Skip to main content

AnthropicLLM matchup

Claude Fable 5.2vs.Claude Fable 5.1

What has improved?

Claude Fable 5.2 performs better than Claude Fable 5.1 and is cheaper: Claude Fable 5.1 costs 1.3 times as much.

Fable 5.2 ahead
IntelligenceOverall index, 100 points = average
130.9

Claude Fable 5.2

Rank 1

124.1

Claude Fable 5.1

Rank 4

SpeedTokens per second
n/a

Claude Fable 5.2

59

Claude Fable 5.1

Fable 5.2 cheaper
Price$ per 1M tokens
$16

Claude Fable 5.2

$20

Claude Fable 5.1

Choose Claude Fable 5.2 for

KnowledgeAgentsGeneralReasoningCodingMathematics

Choose Claude Fable 5.1 for

Legal

Where is the difference?

Strengths at a glance

Fable 5.2Fable 5.1

The median of all ranked models is below 105 in every area, so it sits in the centre of the net.

125145165105CodingFable 5.2ReasoningFable 5.2MathematicsFable 5.2KnowledgeFable 5.2AgentsFable 5.2GeneralFable 5.2FinancelevelLegalFable 5.1
CodingFable 5.2 ahead
Fable 5.2131.6Rank 1
Fable 5.1122.8Rank 6
Median of ranked models87.4

95 % range: Fable 5.2 122.0 to 141.1, Fable 5.1 117.5 to 128.1.

AreaFable 5.2Fable 5.1

The same values and verdicts as the bars below. In the close-up the net starts at 105 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Multimodal, Health.

Fable 5.2 is ahead in 6 of 10 areas, Fable 5.1 in 1.

Fable 5.2 ahead: 6level: 1too little data: 2Fable 5.1 ahead: 1

Areas in the overall index
KnowledgeFable 5.2 +15145.5 to 130.1
AgentsFable 5.2 +10124.2 to 114.0
GeneralFable 5.2 +10132.8 to 122.8
ReasoningFable 5.2 +9124.9 to 116.1
CodingFable 5.2 +9131.6 to 122.8
MathematicsFable 5.2 +3135.2 to 132.5
Multimodalonly Fable 5.1 has a score
Specialist fields
LegalFable 5.1 +10120.9 to 130.6
Financelevel123.5 to 121.8
Healthonly Fable 5.1 has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 2 more areas that do not count toward the overall index
Cybersecurityonly Fable 5.1 has a score
Productivityonly Fable 5.1 has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Claude Fable 5.2 vs. Claude Fable 5.1 at the same effort

Both models measured at the same reasoning efforts. This shows whether a lead comes from the model or only from more compute.

lowFable 5.2 ahead
13.9 points gap across 10 shared test series
mediumFable 5.2 ahead
11.6 points gap across 10 shared test series
highFable 5.2 ahead
12.5 points gap across 10 shared test series
xhighFable 5.2 ahead
10.3 points gap across 10 shared test series
maxFable 5.2 ahead
12.8 points gap across 11 shared test series
Overall index (max vs. max)Fable 5.2 ahead
Fable 5.2 130.9 vs. Fable 5.1 124.1

The gap compares only the Artificial Analysis test series in which both models are measured at that effort. Tied below 3 points, ahead only beyond two standard errors.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeFable 5.2Coding 131.6 to 122.8
Maths and data analysisFable 5.2Mathematics 135.2 to 132.5, Reasoning 124.9 to 116.1
Facts and researchFable 5.2Knowledge 145.5 to 130.1
Agents and workflowsFable 5.2Agents 124.2 to 114.0
Security analysisopenCybersecurity without a score for Fable 5.2
Many requests on a small budgetFable 5.2$16 to $20 per 1M tokens
Finance, legal and medical textsFable 5.1Finance 123.5 to 121.8, Legal 120.9 to 130.6, Health without a score for Fable 5.2
Images, screenshots and PDFsopenMultimodal without a score for Fable 5.2

Claude Fable 5.2 vs. Claude Fable 5.1 in our own test

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

Claude Fable 5.2

Not tested yet

Claude Fable 5.1

Claude Fable 5.1: Pelican on a bicycle
A community classic for free-form SVG drawing.

