Skip to main content

AnthropicLLM matchup

Claude Haiku 5.5vs.Claude Fable 5

Is the higher price worth it?

Claude Fable 5 performs better than Claude Haiku 5.5, but costs 100 times as much.

Fable 5 ahead
IntelligenceOverall index, 100 points = average
103.4

Claude Haiku 5.5

Rank 20

112.5

Claude Fable 5

Rank 12

Haiku 5.5 faster
SpeedTokens per second
236

Claude Haiku 5.5

86

Claude Fable 5

Haiku 5.5 cheaper
Price$ per 1M tokens
$0.20

Claude Haiku 5.5

$20

Claude Fable 5

Haiku 5.5 more popular
Popularity0 to 100
77

Claude Haiku 5.5

Rank 3 of 875

45

Claude Fable 5

Rank 173 of 875

Above 100,000 tokens of context, Claude Haiku 5.5 costs more: $0.50 input and $2.50 output per 1M tokens.

Choose Claude Haiku 5.5 for

No clear advantage

Choose Claude Fable 5 for

KnowledgeLegalProductivityMathematicsHealthFinanceCodingAgents (not certain)

Where is the difference?

Strengths at a glance

Haiku 5.5Fable 5

The median of all ranked models is below 100 in every area, so it sits in the centre of the net.

105110115120100CodingFable 5ReasoninglevelMathematicsFable 5KnowledgeFable 5Agentsslightly Fable 5GenerallevelFinanceFable 5LegalFable 5HealthFable 5
CodingFable 5 ahead
Haiku 5.5106.2Rank 18
Fable 5112.6Rank 14
Median of ranked models83.7

95 % range: Haiku 5.5 102.5 to 109.9, Fable 5 109.4 to 115.8.

AreaHaiku 5.5Fable 5

The same values and verdicts as the bars below. In the top field the net starts at 100 points, the reference group average; values below sit as a hollow point in the centre. Not in the net because a model has no own value there or the data are too thin: Multimodal.

Fable 5 is ahead in 6 of 10 areas, Haiku 5.5 in none.

level: 2too little data: 1Fable 5 slightly ahead: 1Fable 5 ahead: 6

Areas in the overall index
KnowledgeFable 5 +2885.5 to 113.5
MathematicsFable 5 +10107.1 to 117.5
CodingFable 5 +6106.2 to 112.6
Agentsleaning Fable 5not certain · 4 and 2 tests
Generallevel106.4 to 104.0
Reasoninglevel105.2 to 104.4
Multimodalonly Fable 5 has a score
Specialist fields
LegalFable 5 +1694.4 to 110.9
HealthFable 5 +7108.9 to 116.0
FinanceFable 5 +7104.7 to 111.8

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 4 more areas that do not count toward the overall index
ProductivityFable 5 +14101.8 to 115.9
Cybersecurityonly Haiku 5.5 has a score
Searchonly Fable 5 has a score
Educationonly Haiku 5.5 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.

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 5Coding 106.2 to 112.6
Maths and data analysisFable 5Mathematics 107.1 to 117.5, Reasoning 105.2 to 104.4
Facts and researchFable 5Knowledge 85.5 to 113.5, Search without a score for Haiku 5.5
Agents and workflowsleaning Fable 5Agents 106.1 to 111.0
Fast chat repliesHaiku 5.5236 to 86 tokens per second
Security analysisopenCybersecurity without a score for Fable 5
Many requests on a small budgetHaiku 5.5$0.20 to $20 per 1M tokens
Finance, legal and medical textsFable 5Finance 104.7 to 111.8, Legal 94.4 to 110.9, Health 108.9 to 116.0
Images, screenshots and PDFsopenMultimodal without a score for Haiku 5.5

See for yourself: same task, one attempt

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 Haiku 5.5

Not tested yet

Claude Fable 5

Claude Fable 5: Pelican on a bicycle
A community classic for free-form SVG drawing.

