Claude Mythos 5

Released

Claude Mythos 5 is an AI model released by Anthropic on Tuesday, Jun 9 2026, the same day as Claude Fable 5. It has a 1M token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover CharXiv Reasoning, SWE-Bench Pro, SWE-Bench Verified, Terminal-Bench 2.1, BrowseComp, CyberGym, and 8 more.

API pricing

Verified organizations only
Input
$10.00
Cached input
$1.00
5 min cache write
$12.50
1 hr cache write
$20.00
Output
$50.00
  • Adaptive thinking is always on.
USD per 1M tokensModel mappingVerified November 9, 2026Read from platform.claude.com. Click the check to open the source.

Benchmarks

Coding

SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better.
80.3%
#4 of 46
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better.via BenchLM
95.5%
#2 of 89

Terminal & CLI

Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better.via BenchLM
88%
#8 of 40

Agentic & tool use

BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better.via BenchLM
88%
#8 of 45
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better.
83.8%
#5 of 17
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better.via BenchLM
85%
#2 of 33

Reasoning & science

RiemannBenchAdvanced mathematics — mathematical problem-solving evaluation published by Surge
55%
#4 of 5
Humanity's Last ExamMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better.via BenchLM
59%no tools
64.5%with tools
no tools
#3 of 51
with tools
#6 of 59
BioMysteryBenchBiology — Real unsolved-style biology puzzles — the AI has to reason its way to an answer the way a research biologist would. The “hard” split contains the toughest cases. Higher is better.
46.1%hard
83.9%human solved
hard
#4 of 10
human solved
#9 of 11

Knowledge work

OfficeQA ProDocument Q&A — answering the 133 Treasury document questions with extracted text and code execution available
67.1%extracted text
#3 of 9

Healthcare

HealthBench ProfessionalHealth — physician-graded conversations, scored before adjustment for answer length
70.3%raw
66%length-adjusted
raw
#6 of 9
length-adjusted
#2 of 10

Multimodal

CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better.
88.9%
93.5%with tools
#2 of 28
with tools
#1
ChartographyChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better.
85.2%with tools
36%no tools
with tools
#6 of 13
no tools
#13 of 17

Source: BenchLM, retrieved 28 September 2026. Other sources are identified on the linked benchmark pages.

Compare Claude Mythos 5 with

Claude Mythos 5

About

Claude Mythos 5 was announced on June 9, 2026 as an update to Mythos Preview for a small group of vetted organizations. Anthropic described it as the same underlying model as Fable 5, with safeguards lifted in some areas for approved cybersecurity and scientific work. Initial distribution went through Project Glasswing.

Its restricted access distinguished Mythos from the more broadly offered Fable service. Anthropic's launch post also records a temporary suspension of access after launch and a July 1 restoration update. The publication describes access controls and safeguards, so calling Mythos an unrestricted model would overstate what customers were permitted to do.

Frequently asked questions

Claude Mythos 5 was released by Anthropic on Tuesday, Jun 9 2026.

All Anthropic releases

33 tracked