Sep 7, 2026 · 27 s · $0.11

Test details
Run date
Sep 7, 2026
API provider
openrouter
Requested API model
anthropic/claude-fable-5.1
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
2,198 tokens
Cost of the attempt
$0.1102
Response time
27 s
API model reported in response
anthropic/claude-fable-5.1
Pinned endpoint
Anthropic | anthropic/claude-fable-5.1-20260831
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

SVG short test

There is no shared test round for this selection. Results from different rounds are not mixed.

Claude Fable 5.2 and Claude Fable 5.1 in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v5)

20 of 94 models

4 models in this view are measured at a lower reasoning effort than max in the overall index. Dashed column: lower reasoning effort than the top.

Claude Fable 5.2max130.9
Gemini 4 Carbonhigh127.0
Claude Opus 5.5max125.6
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.8
Gemini 4 Argonhigh121.4
GPT-6 Astramax120.2
Muse Wonder Fullmax118.1
GPT-6.1 Solmax118.0
Claude Opus 5max117.4
Muse Wondermax113.3
Claude Fable 5max112.8
Kimi K3.1 Promax112.6
Muse Ember 1.0max110.4
GPT-6 Solmax109.1
GPT-5.6 Solmax109.1
Gemini 3.7 Flashhigh107.9
Muse Spark 1.3max107.3
Gemini 3.8 Flashhigh106.8
DeepSeek V4.1 Flash 1017max106.7

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricClaude Fable 5.2Claude Fable 5.1
Intelligence
Overall indexpoints, 100 = reference group average, higher is better130.9124.1
RankRank 1 of 94Rank 4 of 94
Price per 1M tokens
Inputwhat you send$8$10
Outputwhat the model writes$40$50
Speed
Tokens per secondn/a59
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages1 M tokens≈ 1,500 A4 pages
Knowledge cutoffJune 2026June 2026
ReleasedNov 9, 2026Sep 1, 2026
AvailabilityActiveActive
Open weightsnono
  • Claude Fable 5.2, Batch pricing: $4 input and $20 output per million tokens, separate from standard API pricing. Source
  • Claude Fable 5.2, Fast pricing: $16 input and $80 output per million tokens. Fast is a separate serving mode. Source

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Cheaper than Fable 5.2Claude Opus 5.5

Overall index 125.6, rank 3$4 input and $20 output per 1M tokens

Fable 5.2 vs. Claude Opus 5.5

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: Claude Fable 5.2B: Claude Fable 5.1

