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: API.
Unified ELO 2250 ± 31, rank #3 of 1776 rated models, from 57 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| 100Q-Hard Net Score | 42 | Net score (self-reported) | 100 |
| AA-Omniscience Net Score | 53 | Net score (self-reported) | 100 |
| ArxivMath (Fable/Mythos) | 78.5 | Score (%) | 100 |
| BenchLM | 83.9 | Overall Score | 100 |
| BioMysteryBench Human Difficult (Fable/Mythos) | 46.1 | Score (%) | 100 |
| BioMysteryBench Human Solvable (Fable/Mythos) | 83.9 | Score (%) | 100 |
| BioMysteryBench Human-Difficult | 46.1 | Accuracy (self-reported) | 100 |
| BioMysteryBench Human-Solvable | 83.9 | Accuracy (self-reported) | 100 |
| BrowseComp (Fable/Mythos Single-Agent) | 88 | Score (%) | 100 |
| CharXiv Reasoning (Fable/Mythos No Tools) | 88.9 | Score (%) | 100 |
| CharXiv Reasoning (Fable/Mythos Tools) | 93.5 | Score (%) | 100 |
| CharXiv-R | 93.5 | Score (self-reported) | 100 |
Interactive version: theaggregate.ai/model?slug=claude-mythos-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.