Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs Claude Fable 5.1

Claude Fable 5.1 leads Claude Fable 5 on coding, 84.2 to 79.3 on the Vibe Coding Index, at about the same output price ($50.00 vs $50.00 per million). Updated October 22, 2026; 112 benchmarks have a result for both.

Replace Claude Fable 5 Replace Claude Fable 5.1
Claude Fable 5Anthropic
Coding
79.3
Overall
79.0
Output $/M
$50.00
25
Claude Fable 5.1Anthropic
Coding
84.2
Overall
84.7
Output $/M
$50.00
86
vs boards won of 112 shared, 1 tied

Claude Fable 5 or Claude Fable 5.1: which to pick

Pick Claude Fable 5.1 for coding: it scores 84.2 on the Vibe Coding Index against 79.3 for Claude Fable 5, though on 5 benchmarks against 6.

Pick Claude Fable 5 for work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.

Model AClaude Fable 5Anthropic79.3/1006 independent benchmarks$2.16 per solved taskModel BClaude Fable 5.1Anthropic84.2/1005 independent benchmarksNo cost per solved task
Shared results
112
Claude Fable 5 only
15
Claude Fable 5.1 only
12
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Fable 5 79.3 from 6 benchmarks, Claude Fable 5.1 84.2 from 5 benchmarks.
Widest category
Agentic work, 7.1 points apart on average over 18 shared benchmarks.
Widest single gap
Furniture assembly: Claude Fable 5 35.8% against Claude Fable 5.1 70.0%, 34.2 points apart on a 0 to 100 scale.
Output price
Both cost $50.00 per million output tokens.
Context window
Both take 1M tokens.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Fable 5BarsClaude Fable 5.1Ties
Coding417
Intelligence02
Agentic work216
Reasoning312
Math141 tie
Knowledge37
Web design36
General922
All shared boards25861 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index417
Coding benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
LiveBench coding98.3%97.7%Claude Fable 5
LMArena WebDev16241743Claude Fable 5.1
AA Coding Index76.581.6Claude Fable 5.1
LiveCodeBench (Vals AI)89.8%90.5%Claude Fable 5.1
SWE-bench Verified (Vals AI)95.0%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 4 (Vals AI)41.4%58.1%Claude Fable 5.1
Vibe Code Bench (Vals AI)90.3%90.3%Claude Fable 5
Code migration (Vals AI)55.1%54.6%Claude Fable 5
ProgramBench (Vals AI)2.0%7.0%Claude Fable 5.1
IOI (Vals AI)Not measured90.8%Only Claude Fable 5.1 measured
Terminal-Bench 2.1 (Vals AI)80.5%85.0%Claude Fable 5.1
SWE-bench Multimodal (Vals AI)Not measured61.3%Only Claude Fable 5.1 measured
Vibe Code Bench 1-100 (Vals AI)Not measured28.0%Only Claude Fable 5.1 measured
SkillsBench (Vals AI)Not measured61.5%Only Claude Fable 5.1 measured
CyberBench (Vals AI)Not measured70.4%Only Claude Fable 5.1 measured
SciCode61.0%63.1%Claude Fable 5.1
Terminal-Bench Hard (Artificial Analysis run)62.9%Not measuredOnly Claude Fable 5 measured
FrontierCode53.5%50.9%Claude Fable 5
FrontierSWE47.0%56.3%Claude Fable 5.1
GSO-Bench78.4%88.2%Claude Fable 5.1
WeirdML91.9%92.9%Claude Fable 5.1
MirrorCode63.9%73.3%Claude Fable 5.1
ALE-Bench2041.32143.2Claude Fable 5.1
LMArena Text: coding15181532Claude Fable 5.1
LMArena Text: software and IT15131530Claude Fable 5.1
LMArena WebDev: React16311792Claude Fable 5.1
LMArena WebDev: HTML16511684Claude Fable 5.1
LMArena WebDev: from an image16231722Claude Fable 5.1
Neither model has a result on the other 11 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
AA Intelligence Index49.653.4Claude Fable 5.1
Epoch Capabilities Index163.4166.5Claude Fable 5.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index216
Agentic work benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
AA Agentic Index50.757.9Claude Fable 5.1
Design Arena: agents building web apps12611318Claude Fable 5.1
Design Arena: agents building full-stack apps12801326Claude Fable 5.1
Design Arena: agents building mobile apps12641267Claude Fable 5.1
Design Arena: agents building Android apps1284Not measuredOnly Claude Fable 5 measured
Design Arena: agents building Godot games12921327Claude Fable 5.1
Design Arena: agents building games1285Not measuredOnly Claude Fable 5 measured
Design Arena: HTML slides1227Not measuredOnly Claude Fable 5 measured
Design Arena: PowerPoint slides12701305Claude Fable 5.1
Design Arena: spreadsheetsNot measured1380Only Claude Fable 5.1 measured
LiveBench research86.9%82.0%Claude Fable 5
LiveBench browser92.0%100.0%Claude Fable 5.1
LiveBench long agentic53.2%80.8%Claude Fable 5.1
SREBench (Vals AI)Not measured22.9%Only Claude Fable 5.1 measured
Finance Agent (Vals AI)56.3%58.9%Claude Fable 5.1
Tax Agent Bench (Vals AI)38.3%49.2%Claude Fable 5.1
Legal Research Bench (Vals AI)49.5%55.3%Claude Fable 5.1
Excel Modeling Benchmark (Vals AI)73.7%76.7%Claude Fable 5.1
Terminal-Bench-Science (Vals AI)15.7%40.0%Claude Fable 5.1
Time Horizon Index (Vals AI)Not measured63.3%Only Claude Fable 5.1 measured
CUA-bench (Vals AI)Not measured13.2%Only Claude Fable 5.1 measured
Robo-bench (Vals AI)Not measured5.8%Only Claude Fable 5.1 measured
τ²-Bench Telecom98.5%Not measuredOnly Claude Fable 5 measured
