Claude Mythos (Preview) Benchmarks, Pricing & Rankings
Anthropic · 2026-10-10 · Closed · Preview
Snapshot 2026-10-14 · updated weekly
Claude Mythos (Preview) ranks #10 of 42 on the AMR leaderboard.
Claude Mythos (Preview) benchmark scores
| GPQA Diamond | 94.1% | |
| MMLU-Pro | 90.5% | |
| SWE-Bench Verified | 79% | |
| AIME 2025 | 94.8% | |
| LiveCodeBench v6 | 82.1% |
Claude Mythos (Preview) price, speed & context
Input price
$10
per 1M tokens
Output price
$50
per 1M tokens
Speed
64
tok/s
Context
500K
tokens
About Claude Mythos (Preview)
Claude Mythos Preview is Anthropic’s next-generation frontier model shown to testers on October 10; benchmark values are provisional until the public release.
Models around Claude Mythos (Preview) in the rankings
More Anthropic models
Claude Mythos (Preview) FAQ
Where does Claude Mythos (Preview) rank?
Claude Mythos (Preview) ranks #10 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 91.0. Its strongest dimension is AIME 2025 at 94.8%.
How much does Claude Mythos (Preview) cost?
Claude Mythos (Preview) costs $10 per million input tokens and $50 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $40.00 per million tokens.
What is the Claude Mythos (Preview) context window?
Claude Mythos (Preview) supports a 500K token context window and generates at a median 64 output tokens per second. That context fits roughly 333 standard documents in a single prompt.
Is Claude Mythos (Preview) open source?
No — Claude Mythos (Preview) is a closed model available only through Anthropic’s official API and authorized cloud partners.
What is better than Claude Mythos (Preview)?
GPT-6 Sol ranks one place higher at #9 with an AMR score of 91.4. Claude Mythos (Preview) still wins 5 of the tracked dimensions head-to-head — check the comparison table to see exactly which.