Top 2% of all models
Context
1.0M tokens (~500 books)
Input $/1M
$10.00
Output $/1M
$50.00
Type
multimodal
License
Proprietary
Benchmarks
13 tested
Data updated today
About
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
Tested on 13 benchmarks with 74.4% average. Top scores: Chatbot Arena Elo — Coding (1653.9%), Chatbot Arena Elo — Overall (1507.6%), OTIS Mock AIME 2024-2025 (99.7%).
Looking for similar performance at lower cost?
Step 3.5 Flash scores 89.5 (96% as good) at $0.09/1M input · 99% cheaper
Step 3.5 Flash scores 89.5 (96% as good) at $0.09/1M input · 99% cheaper
Capabilities
coding
87.8
#2 globally
reasoning
78.3
#15 globally
math
91.5
#7 globally
knowledge
54.6
#90 globally
agentic
45.0
#5 globally
speed
105.1
#1 globally
Benchmark Scores
Compare AllTested on 13 benchmarks · Ranked across 7 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
codingCompare coding →
WeirdML
87.8—Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
reasoningCompare reasoning →
SimpleBench
78.3—Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.
mathCompare math →
OTIS Mock AIME 2024-2025
99.7—Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
BenchGecko API
claude-fable-5
Specifications
- Typemultimodal
- Context1.0M tokens (~500 books)
- ReleasedJun 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.070
Available On
Learn More
Share & Export
Frequently Asked Questions
Claude Fable 5 is a proprietary multimodal AI model by Anthropic, released in June 2026. It has an average benchmark score of 93.2. Context window: 1M tokens.