AA-BriefcaseOverall · higher is betterClaude Fable 5.2: 1,785.3 eloClaude Fable 5.1: 1,669.5 eloArtificial AnalysisAs of 11/10/2026
AA-OmniscienceOverall · higher is betterClaude Fable 5.2: 66.8 pointsClaude Fable 5.1: 46.3 pointsArtificial AnalysisAs of 11/09/2026
AA-Omniscience AccuracyOverall · higher is betterClaude Fable 5.2: 79.1%Claude Fable 5.1: 68.4%Artificial AnalysisAs of 11/09/2026
AA-Omniscience Hallucination RateOverall · lower is betterClaude Fable 5.2: 59.3%Claude Fable 5.1: 70.0%Artificial AnalysisAs of 11/09/2026
AutomationBench-AAOverall · higher is betterClaude Fable 5.2: 76.4%Claude Fable 5.1: 59.4%Artificial AnalysisAs of 11/09/2026
CritPt v2 (Hard Subset)Overall · higher is betterClaude Fable 5.2: 76.5%Claude Fable 5.1: 52.5%Artificial AnalysisAs of 11/09/2026
FrontierCodeOverall · higher is betterClaude Fable 5.2: 48.8%Claude Fable 5.1: 31.6%Artificial AnalysisAs of 11/09/2026
FrontierCode 1.1 MainOverall · higher is betterClaude Fable 5.2: 56.2%Claude Fable 5.1: 49.0%Artificial AnalysisAs of 11/09/2026
GDP.pdfOverall · higher is betterClaude Fable 5.2: 24.2%Claude Fable 5.1: 26.2%Artificial AnalysisAs of 11/09/2026
GDPval-AAOverall · higher is betterClaude Fable 5.2: 1,831.3 eloClaude Fable 5.1: 1,763.3 eloArtificial AnalysisAs of 11/10/2026
Show 15 more benchmarks
HLE-DiamondOverall · higher is betterClaude Fable 5.2: 80.2%Claude Fable 5.1: 60.1%Artificial AnalysisAs of 11/09/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalClaude Fable 5.2: 32.1%Claude Fable 5.1: 50.7%Vals AIAs of 11/09/2026
Terminal-BenchOverall · higher is betterClaude Fable 5.2: 59.6%Claude Fable 5.1: 52.0%Artificial AnalysisAs of 11/09/2026
Terminal-Bench-ScienceOverall · higher is betterClaude Fable 5.2: 73.3%Claude Fable 5.1: 43.3%Artificial AnalysisAs of 11/09/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Fable 5.2: 13.3%Claude Fable 5.1: 33.3%Vals AIAs of 11/09/2026
Tax Agent BenchControversy & Precedence Analysis (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 58.2%Claude Fable 5.1: 77.5%Vals AIAs of 11/09/2026
Tax Agent BenchCurrent & Temporal Analysis (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 66.0%Claude Fable 5.1: 77.9%Vals AIAs of 11/09/2026
Tax Agent BenchFact-Pattern Analysis (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 64.5%Claude Fable 5.1: 79.6%Vals AIAs of 11/09/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalClaude Fable 5.2: 20.0%Claude Fable 5.1: 26.7%Vals AIAs of 11/09/2026
Tax Agent BenchForms & Filings (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 60.1%Claude Fable 5.1: 67.3%Vals AIAs of 11/09/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalClaude Fable 5.2: 50.0%Claude Fable 5.1: 63.3%Vals AIAs of 11/09/2026
Tax Agent BenchNumbers & Calculations (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 86.4%Claude Fable 5.1: 88.1%Vals AIAs of 11/09/2026
Tax Agent BenchRule & Source Lookup · higher is betterTest setup not documented as identicalClaude Fable 5.2: 46.7%Claude Fable 5.1: 70.0%Vals AIAs of 11/09/2026
Tax Agent BenchRule & Source Lookup (weighted pass) · higher is betterTest setup not documented as identicalClaude Fable 5.2: 68.0%Claude Fable 5.1: 76.1%Vals AIAs of 11/09/2026
Tax Agent BenchWeighted Pass · higher is betterTest setup not documented as identicalClaude Fable 5.2: 67.0%Claude Fable 5.1: 77.9%Vals AIAs of 11/09/2026

More comparisons

Compare Claude Fable 5.2 and Claude Fable 5.1 with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1Claude Opus 5.5 vs. Claude Fable 5.1
  2. 2Claude Sonnet 5.5 vs. Claude Fable 5.1
  3. 3Claude Fable 5.2 vs. Kimi K3
  4. 4Claude Fable 5.1 vs. GPT-6 Astra
  5. 5Claude Fable 5.1 vs. GPT-5.6 Sol
  6. 6Claude Fable 5.1 vs. Grok 4.7
  7. 7Claude Fable 5.1 vs. GLM-5.3-Flash
  8. 8Claude Fable 5.1 vs. GPT-6 Luna
  9. 9Claude Fable 5.1 vs. GPT-6 Sol
Show all 22 comparisons
  1. 10Claude Fable 5.1 vs. Qwen 3.8 27B
  2. 11Claude Haiku 5.5 vs. Claude Fable 5.1
  3. 12Claude Fable 5.1 vs. DeepSeek V4.1 Flash 1017
  4. 13Claude Fable 5.1 vs. Claude Sonnet 4.6
  5. 14Claude Fable 5.1 vs. Claude Opus 4.6
  6. 15Claude Fable 5.1 vs. Claude Opus 4.8
  7. 16Claude Fable 5.1 vs. Mistral Large 4
  8. 17Claude Fable 5.1 vs. Gemini 4 Argon
  9. 18Claude Fable 5.1 vs. Gemini 4 Carbon
  10. 19Claude Fable 5.2 vs. Claude Opus 5.5
  11. 20Claude Fable 5.1 vs. Kimi K3.1 Pro
  12. 21Claude Fable 5.2 vs. Claude Haiku 5.5
  13. 22Claude Fable 5.1 vs. GPT-6.1 Sol