Project AURIONAI Use-Cases Research & Innovation
LLM

Claude Fable 5

Public Claude 5 release derived from the Mythos line; withdrawn 2026-06-12 and returned 2026-07-01. GA in GitHub Copilot.

AnthropicAnthropicUSAClaudeFamily
Anthropic
Levelmodel
ClassLLM
Parametersnot in the notes
Context2,000,000
Released9 Jun 2026
Opennessproprietary
Runs onnot in the notes
Statusactive

Benchmark Results

vendor-reportedindependent
Arena Text leaderboardhuman preference arena
highindependent
1,504 ±4
1,2001,4001,600

Score in Elo; the axis starts at 1,200, as Elo has no zero. Higher is better.

rank 4, Arena Text overall8 Oct 2026 arena.ai
Arena Vision leaderboardhuman preference arena
highindependent
1,308 ±7
1,2701,2901,310

Score in Elo; the axis starts at 1,270, as Elo has no zero. Higher is better.

rank 1 of 165, Arena Vision overall, style control default, 165 models9 Oct 2026 arena.ai
SWE-bench Procoding
public board (per heyuan110)vendor-reported
80
050100

Score in %. Higher is better.

heyuan110.com
vendor-reported
77.8
050100

Score in %. Higher is better.

ecosistemastartup.com
SWE-bench Verifiedcoding
5-trial averagevendor-reported
95
050100

Score in %. Higher is better.

leaderboard.steel.dev
secondary report; source flags possible Mythos attribution mix-upvendor-reported
93.9
050100

Score in %. Higher is better.

ecosistemastartup.com
Terminal-Bench 2.0agents and tool use
vendor-reported
82
050100

Score in %. Higher is better.

ecosistemastartup.com
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

successorproduct of
Claude Fable 5 to Claude Fable 5.1: successor, medium confidenceClaude Mythos 5 to Claude Fable 5: product of, low confidenceClaude Mythos 5 to Claude Mythos 5.1: successor, low confidenceClaude Mythos 5Claude Mythos 5AnthropicClaude Mythos 5.1Claude Mythos 5.1AnthropicClaude Fable 5Claude Fable 5Anthropic, Jun 2026Claude Fable 5.1Claude Fable 5.1Anthropic, Sep 2026
AnthropicClaude Fable 5.1 is a child (successor)medium confidencenotes
AnthropicClaude Mythos 5 is the parent (product of)low confidencepress claim
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 4 models. Confidence and evidence are the notes' own.

R&D Topics

Frontier pretraining scalingproduced by

Identity

Developer
Anthropic
Family
Claude
Released
9 Jun 2026 sourcessecondary report
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes Not disclosed; shares architecture with restricted Claude Mythos (secondary report)
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
2,000,000 tokensunverified
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
proprietary
Licence
Proprietary sources
Access routes
API
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. Newsroom anthropic.com https://www.anthropic.com/news
  2. Best AI models, October 2026: Opus 5.5, GPT-6, Gemini slash-digital.io https://slash-digital.io/en/insights/ai-models-2026/
  3. Anthropic releases Claude Opus 5.5 with Fable 5.1-level performance at lower cost - AI News vpsranking.com https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/
  4. Text Arena: LLM Rankings & AI Model Benchmarks arena.ai https://arena.ai/leaderboard/chat/text
  5. leaderboard.steel.dev/leaderboards/swe-bench-verified.md https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md
  6. Claude Fable 5: 93.9% en SWE-bench y lo que significa para founders – El Ecosistema Startup ecosistemastartup.com https://ecosistemastartup.com/claude-fable-5-93-9-en-swe-bench-y-lo-que-significa-para-founders/
  7. Claude Opus 5.5: Fable-Class Work, Cheaper to Run llm-stats.com https://llm-stats.com/blog/research/claude-opus-5-5-launch

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Claude Fable 5", https://aurion.semai.id/models/anthropic-claude-fable-5/, records of October 2026.