LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Fable 5.1 vs Claude Sonnet 5

Updated October 21, 2026. 110 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Fable 5.1 Replace Claude Sonnet 5
Claude Fable 5.1Anthropic
Coding
89.1
Overall
53.4
Output $/M
$50.00
107
Claude Sonnet 5Anthropic
Coding
63.5
Overall
38.2
Output $/M
$10.00
3
vs boards won of 110 shared

Decision reading

Pick Claude Fable 5.1 for coding: it scores 89.1 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 what matters is LiveBench research or Vending-Bench 2, where it leads.

Model AClaude Fable 5.1Anthropic89.1/1002 independent benchmarksNo cost per solved taskModel BClaude Sonnet 5Anthropic63.5/1002 independent benchmarks$1.87 per solved task
Shared results
110
Claude Fable 5.1 only
14
Claude Sonnet 5 only
10
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 5.1 89.1 from 2 benchmarks, Claude Sonnet 5 63.5 from 2 benchmarks.
Widest category
Math, 22.0 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Claude Fable 5.1 87.8% against Claude Sonnet 5 29.3%, 58.5 points apart on a 0 to 100 scale.
Output price
Claude Fable 5.1 $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 5.1BarsClaude Sonnet 5Ties
Coding230
Intelligence20
Agentic work162
Reasoning120
Math60
Knowledge100
Web design90
General291
All shared boards1073
CodingLike-for-likeFour of these boards feed the Vibe Coding Index230
Coding benchmarks for Claude Fable 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude Sonnet 5Leader
LiveBench coding97.7%74.7%Claude Fable 5.1
LMArena WebDev17431540Claude Fable 5.1
AA Coding Index81.671.5Claude Fable 5.1
LiveCodeBench (Vals AI)90.5%82.4%Claude Fable 5.1
SWE-bench Verified (Vals AI)Not measured79.6%Only Claude Sonnet 5 measured
Terminal-Bench 4 (Vals AI)58.1%10.6%Claude Fable 5.1
Vibe Code Bench (Vals AI)90.3%81.3%Claude Fable 5.1
Code migration (Vals AI)54.6%44.4%Claude Fable 5.1
ProgramBench (Vals AI)7.0%0.0%Claude Fable 5.1
IOI (Vals AI)90.8%45.0%Claude Fable 5.1
Terminal-Bench 2.1 (Vals AI)85.0%74.5%Claude Fable 5.1
SWE-bench Multimodal (Vals AI)61.3%Not measuredOnly Claude Fable 5.1 measured
Vibe Code Bench 1-100 (Vals AI)28.0%13.8%Claude Fable 5.1
SkillsBench (Vals AI)61.5%46.5%Claude Fable 5.1
CyberBench (Vals AI)70.4%70.3%Claude Fable 5.1
SciCode63.1%54.3%Claude Fable 5.1
FrontierCode50.9%42.7%Claude Fable 5.1
FrontierSWE56.3%Not measuredOnly Claude Fable 5.1 measured
GSO-Bench88.2%37.3%Claude Fable 5.1
WeirdML92.9%68.8%Claude Fable 5.1
MirrorCode73.3%Not measuredOnly Claude Fable 5.1 measured
ALE-Bench2143.21463.1Claude Fable 5.1
LMArena Text: coding15321483Claude Fable 5.1
LMArena Text: software and IT15301474Claude Fable 5.1
LMArena WebDev: React17921541Claude Fable 5.1
LMArena WebDev: HTML16841527Claude Fable 5.1
LMArena WebDev: from an image17221540Claude 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 index20
Intelligence benchmarks for Claude Fable 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude Sonnet 5Leader
AA Intelligence Index53.438.2Claude Fable 5.1
Epoch Capabilities Index166.5156.9Claude Fable 5.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index162
Agentic work benchmarks for Claude Fable 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude Sonnet 5Leader
AA Agentic Index57.943.6Claude Fable 5.1
Design Arena: agents building web apps13181245Claude Fable 5.1
Design Arena: agents building full-stack apps13261249Claude Fable 5.1
Design Arena: agents building mobile apps12671215Claude Fable 5.1
Design Arena: agents building Android appsNot measured1231Only Claude Sonnet 5 measured
Design Arena: agents building Godot games13271225Claude Fable 5.1
Design Arena: agents building gamesNot measured1227Only Claude Sonnet 5 measured
