Anthropic model
Claude Fable 5.1
Claude Fable 5.1 in the public Anthropic catalog.
- Provider
- Anthropic
- Availability
- Available
- Model ID
- claude-fable-5-1
- Snapshot
- 2026-10-07
Claude Fable 5.1 Benchmarks & Agentic Accuracy
Verified primary research & developer preference metrics
What This Means in Real Software Development
- Achieves an Intelligence Index of 53 on Artificial Analysis v4.3.2, second only to Claude Opus 5.5.
- Scores 56 on the Finance & Accounting Index, excelling at complex quantitative workflows and multi-step spreadsheet deduction.
- Delivers 65 TPS throughput at $7.63 weighted average cost per Intelligence task.
- Engineered for deep multi-turn agentic sessions with zero instruction drift across large software systems.
Swarm Multi-Agent Topology
Best Paired With: deepseek-v4p1-flash or gemini-3-8-flash for high-speed subagent execution
Orchestrates multi-stage Task Programs with airtight boundary verification.
Directs parallel subagent worktrees while maintaining master branch integrity.
What Developers & Practitioners Are Saying
Real-world field observations, production strengths, and developer consensus
"Celebrated as Anthropic's most versatile agentic flagship. Exceptional at complex tool calling, multi-file code editing, and holding context across 100+ turns."
Verified Real-World Strengths
- Intelligence Index 53 with stellar multi-turn task completion
- Resilient against edge-case hallucinations in complex codebases
- Superior instruction obedience in long DAG pipelines
Production Caveats & Gaps
- Higher cost per task ($7.63) than fast coder models
- Output latency higher than subagent flash models
Primary Sources & Methodology Citations
- Artificial Analysis Intelligence Index v4.3.2 — Artificial Analysis (September 2026)
- Claude Fable 5.1 Architecture & Benchmark Card — Anthropic (May 2026)
Head-to-Head Frontier Comparisons: Claude Fable 5.1 vs Rivals
Standardized, side-by-side benchmark & economics comparison against peer models
| Model | Role / Tier | SWE-bench | LiveCodeBench | LMSYS Elo | AIME | Input / Output |
|---|---|---|---|---|---|---|
Claude Fable 5.1AnthropicCurrent | Tier 1: Frontier Agentic Lead | 76.2% | 67.4% | 1435 | — | $6 / $30 |
OpenAI GPT-6 AstraOpenAI Compare Claude Fable 5.1 vs OpenAI GPT-6 Astra → | Tier 1: Autonomous Chief Architect | 82% | 84.5% | 1470 | 97% | $6 / $24 |
Muse Spark 1.3Meta Compare Claude Fable 5.1 vs Muse Spark 1.3 → | Tier 1: High-Speed Frontier Coder | 74.8% | 66.2% | 1420 | — | $1.2 / $6 |
xAI Grok 4.20xAI Compare Claude Fable 5.1 vs xAI Grok 4.20 → | Tier 1: Frontier Systems Specialist | 58.5% | 54.2% | 1375 | 76% | $2 / $8 |
Claude Opus 5.5Anthropic Compare Claude Fable 5.1 vs Claude Opus 5.5 → | Tier 1: Master Principal Architect | 79.5% | 70.2% | 1450 | 92% | $15 / $75 |
Claude Fable 5.1 model overview
Claude Fable 5.1 is listed in the public Swarm catalog through Anthropic. This page summarizes the verified catalog fields used by Swarm without claiming real-time access for every provider account.
- Provider
- Anthropic
- Family
- Claude
- Context window
- 1M tokens
- Thinking support
- low · medium · high · xhigh
- Availability status
- Available
- Catalog ID
- anthropic/claude-fable-5-1
Run Claude Fable 5.1 in Swarm
Verified CLI workflow & multi-agent architecture
swarm ctl model set --provider anthropic --model anthropic/claude-fable-5-1# Or switch interactively inside the terminal TUI:
/modelsSubagent Role Matrix
Assign Claude Fable 5.1 to specialized system roles in ~/.swarm/config.json:
- Primary / Planner: Orchestrates full task DAGs and multi-stage pipelines.
- Coder Subagent: Generates code and unit tests inside private Git worktrees.
- Finder Subagent: Performs read-only code search, symbol discovery, and mapping.
Public catalog snapshot. Catalog availability is not a real-time provider status or an access guarantee.