Mythos)78.5Score (%)100
BenchmarkList ECI161.31Capability Index (ECI)100
BioMysteryBench Human Difficult (Fable/Mythos)46.1Score (%)100
BioMysteryBench Human Solvable (Fable/Mythos)83.9Score (%)100
BrowseComp (Fable/Mythos Single-Agent)88Score (%)100
CharXiv Reasoning (Fable/Mythos No Tools)88.9Score (%)100
CharXiv Reasoning (Fable/Mythos Tools)93.5Score (%)100
CyScenarioBench36.7Average Success Rate (%)100
DRACO86.4Score (%)100
FigQA90.7Score (self-reported)100

Interactive version: theaggregate.ai/model?slug=claude-mythos-5 · How It Works · Data refreshed daily, snapshot 2026-09-05.