LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs Claude Sonnet 5

Updated October 21, 2026. 114 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Fable 5 Replace Claude Sonnet 5
Claude Fable 5Anthropic
Coding
82.1
Overall
49.6
Output $/M
$50.00
111
Claude Sonnet 5Anthropic
Coding
63.5
Overall
38.2
Output $/M
$10.00
3
vs boards won of 114 shared

Decision reading

Pick Claude Fable 5 for coding: it scores 82.1 on the Vibe Coding Index against 63.5 for Claude Sonnet 5.

Pick Claude Sonnet 5 when output tokens cost 5.0x less, or when a solved task costs $1.87 against $2.16.

Model AClaude Fable 5Anthropic82.1/1002 independent benchmarks$2.16 per solved taskModel BClaude Sonnet 5Anthropic63.5/1002 independent benchmarks$1.87 per solved task
Shared results
114
Claude Fable 5 only
12
Claude Sonnet 5 only
6
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 82.1 from 2 benchmarks, Claude Sonnet 5 63.5 from 2 benchmarks.
Widest category
Math, 19.9 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Claude Fable 5 90.2% against Claude Sonnet 5 29.3%, 60.9 points apart on a 0 to 100 scale.
Output price
Claude Fable 5 $50.00 against Claude Sonnet 5 $10.00 per million output tokens, 5.0x apart.
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 Sonnet 5Ties
Coding200
Intelligence20
Agentic work181
Reasoning131
Math60
Knowledge101
Web design90
General330
All shared boards1113
CodingLike-for-likeFour of these boards feed the Vibe Coding Index200
Coding benchmarks for Claude Fable 5 and Claude Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
LiveBench coding98.3%74.7%Claude Fable 5
LMArena WebDev16241540Claude Fable 5
AA Coding Index76.571.5Claude Fable 5
LiveCodeBench (Vals AI)89.8%82.4%Claude Fable 5
SWE-bench Verified (Vals AI)95.0%79.6%Claude Fable 5
Terminal-Bench 4 (Vals AI)41.4%10.6%Claude Fable 5
Vibe Code Bench (Vals AI)90.3%81.3%Claude Fable 5
Code migration (Vals AI)55.1%44.4%Claude Fable 5
ProgramBench (Vals AI)2.0%0.0%Claude Fable 5
IOI (Vals AI)Not measured45.0%Only Claude Sonnet 5 measured
Terminal-Bench 2.1 (Vals AI)80.5%74.5%Claude Fable 5
Vibe Code Bench 1-100 (Vals AI)Not measured13.8%Only Claude Sonnet 5 measured
SkillsBench (Vals AI)Not measured46.5%Only Claude Sonnet 5 measured
CyberBench (Vals AI)Not measured70.3%Only Claude Sonnet 5 measured
SciCode61.0%54.3%Claude Fable 5
Terminal-Bench Hard (Artificial Analysis run)62.9%Not measuredOnly Claude Fable 5 measured
FrontierCode53.5%42.7%Claude Fable 5
FrontierSWE47.0%Not measuredOnly Claude Fable 5 measured
GSO-Bench78.4%37.3%Claude Fable 5
WeirdML91.9%68.8%Claude Fable 5
MirrorCode63.9%Not measuredOnly Claude Fable 5 measured
ALE-Bench2041.31463.1Claude Fable 5
LMArena Text: coding15181483Claude Fable 5
LMArena Text: software and IT15131474Claude Fable 5
LMArena WebDev: React16311541Claude Fable 5
LMArena WebDev: HTML16511527Claude Fable 5
LMArena WebDev: from an image16231540Claude Fable 5
Neither model has a result on the other 11 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Fable 5 and Claude Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
AA Intelligence Index49.638.2Claude Fable 5
Epoch Capabilities Index163.4156.9Claude Fable 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index181
Agentic work benchmarks for Claude Fable 5 and Claude Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
AA Agentic Index50.743.6Claude Fable 5
Design Arena: agents building web apps12611245Claude Fable 5
Design Arena: agents building full-stack apps12801249Claude Fable 5
Design Arena: agents building mobile apps12641215Claude Fable 5
Design Arena: agents building Android apps12891231Claude Fable 5
Design Arena: agents building Godot games12921225Claude Fable 5
Design Arena: agents building games12851227Claude Fable 5
Design Arena: HTML slides12771218Claude Fable 5
Design Arena: PowerPoint slides12951216Claude Fable 5
Design Arena: spreadsheetsNot measured1004Only Claude Sonnet 5 measured
LiveBench research86.9%82.8%Claude Fable 5
LiveBench browser92.0%72.0%Claude Fable 5
LiveBench long agentic53.2%39.0%Claude Fable 5
SREBench (Vals AI)Not measured0.4%Only Claude Sonnet 5 measured
Finance Agent (Vals AI)56.3%53.9%Claude Fable 5
Tax Agent Bench (Vals AI)38.3%29.4%Claude Fable 5
Legal Research Bench (Vals AI)49.5%41.8%Claude Fable 5
Excel Modeling Benchmark (Vals AI)73.7%66.3%Claude Fable 5
Terminal-Bench-Science (Vals AI)15.7%5.7%Claude Fable 5
τ²-Bench Telecom98.5%Not measuredOnly Claude Fable 5 measured
APEX-Agents63.6%54.5%Claude Fable 5
Remote Labor Index16.1%Not measuredOnly Claude Fable 5 measured
PostTrainBench41.8%Not measuredOnly Claude Fable 5 measured
