CorX Labs

Claude Mythos 5

by Anthropic · United States
ProprietaryReasoningVisionTool calling1M context

Claude Fable 5's capabilities without its safety classifiers, released alongside it for defensive cybersecurity work under Project Glasswing. Same specifications and pricing as Fable 5; access is approved case by case.


Specification

The numbers

Maker
Anthropic
Released
2026-06
Parameters
Not reported
Architecture
Not reported
Context window
1,000,000 tokens
Max output
128,000 tokens
Input
Text, Image
Output
Text
Reasoning
Yes
Tool calling
Yes
Knowledge cutoff
2026-01
Licence
Proprietary
Availability
Invitation only — Project Glasswing
Weights
Not released

API model ID: claude-mythos-5

Cost

Price per million tokens

Input
$10.00 / M tokens
Output
$50.00 / M tokens
Cached input
$1.00
Blended 3:1
$20.00

Standard first-party API rate, excluding batch discounts. Reasoning models bill thinking tokens as output, so cost per answer can far exceed the cost per token suggests.

Published scores

Benchmarks

Figures published by Anthropic or taken from a public leaderboard. Row last checked 2026-09.

Every reported test

No published benchmark scores yetIts maker has not published benchmark figures for this model, and nothing has been estimated in their place.

Where these numbers come from

Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.

A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.

Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.

Same maker

Other models from Anthropic

AI models with context window, price per million tokens and published benchmark scores. Sortable by any column.
Claude Fable 5.1AnthropicAnthropic1M$10.00$50.00Proprietary
Claude Mythos 5.1AnthropicAnthropic1M$10.00$50.00Proprietary
Claude Opus 5AnthropicAnthropic1M$5.00$25.00Proprietary
Claude Sonnet 5AnthropicAnthropic1M$2.00$10.00Proprietary
Claude Fable 5AnthropicAnthropic1M$10.00$50.00Proprietary
Claude Opus 4.5AnthropicAnthropic200K$5.00$25.0087%96%80.9%Proprietary
Claude Haiku 4.5AnthropicAnthropic200K$1.00$5.0073%77%73.3%Proprietary
Claude Sonnet 4.5AnthropicAnthropic1M$3.00$15.0083.4%87%77.2%Proprietary
Claude Opus 4.1AnthropicAnthropic200K$15.00$75.0080.9%78%74.5%Proprietary
Claude Sonnet 4AnthropicAnthropic200K$3.00$15.0075.4%70.5%72.7%Proprietary
Claude 3.7 SonnetAnthropicAnthropic200K$3.00$15.0068%61.3%62.3%Proprietary
Claude 3.5 HaikuAnthropicAnthropic200K$0.80$4.0065%41.6%40.6%Proprietary
Claude 3.5 SonnetAnthropicAnthropic200K$3.00$15.0078%65%49%Proprietary
Claude 3 OpusAnthropicAnthropic200K$15.00$75.0068.5%50.4%Proprietary