Sep 7, 2026 · 53 s · $0.11

Test details
Run date
Sep 7, 2026
API provider
openrouter
Requested API model
anthropic/claude-fable-5
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
2,287 tokens
Cost of the attempt
$0.1146
Response time
53.1 s
API model reported in response
anthropic/claude-fable-5
Pinned endpoint
Anthropic | anthropic/claude-5-fable-20260609
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

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

Claude Haiku 5.5

Unavailable in this round

Claude Fable 5

Unavailable in this round

Claude Haiku 5.5 and Claude Fable 5 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 v4)

20 of 91 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 Opus 5.5max126.1
Gemini 4 Carbonhigh125.7
Claude Fable 5.1max123.8
Claude Sonnet 5.5max122.8
Gemini 4 Argonhigh122.3
GPT-6 Astramax121.3
GPT-6.1 Solmax119.2
Muse Wonder Fullmax118.3
Claude Opus 5max117.2
Muse Wondermax113.4
Kimi K3.1 Promax112.9
Claude Fable 5max112.5
GPT-6 Solmax110.6
GPT-5.6 Solmax108.7
Muse Spark 1.3max107.4
Gemini 3.7 Flashhigh107.1
DeepSeek V4.1 Flash 1017max106.6
Gemini 3.8 Flashhigh106.5
GPT-6.1 Terramax105.2
Claude Haiku 5.5max103.4

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

Claude Haiku 5.5 is more popular than Claude Fable 5: 77 to 45 out of 100.

Over time

Weekly values from October 18, 2026 to November 5, 2026

Claude Haiku 5.5Claude Fable 5

All data side by side

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

MetricClaude Haiku 5.5Claude Fable 5
Intelligence
Overall indexpoints, 100 = reference group average, higher is better103.4112.5
RankRank 20 of 91Rank 12 of 91
Price per 1M tokens
Inputwhat you send$0.10above 100,000 tokens: $0.50$10
Outputwhat the model writes$0.50above 100,000 tokens: $2.50$50
Speed
Tokens per second23686
Popularity
Popularitysearch, usage and mentions, 0 to 10077Rank 3 of 87545Rank 173 of 875
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages1 M tokens≈ 1,500 A4 pages
Knowledge cutoffJune 2026January 2026
ReleasedOct 7, 2026Jun 9, 2026
AvailabilityActiveActive
Open weightsnono

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

Is there a better choice?

Successor of Fable 5Claude Fable 5.1

Overall index 123.8, rank 3. $10 input and $50 output per 1M tokens.

Haiku 5.5 vs. Claude Fable 5.1
Best model in the overall indexClaude Opus 5.5

Overall index 126.1, rank 1. $4 input and $20 output per 1M tokens.

Fable 5 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 Haiku 5.5B: Claude Fable 5