Vending-Bench 2$5,680$6,378Claude Sonnet 5
LMArena Search1229Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index131
Reasoning benchmarks for Claude Fable 5 and Claude Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
GPQA Diamond93.2%88.9%Claude Fable 5
LiveBench reasoning89.7%88.7%Claude Fable 5
MMMU Pro (Vals AI)89.3%83.0%Claude Fable 5
GPQA Diamond (Artificial Analysis run)92.6%91.1%Claude Fable 5
Humanity's Last Exam (Artificial Analysis run)55.5%41.3%Claude Fable 5
GPQA Diamond (Epoch AI run)85.9%90.5%Claude Sonnet 5
ARC-AGI98.5%Not measuredOnly Claude Fable 5 measured
ARC-AGI-289.2%Not measuredOnly Claude Fable 5 measured
SimpleBench81.9%60.6%Claude Fable 5
Chess puzzles47.0%45.0%Claude Fable 5
Mystery game puzzles52.0%35.0%Claude Fable 5
EBR-bench39.5%Not measuredOnly Claude Fable 5 measured
LMArena Text: hard prompts15071461Claude Fable 5
LMArena Text: expert15341489Claude Fable 5
LMArena Text: hard prompts in English15091464Claude Fable 5
LMArena Vision: diagrams13571293Claude Fable 5
LMArena Vision: homework13611311Claude Fable 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Fable 5 and Claude Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
OTIS Mock AIME100.0%94.7%Claude Fable 5
FrontierMath, tiers 1 to 387.0%65.6%Claude Fable 5
FrontierMath, tier 490.2%29.3%Claude Fable 5
ProofBench95.0%77.0%Claude Fable 5
LMArena Text: math15161467Claude Fable 5
LMArena Text: mathematical work15151481Claude Fable 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
Knowledge benchmarks for Claude Fable 5 and Claude Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
MMLU Pro91.5%87.5%Claude Fable 5
LegalBench (Vals AI)88.6%83.9%Claude Fable 5
CorpFin (Vals AI)71.8%67.0%Claude Fable 5
TaxEval (Vals AI)76.9%75.6%Claude Fable 5
MortgageTax (Vals AI)68.9%70.0%Claude Sonnet 5
MedCode (Vals AI)56.1%47.5%Claude Fable 5
SimpleQA Verified70.7%33.7%Claude Fable 5
LMArena Text: science15061460Claude Fable 5
LMArena Text: medicine and healthcare14801442Claude Fable 5
LMArena Text: legal and government14981454Claude Fable 5
LMArena Text: business and finance14801436Claude Fable 5
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for Claude Fable 5 and Claude Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
Design Arena: websites12961274Claude Fable 5
Design Arena: UI components13181279Claude Fable 5
Design Arena: game dev13361278Claude Fable 5
Design Arena: data viz13041251Claude Fable 5
Design Arena: 3D13191261Claude Fable 5
Design Arena: all code categories13101276Claude Fable 5
Design Arena: SVG13021193Claude Fable 5
Design Arena: ASCII art13281207Claude Fable 5
LiveBench design84.7%82.0%Claude Fable 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index330
General benchmarks for Claude Fable 5 and Claude Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
LiveBench data analysis80.5%71.7%Claude Fable 5
Public Benefits Bench (Vals AI)70.4%66.0%Claude Fable 5
SAGE (Vals AI)51.9%48.9%Claude Fable 5
MedScribe (Vals AI)88.5%76.0%Claude Fable 5
Vals Multimodal Index74.2%68.8%Claude Fable 5
IFBench63.5%Not measuredOnly Claude Fable 5 measured
Long context reasoning (AA-LCR)82.3%82.0%Claude Fable 5
DTBench98.4%92.5%Claude Fable 5
LMCA61.2%50.0%Claude Fable 5
Surface Evolver Bench95.0%60.0%Claude Fable 5
Furniture assembly35.8%Not measuredOnly Claude Fable 5 measured
LMArena Text14911442Claude Fable 5
LMArena Text: instruction following15021452Claude Fable 5
LMArena Text: creative writing14941416Claude Fable 5
LMArena Vision13251273Claude Fable 5
LMArena Text: English14981450Claude Fable 5
LMArena Text: non-English14821431Claude Fable 5
LMArena Text: Chinese15431478Claude Fable 5
LMArena Text: German14861442Claude Fable 5
LMArena Text: Japanese15041422Claude Fable 5
LMArena Text: Korean14871412Claude Fable 5
LMArena Text: French15051463Claude Fable 5
LMArena Text: Spanish14981438Claude Fable 5
LMArena Text: Russian15031450Claude Fable 5
LMArena Text: Polish14941425Claude Fable 5
LMArena Text: multi-turn15041453Claude Fable 5
LMArena Text: longer queries15101462Claude Fable 5
LMArena Text: writing and language15011436Claude Fable 5
LMArena Text: entertainment and media14821411Claude Fable 5
LMArena Vision: English13231275Claude Fable 5
LMArena Vision: Chinese13731331Claude Fable 5
LMArena Vision: reading text13371288Claude Fable 5
LMArena Vision: humor13411261Claude Fable 5
LMArena Vision: creative writing13381246Claude Fable 5
LMArena Document14961466Claude Fable 5
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 Sonnet 5
BenchmarkClaude Fable 5Claude Sonnet 5Leader
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 Sonnet 5$0.0070Fits in one request

