Claude Fable 5.1
anthropic
Cross-checked
DeepSeek V4 Flash 0731 = 100. The index reflects two shared tests, not capability multiples or statistically established gaps. Results reflect particular model configurations. Agent harnesses, reasoning effort, tools, budgets and tasks may differ. Close indices do not establish superiority. B describes a relative position in this selected group, not an inability to code.
Capabilities & Recommended Uses
Strengths
- •Agentic coding
- •Long-running refactors and visual development
Best For
- •Multi-file refactoring
- •Front-end development
Weaknesses
—
Benchmark evidence and ranking method · Claude Fable 5.1
Cross-checked
Terminal-Bench 4.0 · Claude Code · max: 57.88% · 95% CI ± 3.76%
Artificial Analysis · Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Test configuration: max
Terminal-Bench 2.1: 91.39% · SciCode: 63.08%
LiveBench · 2026-06-25 · claude-fable-5-1-max-effort
Coding: 86.38% · Agentic Coding: 66.06%
ModelRank assigns editorial tiers using public coding evidence, not automatic index thresholds or statistically proven classes. Price, speed, context size and sponsorship do not affect tiers.
DeepSeek V4 Flash 0731 = 100. The index reflects two shared tests, not capability multiples or statistically established gaps.
Results reflect particular model configurations. Agent harnesses, reasoning effort, tools, budgets and tasks may differ. Close indices do not establish superiority. B describes a relative position in this selected group, not an inability to code.
Data checked: 2026-09-10. Snapshot date is the retrieval date, not necessarily the evaluation date.
Compare with Alternatives
Related Analysis & Reviews
Claude Fable 5.1 for Coding: When Is the S+ Model Worth Paying For?
Why is Fable 5.1 in S+? Check its coding evidence and API quote, then calculate how much human repair time it would need to save to justify the cost.
Claude Fable 5.1 vs GPT-6 Astra: Which Should You Try for Coding?
Compare Fable 5.1 and GPT-6 Astra using public coding evidence. Understand the 121 vs 112 index gap, agent configurations and when switching is worthwhile.
GPT-6 Astra for Coding: Why Is Its Index Below GPT-5.6 Sol?
GPT-6 Astra and Sol share an S tier despite different rounded indices. Understand the evidence, agent configurations and when to compare Fable 5.1.
Frequently Asked Questions
What is Claude Fable 5.1's coding score and ranking tier?
Claude Fable 5.1 by anthropic is rated as Tier S+ on ModelRank with a coding score of 120.65 (Reference baseline = 100) as a reference index derived from public benchmark evidence. Tiers are editorial assessments; the index does not establish real-world capability differences.
What is the API pricing and context window for Claude Fable 5.1?
Claude Fable 5.1 features a 1,000,000 token context window. Pricing is $10 per 1M input tokens and $50 per 1M output tokens (OpenRouter quote).
What programming tasks is Claude Fable 5.1 best suited for?
Claude Fable 5.1 is recommended for: Multi-file refactoring, Front-end development. Key strengths include: Agentic coding, Long-running refactors and visual development.
Try Claude Fable 5.1
Last updated: October 11, 2026