The AI arena is free today

Open Superagent
AnthropicReleased on Apr 7, 2026

Claude Mythos Preview: Benchmarks, Pricing & Context Window

Claude Mythos Preview is a language model from Anthropic, released in April 2026, with multimodal input.

Claude Mythos Preview is an unreleased general-purpose frontier model from Anthropic, a new tier above Opus (internal codename 'Capybara'). It identified thousands of zero-day vulnerabilities across every major operating system and web

Input
TextImage
Output
Text

Claude Mythos Preview benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Claude Mythos Preview across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Claude Mythos Preview holds up as conversations get longer.

Quality Tracker

Claude Mythos Preview Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Mon Sep 14 2026
Notice missing or incorrect data?

Claude Mythos Preview pricing

Providers

Claude Mythos Preview starts at $25.00 per million input tokens and $125 per million output tokens via Anthropic.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
Anthropic logoAnthropic
$25.00$125/
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Try now

huggle
Claude Mythos Previewin Huggle

Make it with
Claude Mythos Preview.

Claude Mythos Preview

Claude Mythos Preview latency

Claude Mythos Preview time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Claude Mythos Preview examples

Recent arena outputs from Claude Mythos Preview, picked from the highest-ranked matchups.

Claude Mythos Preview license

Claude Mythos Preview is a proprietary model available under its provider's product and API terms.

License
Proprietary
Hosted access

Proprietary license - usage restrictions apply

Claude Mythos Preview resources

Official sources for Claude Mythos Preview: paper or system card, official launch post.

Claude Mythos Preview vs other models

The most-compared alternatives to Claude Mythos Preview are GPT-6 Astra, Kimi K2.6, Claude Opus 4.8. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Claude Mythos Preview

Models ranked just above and below Claude Mythos Preview by LLM Stats score.

 

GPT-6 Astra

Score pending
 

Kimi K2.6

Score pending
 

Claude Opus 4.8

Score pending
 

Claude Opus 4.7

Score pending
 

GPT-5.6 Sol

Score pending
 

Gemini 3.1 Pro

Score pending

FAQ

Common questions about Claude Mythos Preview.

How much does Claude Mythos Preview cost?

Claude Mythos Preview pricing starts at $25.00 per million input tokens and $125.00 per million output tokens via Anthropic, the lowest price among tracked providers.

Who created Claude Mythos Preview?

Claude Mythos Preview was created by Anthropic.

What is the license for Claude Mythos Preview?

Claude Mythos Preview is released under the Proprietary license.

Is Claude Mythos Preview multimodal?

Yes, Claude Mythos Preview is multimodal and can accept both text and images as input.

Where can I use Claude Mythos Preview?

Claude Mythos Preview is available through 1 provider including Anthropic.

Where is the Claude Mythos Preview paper or technical report?

Claude Mythos Preview has a paper or technical report available at https://www.anthropic.com/claude-mythos-preview-system-card. Use that source for architecture, training, release and evaluation details.

What models should I compare Claude Mythos Preview against?

Common Claude Mythos Preview comparisons include Claude Mythos Preview vs GPT-6 Astra, Claude Mythos Preview vs Kimi K2.6, Claude Mythos Preview vs Claude Opus 4.8. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.