APEX-Agents63.6%68.6%Claude Fable 5.1
Remote Labor Index16.1%17.9%Claude Fable 5.1
PostTrainBench41.8%Not measuredOnly Claude Fable 5 measured
SpireClimbNot measured2.0%Only Claude Fable 5.1 measured
Vending-Bench 2$5,680$5,422Claude Fable 5
LMArena Search12291246Claude Fable 5.1
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index312
Reasoning benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
GPQA Diamond93.2%93.4%Claude Fable 5.1
LiveBench reasoning89.7%91.7%Claude Fable 5.1
MysteryMechanism (Vals AI)Not measured47.8%Only Claude Fable 5.1 measured
MMMU Pro (Vals AI)89.3%90.6%Claude Fable 5.1
GPQA Diamond (Artificial Analysis run)92.6%93.7%Claude Fable 5.1
Humanity's Last Exam (Artificial Analysis run)55.5%59.1%Claude Fable 5.1
GPQA Diamond (Epoch AI run)85.9%Not measuredOnly Claude Fable 5 measured
ARC-AGI98.5%97.5%Claude Fable 5
ARC-AGI-289.2%90.0%Claude Fable 5.1
SimpleBench81.9%Not measuredOnly Claude Fable 5 measured
Chess puzzles47.0%48.0%Claude Fable 5.1
Mystery game puzzles52.0%58.0%Claude Fable 5.1
EBR-bench39.5%57.1%Claude Fable 5.1
LMArena Text: hard prompts15071528Claude Fable 5.1
LMArena Text: expert15341544Claude Fable 5.1
LMArena Text: hard prompts in English15091522Claude Fable 5.1
LMArena Vision: diagrams13571343Claude Fable 5
LMArena Vision: homework13611345Claude Fable 5
Kagi LLM Benchmark91.4%Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index14
Math benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
OTIS Mock AIME100.0%100.0%Tie
FrontierMath, tiers 1 to 387.0%90.2%Claude Fable 5.1
FrontierMath, tier 490.2%87.8%Claude Fable 5
ProofBench95.0%100.0%Claude Fable 5.1
LMArena Text: math15161531Claude Fable 5.1
LMArena Text: mathematical work15151541Claude Fable 5.1
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index37
Knowledge benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
MMLU Pro91.5%92.4%Claude Fable 5.1
LegalBench (Vals AI)88.6%88.5%Claude Fable 5
CorpFin (Vals AI)71.8%Not measuredOnly Claude Fable 5 measured
TaxEval (Vals AI)76.9%76.0%Claude Fable 5
MortgageTax (Vals AI)68.9%70.8%Claude Fable 5.1
MedCode (Vals AI)56.1%53.5%Claude Fable 5
SimpleQA Verified70.7%70.8%Claude Fable 5.1
LMArena Text: science15061532Claude Fable 5.1
LMArena Text: medicine and healthcare14801531Claude Fable 5.1
LMArena Text: legal and government14981514Claude Fable 5.1
LMArena Text: business and finance14801493Claude Fable 5.1
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index36
Web design benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
Design Arena: websites12951312Claude Fable 5.1
Design Arena: UI components13161336Claude Fable 5.1
Design Arena: game dev13351381Claude Fable 5.1
Design Arena: data viz13041344Claude Fable 5.1
Design Arena: 3D13181392Claude Fable 5.1
Design Arena: all code categories13101335Claude Fable 5.1
Design Arena: SVG13021300Claude Fable 5
Design Arena: ASCII art13291323Claude Fable 5
LiveBench design84.7%83.4%Claude Fable 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index922
General benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
LiveBench data analysis80.5%80.3%Claude Fable 5
Public Benefits Bench (Vals AI)70.4%74.9%Claude Fable 5.1
SAGE (Vals AI)51.9%48.5%Claude Fable 5
MedScribe (Vals AI)88.5%91.3%Claude Fable 5.1
Vals Multimodal Index74.2%Not measuredOnly Claude Fable 5 measured
IFBench63.5%Not measuredOnly Claude Fable 5 measured
Long context reasoning (AA-LCR)82.3%85.3%Claude Fable 5.1
DTBench98.4%97.6%Claude Fable 5
LMCA61.2%65.5%Claude Fable 5.1
Surface Evolver Bench95.0%Not measuredOnly Claude Fable 5 measured
Furniture assembly35.8%70.0%Claude Fable 5.1
LMArena Text14911512Claude Fable 5.1
LMArena Text: instruction following15021518Claude Fable 5.1
LMArena Text: creative writing14941509Claude Fable 5.1
LMArena Vision13251319Claude Fable 5
LMArena Text: English14981506Claude Fable 5.1
LMArena Text: non-English14821508Claude Fable 5.1
LMArena Text: Chinese15431584Claude Fable 5.1
LMArena Text: German14861499Claude Fable 5.1
LMArena Text: Japanese15041562Claude Fable 5.1
LMArena Text: Korean14871517Claude Fable 5.1
LMArena Text: French15051523Claude Fable 5.1
LMArena Text: Spanish14981520Claude Fable 5.1
LMArena Text: Russian15031520Claude Fable 5.1
LMArena Text: Polish14941525Claude Fable 5.1
LMArena Text: multi-turn15041493Claude Fable 5
LMArena Text: longer queries15101524Claude Fable 5.1
LMArena Text: writing and language15011510Claude Fable 5.1
LMArena Text: entertainment and media14821497Claude Fable 5.1
LMArena Vision: English13231313Claude Fable 5
LMArena Vision: Chinese13731391Claude Fable 5.1
LMArena Vision: reading text13371327Claude Fable 5
LMArena Vision: humor13411318Claude Fable 5
LMArena Vision: creative writing13381330Claude Fable 5
LMArena Document1496Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Fable 5 and Claude Fable 5.1
BenchmarkClaude Fable 5Claude Fable 5.1Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Fable 5$0.035Fits in one request
Claude Fable 5.1$0.035Fits in one request

