Claude Fable 5

Across the task benchmarks we track, Claude Fable 5’s strongest relative results are in knowledge work, reasoning, and coding. On GDPval-AA v2.1, it scores 1,618 Elo, ranking #13 among 38 models with reported results in our dataset.

Updated: Nov 5, 2026Data as of: Nov 2, 2026

Compare this model

Strongest results

Strongest results for Claude Fable 5 in tracked evaluation cohorts
Benchmark	Measures	Score
Humanity's Last Exam ↗Stable HLE — text-only subset	Expert reasoning	55.5%#3 of 68
GDPval-AA ↗2.1	Knowledge work	1,618.39 Elo#13 of 38
GPQA ↗Diamond / Artificial Analysis	Reasoning	92.63%#12 of 30
DeepSWE ↗v1.1	Coding agents	70%#5 of 11

Model details

Proprietary11 benchmarks

Specifications for Claude Fable 5
Model	Claude Fable 5
Agent Index v1.2	Insufficient coverage (1/7) · Preview
Creator	Anthropic (opens in a new tab)
Availability	Proprietary
Context size	1,000,000 tokens (opens in a new tab)
Max output	128,000 tokens (opens in a new tab)
Knowledge cutoff	Not reported
License	Not reported

Pricing and performance

Per provider and reported configuration. Prices are USD per 1M tokens.

Provider offerings for Claude Fable 5
Provider / configuration	Contexttokens	InputUSD / 1M tokens	OutputUSD / 1M tokens	LatencyTTFT · seconds	Speedtokens / sec
Anthropic (opens in a new tab) Claude Fable 5 (with fallback)	1,000,000	$10.00 (opens in a new tab)	$50.00 (opens in a new tab)	117.332 (opens in a new tab)	68.168 (opens in a new tab)
Azure (opens in a new tab) Claude Fable 5 (with fallback)	1,000,000	$10.00 (opens in a new tab)	$50.00 (opens in a new tab)	115.288 (opens in a new tab)	68.983 (opens in a new tab)
Google (opens in a new tab) Claude Fable 5 (with fallback)	1,000,000	$10.00 (opens in a new tab)	$50.00 (opens in a new tab)	106.118 (opens in a new tab)	70.091 (opens in a new tab)

Benchmark performance

Claude Fable 5 in color, alongside leading models. Latest stored reports, best effort per report date.

Reasoning

198-question Diamond subset; independent AA evaluation

GPQA Diamond ↗

01
GPT-6 Astra96.3%
02
Gemini 3.8 Flash95.3%
03
Gemini 3.1 Pro94.1%
03
GPT-5.6 Sol94.1%
03
Muse Spark 1.394.1%
12
Claude Fable 5This model92.6%

Coding

113 tasks; mini-swe-agent

DeepSWE v1.1 ↗

Terminal Use

Official 4.0 board; native agent harnesses

Terminal-Bench 4.0 ↗

Web Research

Professional benchmark table; OpenAI Astra release comparison

BrowseComp ↗

Work Automations

Private held-out set; API mode; 50 steps; strict pass/fail

AutomationBench 1.0.6 ↗

Knowledge Work

220 tasks; Stirrup agent; pairwise Elo

GDPval-AA v2.1 ↗

01
Claude Opus 5.51,866 Elo
02
Kimi K3.1 Pro1,858 Elo
03
Claude Sonnet 5.51,838 Elo
04
Claude Fable 5.11,763 Elo
05
DeepSeek V4.1 Flash 10171,746 Elo
13
Claude Fable 5This model1,618 Elo

Reported benchmarks

All published results in our dataset, with versions, evaluation settings, and sources.