Design Arena: HTML slidesNot measured1218Only Claude Sonnet 5 measured
Design Arena: PowerPoint slides13281216Claude Fable 5.1
Design Arena: spreadsheets13741004Claude Fable 5.1
LiveBench research82.0%82.8%Claude Sonnet 5
LiveBench browser100.0%72.0%Claude Fable 5.1
LiveBench long agentic80.8%39.0%Claude Fable 5.1
SREBench (Vals AI)22.9%0.4%Claude Fable 5.1
Finance Agent (Vals AI)58.9%53.9%Claude Fable 5.1
Tax Agent Bench (Vals AI)49.2%29.4%Claude Fable 5.1
Legal Research Bench (Vals AI)55.3%41.8%Claude Fable 5.1
Excel Modeling Benchmark (Vals AI)76.7%66.3%Claude Fable 5.1
Terminal-Bench-Science (Vals AI)40.0%5.7%Claude Fable 5.1
Time Horizon Index (Vals AI)63.3%Not measuredOnly Claude Fable 5.1 measured
CUA-bench (Vals AI)13.2%Not measuredOnly Claude Fable 5.1 measured
Robo-bench (Vals AI)5.8%Not measuredOnly Claude Fable 5.1 measured
APEX-Agents68.6%54.5%Claude Fable 5.1
Remote Labor Index17.9%Not measuredOnly Claude Fable 5.1 measured
SpireClimb2.0%Not measuredOnly Claude Fable 5.1 measured
Vending-Bench 2$5,422$6,378Claude Sonnet 5
LMArena Search1246Not measuredOnly Claude Fable 5.1 measured
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
Reasoning benchmarks for Claude Fable 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude Sonnet 5Leader
GPQA Diamond93.4%88.9%Claude Fable 5.1
LiveBench reasoning91.7%88.7%Claude Fable 5.1
MysteryMechanism (Vals AI)47.8%Not measuredOnly Claude Fable 5.1 measured
MMMU Pro (Vals AI)90.6%83.0%Claude Fable 5.1
GPQA Diamond (Artificial Analysis run)93.7%91.1%Claude Fable 5.1
Humanity's Last Exam (Artificial Analysis run)59.1%41.3%Claude Fable 5.1
GPQA Diamond (Epoch AI run)Not measured90.5%Only Claude Sonnet 5 measured
ARC-AGI97.5%Not measuredOnly Claude Fable 5.1 measured
ARC-AGI-290.0%Not measuredOnly Claude Fable 5.1 measured
SimpleBenchNot measured60.6%Only Claude Sonnet 5 measured
Chess puzzles48.0%45.0%Claude Fable 5.1
Mystery game puzzles58.0%35.0%Claude Fable 5.1
EBR-bench57.1%Not measuredOnly Claude Fable 5.1 measured
LMArena Text: hard prompts15281461Claude Fable 5.1
LMArena Text: expert15441489Claude Fable 5.1
LMArena Text: hard prompts in English15221464Claude Fable 5.1
LMArena Vision: diagrams13431293Claude Fable 5.1
LMArena Vision: homework13451311Claude Fable 5.1
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Fable 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude Sonnet 5Leader
OTIS Mock AIME100.0%94.7%Claude Fable 5.1
FrontierMath, tiers 1 to 390.2%65.6%Claude Fable 5.1
FrontierMath, tier 487.8%29.3%Claude Fable 5.1
ProofBench100.0%77.0%Claude Fable 5.1
LMArena Text: math15311467Claude Fable 5.1
LMArena Text: mathematical work15411481Claude 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 index100
Knowledge benchmarks for Claude Fable 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude Sonnet 5Leader
MMLU Pro92.4%87.5%Claude Fable 5.1
LegalBench (Vals AI)88.5%83.9%Claude Fable 5.1
CorpFin (Vals AI)Not measured67.0%Only Claude Sonnet 5 measured
TaxEval (Vals AI)76.0%75.6%Claude Fable 5.1
MortgageTax (Vals AI)70.8%70.0%Claude Fable 5.1
MedCode (Vals AI)53.5%47.5%Claude Fable 5.1
SimpleQA Verified70.8%33.7%Claude Fable 5.1
LMArena Text: science15321460Claude Fable 5.1
LMArena Text: medicine and healthcare15311442Claude Fable 5.1
LMArena Text: legal and government15141454Claude Fable 5.1
LMArena Text: business and finance14931436Claude Fable 5.1
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 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude Sonnet 5Leader
Design Arena: websites13131274Claude Fable 5.1
Design Arena: UI components13381279Claude Fable 5.1
Design Arena: game dev13821278Claude Fable 5.1
Design Arena: data viz13441251Claude Fable 5.1
