Skip to main content

AnthropicLLM matchup

Claude Haiku 5.5vs.Claude Sonnet 4.5

Is the higher price worth it?

Claude Haiku 5.5 performs better than Claude Sonnet 4.5 and is cheaper: Claude Sonnet 4.5 costs 30 times as much.

Haiku 5.5 ahead
IntelligenceOverall index, 100 points = average
103.4

Claude Haiku 5.5

Rank 20

65.4

Claude Sonnet 4.5

Rank 71

Haiku 5.5 faster
SpeedTokens per second
236

Claude Haiku 5.5

59

Claude Sonnet 4.5

Haiku 5.5 cheaper
Price$ per 1M tokens
$0.20

Claude Haiku 5.5

$6

Claude Sonnet 4.5

Haiku 5.5 more popular
Popularity0 to 100
77

Claude Haiku 5.5

Rank 3 of 631

50

Claude Sonnet 4.5

Rank 110 of 631

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

CodingAgentsFinanceProductivityHealthLegal

Choose Claude Sonnet 4.5 for

No clear advantage

Where is the difference?

Haiku 5.5 is ahead in 5 of 9 areas, Sonnet 4.5 in none.

Haiku 5.5 ahead: 5too little data: 4

Areas in the overall index
CodingHaiku 5.5 +45106.2 to 61.7
AgentsHaiku 5.5 +38106.1 to 67.9
Reasoningonly Haiku 5.5 has a score
Mathematicsonly Haiku 5.5 has a score
Knowledgeonly Haiku 5.5 has a score
Generalonly Haiku 5.5 has a score
Specialist fields
FinanceHaiku 5.5 +36104.7 to 68.3
HealthHaiku 5.5 +35108.9 to 74.3
LegalHaiku 5.5 +3094.4 to 64.7

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 3 more areas that do not count toward the overall index
ProductivityHaiku 5.5 +35101.8 to 67.0
Cybersecurityonly Haiku 5.5 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 codeHaiku 5.5Coding 106.2 to 61.7
Maths and data analysisopenMathematics without a score for Sonnet 4.5, Reasoning without a score for Sonnet 4.5
Facts and researchopenKnowledge without a score for Sonnet 4.5
Agents and workflowsHaiku 5.5Agents 106.1 to 67.9
Fast chat repliesHaiku 5.5236 to 59 tokens per second
Security analysisopenCybersecurity without a score for Sonnet 4.5
Many requests on a small budgetHaiku 5.5$0.20 to $6 per 1M tokens
Finance, legal and medical textsHaiku 5.5Finance 104.7 to 68.3, Legal 94.4 to 64.7, Health 108.9 to 74.3

See for yourself: same task, one attempt

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 Sonnet 4.5

Claude Sonnet 4.5: SVG short test

Oct 14, 2026 · $0.0105

Test details
Test run
Oct 14, 2026
Provider
anthropic
API model
anthropic/claude-sonnet-4.5
Output
686 tokens
Reasoning
API reports 0 reasoning tokens
Cost of the attempt
$0.0105
Test round
43b8c5c46830
Earlier tests

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 Sonnet 4.5

Claude Sonnet 4.5: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 1, 2026 · 30 s · $0.04

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
anthropic/claude-sonnet-4.5
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
2,710 tokens
Cost of the attempt
$0.0408
Response time
30.2 s
API model reported in response
anthropic/claude-sonnet-4.5
Pinned endpoint
Anthropic | anthropic/claude-4.5-sonnet-20250929
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.

Claude Haiku 5.5 and Claude Sonnet 4.5 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 92 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 Carbonhigh125.8
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 Solmax110.5
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
Claude Haiku 5.5max103.4
Claude Sonnet 4.565.4

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 Sonnet 4.5: 77 to 50 out of 100.

Over time

Weekly values from October 18, 2026 to November 7, 2026

Claude Haiku 5.5Claude Sonnet 4.5

All data side by side

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

MetricClaude Haiku 5.5Claude Sonnet 4.5
Intelligence
Overall indexpoints, 100 = reference group average, higher is better103.465.4
RankRank 20 of 92Rank 71 of 92
Price per 1M tokens
Inputwhat you send$0.10above 100,000 tokens: $0.50$3
Outputwhat the model writes$0.50above 100,000 tokens: $2.50$15
Speed
Tokens per second23659
Popularity
Popularitysearch, usage and mentions, 0 to 10077Rank 3 of 63150Rank 110 of 631
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages200,000 tokens≈ 300 A4 pages
Knowledge cutoffJune 2026January 2025
ReleasedOct 7, 2026September 2025
AvailabilityActiveDiscontinued
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 Sonnet 4.5Claude Sonnet 4.6

Overall index 86.4, rank 44$3 input and $15 output per 1M tokens

Haiku 5.5 vs. Claude Sonnet 4.6
Cheaper than Haiku 5.5MiMo V2.6 Flash

Overall index 98.3, rank 31$0.14 input and $0.28 output per 1M tokens

View profile
Best model in the overall indexClaude Opus 5.5

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

Haiku 5.5 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 Sonnet 4.5

MedCodeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 51.5%Claude Sonnet 4.5: 40.6%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89.5%Claude Sonnet 4.5: 84.5%Vals AIAs of 10/29/2026

