Claude Fable 5.1

AnthropicLegacy

Input price: $10.00; Per 1 million tokens (USD)
Output price: $50.00; Per 1 million tokens (USD)
Effort levels: 5total; Default: High
Benchmark results: 63total; Benchmark types: 20

Model information

API model ID: claude-fable-5-1
release date: Unknown
effort: Low / Med / High (default) / Xhigh / Max
Effort source: Based on Anthropic effort documentation (platform.claude.com/docs/en/build-with-claude/effort).
Claude Code: available
Codex: unavailable
Availability notes: Selectable with `/model claude-fable-5-1` (Anthropic API). Codex's official model list (learn.chatgpt.com/docs/models) contains only OpenAI models, so codex is false (connections via a custom provider are not counted as official options).
Availability source: https://code.claude.com/docs/en/model-config

Price (USD per 1 million tokens)

Prices do not vary by effort; token consumption does.

input	$10.00
output	$50.00
cache read	$0.25
cache write	$12.50

cacheWritePerMTok is for a 5-minute cache write. 1h write $20. cache read 0.025x.

Claude Fable 5.1 | $10 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok | $50 / MTok

Source: https://platform.claude.com/docs/en/about-claude/pricing

Benchmark results

Benchmark	effort	Score	Source cost (metric)	measured/reported by	source	Conditions and extraction method
Terminal-Bench 4.0Low	Low	40.2%	$5.70Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Fable 5.1 · Low: 40.2% $5.70"
Terminal-Bench 4.0Med	Med	43.4%	$7.80Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Fable 5.1 · Med: 43.4% $7.80"
Terminal-Bench 4.0High (default)	High	49.4%	$10.50Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Fable 5.1 · High: 49.4% $10.50"
Terminal-Bench 4.0Xhigh	Xhigh	51.3%	$15.80Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Fable 5.1 · Xhigh: 51.3% $15.80"
Terminal-Bench 4.0Max	Max	55.8%	$19.50Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Terminal-Bench 4.0 — Accuracy vs Cost: "Fable 5.1 · Max: 55.8% $19.50"
Terminal-Bench-Science 0.1not stated	not stated	52.6%	—	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled. SE ±3.5–5pt. The GPT-6 Astra figure is a reported value from OpenAI.transcribed from table Source excerpt 52.6%Location Table, Terminal-Bench-Science 0.1 row: 52.6
Terminal-Bench-Science 0.1not stated	not stated	52.6%	—	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.transcribed from table Source excerpt 52.6%Location Table, Terminal-Bench-Science 0.1 row: 52.6
FrontierCode v1.1(main set)Low	Low	52.8%	$2.47Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Fable 5.1 · Low: 52.8% $2.47"
FrontierCode v1.1(main set)Med	Med	50.9%	$3.28Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Fable 5.1 · Med: 50.9% $3.28"
FrontierCode v1.1(main set)High (default)	High	50.3%	$5.27Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Fable 5.1 · High: 50.3% $5.27"
FrontierCode v1.1(main set)Xhigh	Xhigh	48.7%	$9.27Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Fable 5.1 · Xhigh: 48.7% $9.27"
FrontierCode v1.1(main set)Max	Max	50.3%	$12.82Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode v1.1, main set — Accuracy vs Cost: "Fable 5.1 · Max: 50.3% $12.82"
FrontierCode 2.0Low	Low	20.6%	$3.01Cost per task	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode 2.0 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode 2.0 — Accuracy vs. cost: "Fable 5.1 · Low: 20.6% $3.01"
FrontierCode 2.0Med	Med	21.5%	$3.89Cost per task	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode 2.0 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode 2.0 — Accuracy vs. cost: "Fable 5.1 · Med: 21.5% $3.89"
FrontierCode 2.0High (default)	High	25.7%	$5.39Cost per task	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode 2.0 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode 2.0 — Accuracy vs. cost: "Fable 5.1 · High: 25.7% $5.39"
FrontierCode 2.0Xhigh	Xhigh	32.4%	$8.68Cost per task	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode 2.0 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode 2.0 — Accuracy vs. cost: "Fable 5.1 · Xhigh: 32.4% $8.68"
FrontierCode 2.0Max	Max	31.7%	$11.46Cost per task	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "FrontierCode 2.0 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt FrontierCode 2.0 — Accuracy vs. cost: "Fable 5.1 · Max: 31.7% $11.46"
FrontierSWE 2not stated	not stated	56.3%	—	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.transcribed from table Source excerpt 56.3%Location Table, FrontierSWE v2 row: 56.3
CursorBench 4.0Low	Low	45.1%	$5.44Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Fable 5.1 · Low: 45.1% $5.44"
CursorBench 4.0Med	Med	46.8%	$7.05Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Fable 5.1 · Med: 46.8% $7.05"