Code MigrationOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44.6%Claude Fable 5: 55.1%Vals AIAs of 10/29/2026
EMBOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 59%Claude Fable 5: 73.7%Vals AIAs of 10/20/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 54.1%Claude Fable 5: 56.3%Vals AIAs of 10/29/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 43.8%Claude Fable 5: 49.5%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevOverall · higher is betterClaude Haiku 5.5: 1,589Claude Fable 5: 1,624LMArenaAs of 10/28/2026
LMArena Text, Style ControlOverall · higher is betterClaude Haiku 5.5: 1,425Claude Fable 5: 1,504LMArenaAs of 10/28/2026
MedCodeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 51.5%Claude Fable 5: 56.1%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89.5%Claude Fable 5: 88.5%Vals AIAs of 10/29/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%Claude Fable 5: 2%Vals AIAs of 11/05/2026
ProofBench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89%Claude Fable 5: 95%Vals AIAs of 10/29/2026
Show 54 more benchmarks
Public Benefits Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 63.2%Claude Fable 5: 70.4%Vals AIAs of 10/12/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 31.9%Claude Fable 5: 38.3%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.4%Claude Fable 5: 41.4%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 10%Claude Fable 5: 15.7%Vals AIAs of 11/05/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 90.4%Claude Fable 5: 90.4%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.1%Claude Fable 5: 60.1%Vals AIAs of 10/29/2026
EMBComps · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 77.9%Claude Fable 5: 70.8%Vals AIAs of 10/20/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 49.6%Claude Fable 5: 51.1%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 50%Claude Fable 5: 57.6%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevHTML development · higher is betterClaude Haiku 5.5: 1,568Claude Fable 5: 1,651LMArenaAs of 10/28/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterClaude Haiku 5.5: 1,435Claude Fable 5: 1,501LMArenaAs of 10/28/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 29.5%Claude Fable 5: 33%Vals AIAs of 11/05/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 6.7%Claude Fable 5: 13.3%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 20%Claude Fable 5: 40%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceEarth Sciences · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 0%Claude Fable 5: 25%Vals AIAs of 11/05/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 70%Claude Fable 5: 40%Vals AIAs of 10/29/2026
EMBDataroom · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 85.5%Claude Fable 5: 85.4%Vals AIAs of 10/20/2026
Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 42.9%Claude Fable 5: 45.7%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 88.7%Claude Fable 5: 90.2%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevReact development · higher is betterClaude Haiku 5.5: 1,608Claude Fable 5: 1,630LMArenaAs of 10/28/2026
LMArena Text, Style ControlChinese · higher is betterClaude Haiku 5.5: 1,468Claude Fable 5: 1,555LMArenaAs of 10/28/2026
ProgramBenchFully Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%Claude Fable 5: 2%Vals AIAs of 11/05/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 54.1%Claude Fable 5: 68.4%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 25%Claude Fable 5: 50%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceEngineering Sciences · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 0%Claude Fable 5: 0%Vals AIAs of 11/05/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 4.825 / 5Claude Fable 5: 4.442 / 5Vals AIAs of 10/29/2026
EMBDCF · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 55.1%Claude Fable 5: 68.9%Vals AIAs of 10/20/2026
Finance Agent (v2)Comparables · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 45.3%Claude Fable 5: 44%Vals AIAs of 10/29/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44.2%Claude Fable 5: 51.2%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevWeb development · higher is betterClaude Haiku 5.5: 1,589Claude Fable 5: 1,624LMArenaAs of 10/28/2026
LMArena Text, Style ControlCoding · higher is betterClaude Haiku 5.5: 1,489Claude Fable 5: 1,550LMArenaAs of 10/28/2026
ProgramBenchRaw Pass Rate · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 78.7%Claude Fable 5: 76.8%Vals AIAs of 11/05/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.7%Claude Fable 5: 53.2%Vals AIAs of 11/05/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 63.6%Claude Fable 5: 42.4%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceLife Sciences · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 15.8%Claude Fable 5: 10.5%Vals AIAs of 11/05/2026
EMBLBO · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 28.2%Claude Fable 5: 65.9%Vals AIAs of 10/20/2026
Finance Agent (v2)Disclosure Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 64.3%Claude Fable 5: 68.8%Vals AIAs of 10/29/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 87%Claude Fable 5: 91.4%Vals AIAs of 11/05/2026
LMArena Text, Style ControlCreative writing · higher is betterClaude Haiku 5.5: 1,361Claude Fable 5: 1,501LMArenaAs of 10/28/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 56.2%Claude Fable 5: 71%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 18.5%Claude Fable 5: 25.9%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceMathematical Sciences · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 11.8%Claude Fable 5: 11.8%Vals AIAs of 11/05/2026
EMBM&A · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 57.8%Claude Fable 5: 80.6%Vals AIAs of 10/20/2026
Finance Agent (v2)Earnings Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 73.5%Claude Fable 5: 77.3%Vals AIAs of 10/29/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 40.7%Claude Fable 5: 44.4%Vals AIAs of 11/05/2026
LMArena Text, Style ControlEnglish · higher is betterClaude Haiku 5.5: 1,438Claude Fable 5: 1,512LMArenaAs of 10/28/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 30.2%Claude Fable 5: 39.4%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Science · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 21.4%Claude Fable 5: 45.2%Vals AIAs of 11/05/2026
Terminal-Bench-SciencePhysical Sciences · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 11.8%Claude Fable 5: 29.4%Vals AIAs of 11/05/2026
EMBMisc · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 52.3%Claude Fable 5: 71.4%Vals AIAs of 10/20/2026
Finance Agent (v2)Financial Modeling · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 28.3%Claude Fable 5: 17.6%Vals AIAs of 10/29/2026
Legal Research BenchCivil Litigation · Weighted partial credit · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 83%Claude Fable 5: 91.5%Vals AIAs of 11/05/2026
LMArena Text, Style ControlEntertainment, sports and media · higher is betterClaude Haiku 5.5: 1,378Claude Fable 5: 1,493LMArenaAs of 10/28/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 59.2%Claude Fable 5: 74.3%Vals AIAs of 11/05/2026