Design Arena: 3D13931261Claude Fable 5.1
Design Arena: all code categories13361276Claude Fable 5.1
Design Arena: SVG13011193Claude Fable 5.1
Design Arena: ASCII art13241207Claude Fable 5.1
LiveBench design83.4%82.0%Claude Fable 5.1
GeneralLike-for-likePublic boards, shown as published, kept out of the index291
General benchmarks for Claude Fable 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude Sonnet 5Leader
LiveBench data analysis80.3%71.7%Claude Fable 5.1
Public Benefits Bench (Vals AI)74.9%66.0%Claude Fable 5.1
SAGE (Vals AI)48.5%48.9%Claude Sonnet 5
MedScribe (Vals AI)91.3%76.0%Claude Fable 5.1
Vals Multimodal IndexNot measured68.8%Only Claude Sonnet 5 measured
Long context reasoning (AA-LCR)85.3%82.0%Claude Fable 5.1
DTBench97.6%92.5%Claude Fable 5.1
LMCA65.5%50.0%Claude Fable 5.1
Surface Evolver BenchNot measured60.0%Only Claude Sonnet 5 measured
Furniture assembly70.0%Not measuredOnly Claude Fable 5.1 measured
LMArena Text15121442Claude Fable 5.1
LMArena Text: instruction following15181452Claude Fable 5.1
LMArena Text: creative writing15091416Claude Fable 5.1
LMArena Vision13191273Claude Fable 5.1
LMArena Text: English15061450Claude Fable 5.1
LMArena Text: non-English15081431Claude Fable 5.1
LMArena Text: Chinese15841478Claude Fable 5.1
LMArena Text: German14991442Claude Fable 5.1
LMArena Text: Japanese15621422Claude Fable 5.1
LMArena Text: Korean15171412Claude Fable 5.1
LMArena Text: French15231463Claude Fable 5.1
LMArena Text: Spanish15201438Claude Fable 5.1
LMArena Text: Russian15201450Claude Fable 5.1
LMArena Text: Polish15251425Claude Fable 5.1
LMArena Text: multi-turn14931453Claude Fable 5.1
LMArena Text: longer queries15241462Claude Fable 5.1
LMArena Text: writing and language15101436Claude Fable 5.1
LMArena Text: entertainment and media14971411Claude Fable 5.1
LMArena Vision: English13131275Claude Fable 5.1
LMArena Vision: Chinese13911331Claude Fable 5.1
LMArena Vision: reading text13271288Claude Fable 5.1
LMArena Vision: humor13181261Claude Fable 5.1
LMArena Vision: creative writing13301246Claude Fable 5.1
LMArena DocumentNot measured1466Only Claude Sonnet 5 measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Fable 5.1 and Claude Sonnet 5
BenchmarkClaude Fable 5.1Claude 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 5.1$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 5.1$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 5.1$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 5.1 and Claude Sonnet 5
SpecificationAnthropic Claude Fable 5.1Anthropic Claude Sonnet 5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 1, 2026June 30, 2026
Context window1M1M
Input $/Mtok$10.00$2.00
Output $/Mtok$50.00$10.00
Coding index89.163.5
Independent measurements behind it22
Cost per solved taskNot computable$1.87
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Claude Fable 5.1 for coding: it scores 89.1 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 what matters is LiveBench research or Vending-Bench 2, where it leads.

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

Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; Claude Sonnet 5 costs $2.00 and $10.00. Cost per solved task is known for Claude Sonnet 5 only.

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

Neither: both take 1M tokens.

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

110 benchmarks have a result for both models as of October 21, 2026. Claude Fable 5.1'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-5-1-vs-claude-sonnet-5" title="Claude Fable 5.1 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-5-1-vs-claude-sonnet-5">LLMBenchmark.ai, Claude Fable 5.1 vs Claude Sonnet 5</a></p>