CursorBench 4.0High (default)	High	49.2%	$9.08Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Fable 5.1 · High: 49.2% $9.08"
CursorBench 4.0Xhigh	Xhigh	51.6%	$13.01Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Fable 5.1 · Xhigh: 51.6% $13.01"
CursorBench 4.0Max	Max	51.8%	$17.28Cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "CursorBench 4.0 / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt CursorBench 4.0 — Accuracy vs Cost: "Fable 5.1 · Max: 51.8% $17.28"
GDPval-AA v2.1Low	Low	1,450	$1.41Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Fable 5.1 · Low: 1450 $1.41"
GDPval-AA v2.1Med	Med	1,536	$2.17Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Fable 5.1 · Med: 1536 $2.17"
GDPval-AA v2.1High (default)	High	1,617	$3.43Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Fable 5.1 · High: 1617 $3.43"
GDPval-AA v2.1Xhigh	Xhigh	1,721	$7.09Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Fable 5.1 · Xhigh: 1721 $7.09"
GDPval-AA v2.1Max	Max	1,735	$9.59Estimated cost per task	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Elo vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt GDPval-AA v2.1 — Elo vs Cost: "Fable 5.1 · Max: 1735 $9.59"
AA-Briefcase v1.1(Elo)not stated	not stated	1,669	—	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.transcribed from table Source excerpt 1669Location Table, AA-Briefcase v1.1 (Elo) row: 1669
AA-Briefcase v1.1(rubric)not stated	not stated	61.5%	—	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.transcribed from table Source excerpt 61.5%Location Table, AA-Briefcase v1.1 (rubric) row: 61.5
AutomationBenchnot stated	not stated	31.4%	—	Zapier	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled. Run and reported by Zapier.transcribed from table Source excerpt 31.4%Location Table, AutomationBench row: 31.4
AutomationBenchnot stated	not stated	31.4%	—	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.transcribed from table Source excerpt 31.4%Location Table, AutomationBench row: 31.4
Humanity's Last Exam (with tools)not stated	not stated	65.6%	—	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled.transcribed from table Source excerpt 65.6%Location Table, Humanity's Last Exam (with tools) row: 65.6
Humanity's Last Exam (with tools)Low	Low	60.2%	$0.59Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Humanity’s Last Exam (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Humanity’s Last Exam (with tools) — Accuracy vs. cost: "Fable 5.1 · Low: 60.2% $0.59"
Humanity's Last Exam (with tools)Med	Med	62.4%	$0.85Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Humanity’s Last Exam (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Humanity’s Last Exam (with tools) — Accuracy vs. cost: "Fable 5.1 · Med: 62.4% $0.85"
Humanity's Last Exam (with tools)High (default)	High	63.1%	$1.37Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Humanity’s Last Exam (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Humanity’s Last Exam (with tools) — Accuracy vs. cost: "Fable 5.1 · High: 63.1% $1.37"
Humanity's Last Exam (with tools)Xhigh	Xhigh	65.2%	$2.70Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Humanity’s Last Exam (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Humanity’s Last Exam (with tools) — Accuracy vs. cost: "Fable 5.1 · Xhigh: 65.2% $2.70"
Humanity's Last Exam (with tools)Max	Max	65.6%	$3.77Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Humanity’s Last Exam (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Humanity’s Last Exam (with tools) — Accuracy vs. cost: "Fable 5.1 · Max: 65.6% $3.77"
OSWorld 2.1(partial)not stated	not stated	80.7%	—	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled.transcribed from table Source excerpt 80.7%Location Table, OSWorld 2.1 (partial) row: 80.7
OSWorld 2.1 (offline set, partial)not stated	not stated	83.5%	—	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.transcribed from table Source excerpt 83.5%Location Table, OSWorld 2.1 (offline set, partial) row: 83.5
Chartography (with tools)not stated	not stated	88.4%	—	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. table note: Unless otherwise noted, all Claude Opus 5.5 results use adaptive thinking at max effort. production safeguards enabled.transcribed from table Source excerpt 88.4%Location Table, Chartography (with tools) row: 88.4
Chartography (without tools)Low	Low	36.6%	$0.03Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Chartography (no tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Chartography (no tools) — Accuracy vs. cost: "Fable 5.1 · Low: 36.6% $0.03"
Chartography (without tools)Med	Med	42.2%	$0.05Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Chartography (no tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Chartography (no tools) — Accuracy vs. cost: "Fable 5.1 · Med: 42.2% $0.05"
