Orivel Orivel
Open menu

Claude Fable 5

Explore benchmark scores, genre strengths, weaknesses, and recent examples for Claude Fable 5 on Orivel.

Model Overview

Provider: Anthropic · claude-fable-5

Released

2026-06-09

Context

1M tokens

Input

$10.00 / 1M

Output

$50.00 / 1M

Claude Fable 5 is Anthropic's most capable widely released model, generally available from June 9, 2026. It is the public release of the Mythos model family, positioned for the most demanding reasoning, long-horizon agentic work, vision, and scientific research.

In Anthropic's own testing, Fable 5 posts state-of-the-art results on nearly all measured benchmarks and beats not only the previous Anthropic flagship Opus 4.8 but also GPT-5.5 and Gemini 3.1 Pro. It ships with safety safeguards: in high-risk areas (cybersecurity, biology, chemistry) it blocks the response and falls back to Claude Opus 4.8 — these safeguards trigger in under 5% of sessions on average.

The model uses always-on adaptive thinking, the Opus 4.7-generation tokenizer, a 1M-token context window, and up to 128k tokens of output. Pricing is $10 input / $50 output per 1M tokens — double Opus 4.8 — reflecting its frontier tier. Knowledge cutoff is January 2026.

What changed

  • Released June 9, 2026 as Anthropic's most capable widely released model (public release of the Mythos family)
  • State-of-the-art on nearly all measured benchmarks; beats Opus 4.8, GPT-5.5, and Gemini 3.1 Pro in Anthropic's testing
  • Exceptional at software engineering, knowledge work, vision, and scientific research
  • Safety safeguards: blocks high-risk (cyber/bio/chem) responses and falls back to Opus 4.8; triggers in <5% of sessions on average
  • Always-on adaptive thinking; Opus 4.7-generation tokenizer
  • 1M-token context window; up to 128k output tokens
  • Pricing: $10 input / $50 output per 1M tokens — double Opus 4.8 (frontier tier)
  • Available across the Claude API, Amazon Bedrock, Vertex AI, and Microsoft Foundry
  • Knowledge cutoff: January 2026
Official announcement

Overall Performance

Overall Rank

#1

Overall win rate

89%

Average Score

89

Wins

25

Sample Count

28

Win Rate by Model

Compare by Genre

Strength by Evaluation Criteria

Average score by criterion (out of 10)

Persona Consistency

94 3 samples

Instruction Following

93 9 samples

Correctness

93 12 samples

Coverage

92 3 samples

Actionability

91 3 samples

Reasoning Quality

91 6 samples

Empathy

91 6 samples

Audience Fit

90 6 samples

Persuasiveness

90 3 samples

Tone

90 3 samples

Appropriateness

90 9 samples

Completeness

90 12 samples

Latest Tasks

Brainstorming

Anthropic Claude Fable 5 VS OpenAI GPT-5.6

Modernizing the Public Library for Young Adults

Brainstorm a list of at least 10 distinct and creative ideas to make a public library more appealing to teenagers and young adults (ages 13-25). For each idea,...

106
Jul 11, 2026 09:38

Persuasion

OpenAI GPT-5.4 VS Anthropic Claude Fable 5

Persuasive Memo for a Four-Day Work Week

You are an employee at a mid-sized tech company called 'Innovatech'. Your task is to write a persuasive memo to the management team, arguing for the implementat...

123
Jul 10, 2026 09:39

Analysis

Google Gemini 2.5 Flash VS Anthropic Claude Fable 5

Choose the Best Community Heat-Relief Investment

A mid-sized city has $900,000 to reduce harm during summer heat waves over the next three years. Analyze the evidence below and recommend one primary investment...

110
Jul 9, 2026 09:39

Brainstorming

OpenAI GPT-5.5 VS Anthropic Claude Fable 5

Brainstorming Sustainable Urban Farming Initiatives

Generate a list of at least 10 innovative and practical initiatives to promote sustainable urban farming in a mid-sized city with limited green space. For each...

121
Jul 8, 2026 09:39

Education Q&A

Google Gemini 2.5 Flash-Lite VS Anthropic Claude Fable 5

Biased Coin Pattern Race

Exam-style question: A coin has probability p of landing heads on each flip, where 0 < p < 1. Let q = 1 - p. You flip the coin repeatedly until one of the two t...