More comparisons

Compare Claude Haiku 5.5 and Claude Fable 5 with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1Claude Haiku 5.5 vs. GPT-6 Luna
  2. 2Claude Sonnet 5.5 vs. Claude Haiku 5.5
  3. 3Claude Haiku 5.5 vs. DeepSeek V4.1 Flash 1017
  4. 4Claude Haiku 5.5 vs. DeepSeek-V4-Flash
  5. 5Claude Haiku 5.5 vs. DeepSeek-V4.1-Flash
  6. 6Claude Opus 5.5 vs. Claude Haiku 5.5
  7. 7Claude Haiku 5.5 vs. GLM-5.3
  8. 8Claude Haiku 5.5 vs. Gemini 3.5 Flash-Lite
  9. 9Claude Haiku 5.5 vs. Gemini 3.8 Flash
Show all 43 comparisons
  1. 10Claude Haiku 5.5 vs. Claude Sonnet 4.5
  2. 11Claude Sonnet 5.5 vs. Claude Fable 5
  3. 12Claude Haiku 5.5 vs. Claude Sonnet 5
  4. 13Claude Haiku 5.5 vs. Claude Opus 5
  5. 14Claude Haiku 5.5 vs. GPT-6 Astra
  6. 15Claude Haiku 5.5 vs. Gemini 3.5 Flash
  7. 16Claude Haiku 5.5 vs. Claude Opus 4.8
  8. 17Claude Haiku 5.5 vs. Gemini 4 Argon
  9. 18Claude Haiku 5.5 vs. Grok 4.7
  10. 19Claude Haiku 5.5 vs. GPT-5.6 Luna
  11. 20Claude Haiku 5.5 vs. Qwen 3.8 Max 0902
  12. 21Claude Haiku 5.5 vs. Muse Spark 1.3
  13. 22Claude Haiku 5.5 vs. Claude Sonnet 4.6
  14. 23Claude Haiku 5.5 vs. Gemini 3.7 Flash
  15. 24Claude Haiku 5.5 vs. Mistral Large 4
  16. 25Claude Haiku 5.5 vs. GPT-6.1 Sol
  17. 26Claude Opus 5.5 vs. Claude Fable 5
  18. 27Claude Haiku 5.5 vs. Gemini 3.1 Pro Preview
  19. 28Claude Haiku 5.5 vs. GLM-5.3-Flash
  20. 29Claude Haiku 5.5 vs. DeepSeek-V4-Pro
  21. 30Claude Haiku 5.5 vs. GPT-5.6 Sol
  22. 31Claude Haiku 5.5 vs. Gemini 3.6 Flash
  23. 32Claude Haiku 5.5 vs. Claude Opus 4.6
  24. 33Claude Haiku 5.5 vs. Kimi K2.6
  25. 34Claude Fable 5 vs. Kimi K3
  26. 35Claude Fable 5 vs. DeepSeek-V4.1-Flash
  27. 36Claude Fable 5 vs. Gemini 3.8 Flash
  28. 37Claude Haiku 5.5 vs. Claude Opus 4.7
  29. 38Claude Haiku 5.5 vs. Mistral Large 3
  30. 39Claude Haiku 5.5 vs. GPT-5.5
  31. 40Claude Fable 5 vs. GPT-6.1 Sol
  32. 41Claude Fable 5 vs. Muse Wonder Full
  33. 42Claude Haiku 5.5 vs. GPT-6.1 Terra
  34. 43Claude Fable 5 vs. Gemini 4 Carbon