Same cost

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
Claude Fable 5.1$0.650Fits in one request

Same cost

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits in one request
Claude Fable 5.1$2.50Fits in one request

Same cost

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Fable 5 and Claude Fable 5.1
SpecificationAnthropic Claude Fable 5Anthropic Claude Fable 5.1
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedJune 9, 2026September 1, 2026
Context window1M1M
Input $/Mtok$10.00$10.00
Output $/Mtok$50.00$50.00
Coding index79.384.2
Independent measurements behind it65
Cost per solved task$2.16Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5 better than Claude Fable 5.1 for coding?

Pick Claude Fable 5.1 for coding: it scores 84.2 on the Vibe Coding Index against 79.3 for Claude Fable 5, though on 5 benchmarks against 6. Pick Claude Fable 5 for work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.

Which is cheaper, Claude Fable 5 or Claude Fable 5.1?

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Claude Fable 5.1 costs $10.00 and $50.00. Cost per solved task is known for Claude Fable 5 only.

Which has the bigger context window, Claude Fable 5 or Claude Fable 5.1?

Neither: both take 1M tokens.

How many benchmarks is the Claude Fable 5 vs Claude Fable 5.1 comparison based on?

112 benchmarks have a result for both models as of October 22, 2026. Claude Fable 5's coding index rests on 6 independent benchmarks and Claude Fable 5.1's on 5. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-fable-5-vs-claude-fable-5-1" title="Claude Fable 5 vs Claude Fable 5.1, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-fable-5-vs-claude-fable-5-1">LLMBenchmark.ai, Claude Fable 5 vs Claude Fable 5.1</a></p>