Claude Sonnet 5 costs less

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
Claude Sonnet 5$0.130Fits in one request

Claude Sonnet 5 costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits in one request
Claude Sonnet 5$0.500Fits in one request

Claude Sonnet 5 costs less

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 Sonnet 5
SpecificationAnthropic Claude Fable 5Anthropic Claude Sonnet 5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedJune 9, 2026June 30, 2026
Context window1M1M
Input $/Mtok$10.00$2.00
Output $/Mtok$50.00$10.00
Coding index82.163.5
Independent measurements behind it22
Cost per solved task$2.16$1.87
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Claude Fable 5 for coding: it scores 82.1 on the Vibe Coding Index against 63.5 for Claude Sonnet 5. Pick Claude Sonnet 5 when output tokens cost 5.0x less, or when a solved task costs $1.87 against $2.16.

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

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Claude Sonnet 5 costs $2.00 and $10.00. Per solved SWE-bench Verified task, Claude Fable 5 costs $2.16 and Claude Sonnet 5 $1.87.

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

Neither: both take 1M tokens.

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

114 benchmarks have a result for both models as of October 21, 2026. Claude Fable 5's coding index rests on 2 independent benchmarks and Claude Sonnet 5's on 2. 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-sonnet-5" title="Claude Fable 5 vs Claude Sonnet 5, 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-sonnet-5">LLMBenchmark.ai, Claude Fable 5 vs Claude Sonnet 5</a></p>