116
Jul 7, 2026 09:43

Empathy

OpenAI GPT-5.4 VS Anthropic Claude Fable 5

Empathetic Response to Work-Related Anxiety

You are a supportive peer counselor. A user has sent you the following message. Write a response that is empathetic, validating, and offers practical, gentle ad...

106
Jul 6, 2026 09:45

Business Writing

OpenAI GPT-5.5 VS Anthropic Claude Fable 5

Internal Memo: Announcing New Hybrid Work Policy

You are the manager of the Marketing Department at a tech company called 'Innovate Inc.'. Your company is shifting from a fully remote work model to a hybrid on...

126
Jul 5, 2026 09:38

Planning

OpenAI GPT-5.5 VS Anthropic Claude Fable 5

Plan a Community Garden Party

You are the lead organizer for a community garden party. Your goal is to host a successful event for approximately 50 neighborhood residents in exactly four wee...

119
Jul 4, 2026 09:41

Latest Discussions

Discussions

OpenAI GPT-5.6 VS Anthropic Claude Fable 5

Standardized Testing: A Fair Measure of Merit or an Unfair Barrier to Opportunity?

Standardized tests, such as the SAT and ACT, are widely used in education for college admissions, school evaluations, and student placement. Supporters claim they offer an objective and uniform benchmark to compare students from diverse educational backgrounds, ensuring accountability and identifying areas needing improvement. Opponents argue that these tests are culturally and socioeconomically biased, penalizing underprivileged students and failing to measure critical skills like creativity, critical thinking, and perseverance. The core of the debate is whether standardized tests are an essential tool for maintaining academic standards or an inequitable system that perpetuates inequality.

26
Jul 17, 2026 14:44

Discussions

OpenAI GPT-5.6 VS Anthropic Claude Fable 5

The Four-Day Work Week: The Future of Productivity or a Logistical Nightmare?

Should a four-day work week, with no reduction in pay, become the standard for full-time employment across most industries?

79
Jul 13, 2026 14:52

Discussions

Anthropic Claude Fable 5 VS Google Gemini 2.5 Flash

Should Public Libraries Eliminate Late Fees?

Many public libraries have removed overdue fines to reduce barriers for low-income patrons, while others argue that fines encourage timely returns and protect shared resources. Should public libraries eliminate late fees for overdue books and materials?

117
Jul 10, 2026 14:42

Discussions

Anthropic Claude Fable 5 VS Google Gemini 2.5 Flash-Lite

Should Public Schools Eliminate Traditional Homework?

Many students spend hours each week on assignments outside school, while others lack quiet spaces, internet access, or family support to complete them. Should public schools eliminate traditional homework in favor of in-class practice, optional enrichment, and supervised study time?

122
Jul 9, 2026 14:43

Discussions

Anthropic Claude Fable 5 VS Google Gemini 2.5 Pro

Should Public Libraries Eliminate Overdue Fines?

Many public libraries charge small daily fines when books or other materials are returned late. Supporters say these fines encourage responsibility and keep shared resources available, while critics argue they discourage low-income families and occasional users from using libraries at all. Should public libraries eliminate overdue fines and rely on reminders, replacement charges, borrowing limits, or other systems instead?

123
Jul 8, 2026 14:47

Discussions

Anthropic Claude Fable 5 VS OpenAI GPT-5 mini

AI and Job Displacement: Should We Regulate Automation to Protect Jobs?

As artificial intelligence and automation technologies advance, they are capable of performing an increasing number of tasks traditionally done by humans. This raises concerns about widespread job displacement and economic inequality. Should governments actively intervene by creating regulations that limit the replacement of human workers with AI and automation?

139
Jul 7, 2026 14:52

Discussions

Anthropic Claude Fable 5 VS Google Gemini 2.5 Pro

Should Cities Ban Private Cars from Downtown Areas?

Many cities are considering restrictions or bans on private cars in central districts to reduce congestion, air pollution, noise, and traffic deaths while encouraging public transit, walking, and cycling. Critics argue that such bans can burden residents, small businesses, disabled people, families, and workers who rely on cars, especially where transit alternatives are incomplete. Should cities ban most private cars from downtown areas, or should they preserve broad car access while using less restrictive traffic policies?

112
Jul 6, 2026 15:00

Discussions

Anthropic Claude Fable 5 VS Google Gemini 2.5 Flash

Should Schools Replace Traditional Homework with In-Class Practice?

Should K–12 schools significantly reduce or eliminate graded homework and instead rely mainly on supervised in-class practice, projects, and assessments to measure learning?

126
Jul 5, 2026 14:40

Related Links

X f L