All published benchmark reports for Claude Fable 5
Benchmark	Score	Evaluation setup	Source
AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better	12.48%	Claude Fable 5.0 (Low); private held-out 657 tasks; API mode; 50-step cap; strict completion	Zapier ↗ (opens in a new tab)benchmark publisher
AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better	13.7%	Claude Fable 5.0 (Medium); private held-out 657 tasks; API mode; 50-step cap; strict completion	Zapier ↗ (opens in a new tab)benchmark publisher
AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better	15.22%	Claude Fable 5.0 (XHigh); private held-out 657 tasks; API mode; 50-step cap; strict completion	Zapier ↗ (opens in a new tab)benchmark publisher
AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better	16.13%	Claude Fable 5.0 (High); private held-out 657 tasks; API mode; 50-step cap; strict completion	Zapier ↗ (opens in a new tab)benchmark publisher
AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better	17.05%	Claude Fable 5.0 (Max); private held-out 657 tasks; API mode; 50-step cap; strict completion	Zapier ↗ (opens in a new tab)benchmark publisher
AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better	54.1%	reported precision decimals: 1 · result quality: reported · Claude Fable 5 (with fallback); private held-out 657 tasks; 50 turns; objective completion with zero credit for any guardrail violation. · source model href: /models/claude-fable-5 · task count: 657 · Tools enabled · turn cap: 50	Artificial Analysis (opens in a new tab)independent
BrowseCompOpenAI Astra launch comparison / September 2026Accuracy · Higher is better	87.4%	OpenAI GPT-6 Astra launch comparison; best reported reasoning setting; see source evaluation footnotes	OpenAI ↗ (opens in a new tab)provider reported
DeepSWEv1.1Pass@1 · Higher is better	70%	mini-swe-agent; effort=xhigh; ±3 percentage points	Datacurve ↗ (opens in a new tab)benchmark publisher
DeepSWEv1.1Pass@1 · Higher is better	70%	xhigh; ±3 percentage points	Datacurve ↗ (opens in a new tab)benchmark publisher
DeepSWEv1.1 / OpenAI Astra launch comparisonPass@1 · Higher is better	69.9%	OpenAI GPT-6 Astra launch comparison; best reported reasoning setting; see source evaluation footnotes	OpenAI ↗ (opens in a new tab)provider reported
GDPval-AA2.1Elo · Higher is better	1,618.39 Elo	Claude Fable 5 (Max, Opus 4.8 Fallback); 220 tasks; Stirrup agent; pairwise Elo	Artificial Analysis (opens in a new tab)independent
GPQADiamond / Artificial AnalysisAccuracy · Higher is better	92.626%	Claude Fable 5 (Max, Opus 4.8 Fallback); 198-question Diamond subset; independent AA evaluation	Artificial Analysis (opens in a new tab)independent
Humanity's Last ExamStable HLE — full setAccuracy · Higher is better	63%	Full-set comparison; reasoning effort and tool configuration as reported. Kept separate from later publications. · subset: full · Tools enabled	Moonshot AI ↗ (opens in a new tab)provider reported
Humanity's Last ExamStable HLE — full setAccuracy · Higher is better	53.3%	Full-set comparison; reasoning effort and tool configuration as reported. Kept separate from later publications. · subset: full · No tools	Moonshot AI ↗ (opens in a new tab)provider reported
Humanity's Last ExamStable HLE — full setAccuracy · Higher is better	63.8%	subset: full · Tools enabled	Anthropic ↗ (opens in a new tab)provider reported
Humanity's Last ExamStable HLE — full setAccuracy · Higher is better	57.8%	subset: full · No tools	Anthropic ↗ (opens in a new tab)provider reported
Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better	55.5%	question count: 2158 · reported precision decimals: 1 · Claude Fable 5 (with fallback); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/claude-fable-5 · subset: text · No tools	Artificial Analysis (opens in a new tab)independent
Terminal-Bench4.0Task success · Higher is better	44.5%	Claude Code; effort=max; 44.5% ± 3.8%	Terminal-Bench ↗ (opens in a new tab)benchmark publisher
Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better	42.424%	harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Claude Fable 5 (Max, Opus 4.8 Fallback)	Artificial Analysis (opens in a new tab)independent