Chartography (without tools)High (default)	High	46.0%	$0.08Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Chartography (no tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Chartography (no tools) — Accuracy vs. cost: "Fable 5.1 · High: 46.0% $0.08"
Chartography (without tools)Xhigh	Xhigh	47.0%	$0.38Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Chartography (no tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Chartography (no tools) — Accuracy vs. cost: "Fable 5.1 · Xhigh: 47.0% $0.38"
Chartography (without tools)Max	Max	44.8%	$0.87Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "Chartography (no tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt Chartography (no tools) — Accuracy vs. cost: "Fable 5.1 · Max: 44.8% $0.87"
WANDRLow	Low	63.3%	$23.25Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Fable 5.1 · Low: 63.3% $23.25"
WANDRMed	Med	64.5%	$27.41Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Fable 5.1 · Med: 64.5% $27.41"
WANDRHigh (default)	High	66.7%	$33.62Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Fable 5.1 · High: 66.7% $33.62"
WANDRXhigh	Xhigh	67.7%	$42.81Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Fable 5.1 · Xhigh: 67.7% $42.81"
WANDRMax	Max	68.7%	$49.02Cost per attempt	Anthropic	Introducing Claude Opus 5.5official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR / Accuracy vs Cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR — Accuracy vs Cost: "Fable 5.1 · Max: 68.7% $49.02"
WANDR(relaxed score)Low	Low	63.3%	$24.41Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR (relaxed score) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR (relaxed score) — Accuracy vs. cost: "Fable 5.1 · Low: 63.3% $24.41"
WANDR(relaxed score)Med	Med	64.5%	$28.78Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR (relaxed score) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR (relaxed score) — Accuracy vs. cost: "Fable 5.1 · Med: 64.5% $28.78"
WANDR(relaxed score)High (default)	High	66.7%	$37.60Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR (relaxed score) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR (relaxed score) — Accuracy vs. cost: "Fable 5.1 · High: 66.7% $37.60"
WANDR(relaxed score)Xhigh	Xhigh	67.7%	$44.50Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR (relaxed score) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR (relaxed score) — Accuracy vs. cost: "Fable 5.1 · Xhigh: 67.7% $44.50"
WANDR(relaxed score)Max	Max	68.7%	$51.10Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "WANDR (relaxed score) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); WANDR: Claude was run with offline web search/fetch, programmatic tool calling, code execution, and a 980k token task budget (different from the Perplexity public configuration)transcribed from text Source excerpt WANDR (relaxed score) — Accuracy vs. cost: "Fable 5.1 · Max: 68.7% $51.10"
BenchCAD 2.1 (with tools)Low	Low	12.1	$2.95Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "BenchCAD 2.1 (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt BenchCAD 2.1 (with tools) — Accuracy vs. cost: "Fable 5.1 · Low: 12.1 $2.95"
BenchCAD 2.1 (with tools)Med	Med	15.7	$5.70Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "BenchCAD 2.1 (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt BenchCAD 2.1 (with tools) — Accuracy vs. cost: "Fable 5.1 · Med: 15.7 $5.70"
BenchCAD 2.1 (with tools)High (default)	High	25.8	$12.44Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "BenchCAD 2.1 (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt BenchCAD 2.1 (with tools) — Accuracy vs. cost: "Fable 5.1 · High: 25.8 $12.44"
BenchCAD 2.1 (with tools)Xhigh	Xhigh	40.5	$27.38Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "BenchCAD 2.1 (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt BenchCAD 2.1 (with tools) — Accuracy vs. cost: "Fable 5.1 · Xhigh: 40.5 $27.38"
BenchCAD 2.1 (with tools)Max	Max	44.4	$34.69Cost per attempt	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. A point in the figure "BenchCAD 2.1 (with tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic)transcribed from text Source excerpt BenchCAD 2.1 (with tools) — Accuracy vs. cost: "Fable 5.1 · Max: 44.4 $34.69"
RoboDojo Simnot stated	not stated	27.6%	—	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted. ‡ highest-available effort, run internally.transcribed from table Source excerpt 27.6%Location Table, RoboDojo Sim row: 27.6
Remote Labor Index(RLI)not stated	not stated	17.9%	—	Anthropic	Introducing Claude Fable 5.2 and Claude Mythos 5.2official · Retrieved 2026-11-12	Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.transcribed from table Source excerpt 17.9%Location Table, Remote Labor Index (RLI) row: 17.9

Claude Fable 5.1

Model information

Price (USD per 1 million tokens)

Benchmark results

Related rankings

References