More comparisons

Compare Claude Haiku 5.5 and Claude Sonnet 4.5 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 Haiku 5.5 vs. DeepSeek V4.1 Flash 1017
  3. 3Claude Sonnet 5.5 vs. Claude Haiku 5.5
  4. 4Claude Haiku 5.5 vs. DeepSeek-V4-Flash
  5. 5Claude Opus 5.5 vs. Claude Haiku 5.5
  6. 6Claude Haiku 5.5 vs. DeepSeek-V4.1-Flash
  7. 7Claude Haiku 5.5 vs. Gemini 3.8 Flash
  8. 8Claude Haiku 5.5 vs. Gemini 3.5 Flash-Lite
  9. 9Claude Opus 5.5 vs. Claude Sonnet 4.5
Show all 60 comparisons
  1. 10Claude Haiku 5.5 vs. Grok 4.7
  2. 11Claude Haiku 5.5 vs. GLM-5.3
  3. 12Claude Haiku 5.5 vs. Qwen 3.8 27B
  4. 13Claude Haiku 5.5 vs. GPT-6 Astra
  5. 14Claude Sonnet 4.5 vs. Gemini 3.8 Flash
  6. 15Claude Haiku 5.5 vs. GLM-5.3-Flash
  7. 16Claude Haiku 5.5 vs. Muse Spark 1.3
  8. 17Claude Haiku 5.5 vs. Claude Sonnet 5
  9. 18Claude Haiku 5.5 vs. GPT-5.6 Luna
  10. 19Claude Haiku 5.5 vs. Claude Opus 4.8
  11. 20Claude Sonnet 4.5 vs. GPT-6 Luna
  12. 21Claude Haiku 5.5 vs. Claude Opus 5
  13. 22Claude Haiku 5.5 vs. Claude Sonnet 4.6
  14. 23Claude Haiku 5.5 vs. Qwen 3.8 Max 0902
  15. 24Claude Haiku 5.5 vs. Mistral Large 4
  16. 25Claude Haiku 5.5 vs. DeepSeek-V4-Pro
  17. 26Claude Haiku 5.5 vs. Gemini 3.5 Flash
  18. 27Claude Sonnet 4.5 vs. DeepSeek V4.1 Flash 1017
  19. 28Claude Haiku 5.5 vs. GPT-6 Sol
  20. 29Claude Haiku 5.5 vs. Gemini 3.7 Flash
  21. 30Claude Haiku 5.5 vs. Gemini 3.6 Flash
  22. 31Claude Sonnet 4.5 vs. Qwen 3.8 27B
  23. 32Claude Haiku 5.5 vs. GPT-5.4 mini
  24. 33Claude Haiku 5.5 vs. Gemini 3.1 Pro Preview
  25. 34Claude Sonnet 4.5 vs. Mistral Large 4
  26. 35Claude Haiku 5.5 vs. GLM-5.2
  27. 36Claude Haiku 5.5 vs. Claude Opus 4.6
  28. 37Claude Sonnet 4.5 vs. Mistral Medium 3.5
  29. 38Claude Haiku 5.5 vs. Claude Fable 5
  30. 39Claude Haiku 5.5 vs. Kimi K2.6
  31. 40Claude Opus 5 vs. Claude Sonnet 4.5
  32. 41Claude Sonnet 4.5 vs. Qwen 3.8 Max 0902
  33. 42Claude Sonnet 4.5 vs. Grok 4.7
  34. 43Claude Sonnet 4.5 vs. Claude Haiku 4.5
  35. 44Claude Sonnet 4.5 vs. GPT-5.6 Luna
  36. 45Claude Sonnet 5.5 vs. Claude Sonnet 4.5
  37. 46Claude Haiku 5.5 vs. GPT-5.5
  38. 47Claude Haiku 5.5 vs. Claude Opus 4.7
  39. 48Claude Haiku 5.5 vs. Mistral Large 3
  40. 49Claude Sonnet 4.5 vs. DeepSeek-V4.1-Flash
  41. 50Claude Haiku 5.5 vs. GPT-6.1 Terra
  42. 51Claude Sonnet 4.5 vs. Gemini 4 Argon
  43. 52Claude Opus 4.5 vs. Claude Sonnet 4.5
  44. 53Claude Haiku 5.5 vs. Gemini 4 Argon
  45. 54Claude Haiku 5.5 vs. GPT-6.1 Sol
  46. 55Claude Sonnet 4.5 vs. GPT-6.1 Sol
  47. 56Claude Sonnet 4.5 vs. Gemini 4 Carbon
  48. 57Claude Sonnet 4.5 vs. Kimi K3.1 Pro
  49. 58Claude Haiku 5.5 vs. Kimi K3.1 Pro
  50. 59Claude Haiku 5.5 vs. Gemini 4 Carbon
  51. 60Claude Sonnet 4.5 vs. Muse Wonder Full