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 70

Haiku 5.5 faster

SpeedTokens per second

236

Claude Haiku 5.5

Claude Sonnet 4.5

Haiku 5.5 cheaper

Price$ per 1M tokens

$0.20

Claude Haiku 5.5

Claude Sonnet 4.5

Haiku 5.5 more popular

Popularity0 to 100

Claude Haiku 5.5

Rank 3 of 875

Claude Sonnet 4.5

Rank 101 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

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 68.0

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 67.1

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.

TaskBetter choicebased 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 68.0

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

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

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 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

Claude Haiku 5.5max103.4

Claude Sonnet 4.565.4

Claude Opus 5.5

Gemini 4 Carbon

Claude Fable 5.1

Claude Sonnet 5.5

Gemini 4 Argon

GPT-6 Astra

GPT-6.1 Sol

Muse Wonder Full

Claude Opus 5

Muse Wonder

Kimi K3.1 Pro

Claude Fable 5

GPT-6 Sol

GPT-5.6 Sol

Muse Spark 1.3

Gemini 3.7 Flash

DeepSeek V4.1 Flash 1017

Gemini 3.8 Flash

Claude Haiku 5.5

Claude Sonnet 4.5

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 5, 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.

Metric	Claude Haiku 5.5	Claude Sonnet 4.5
Intelligence
Overall indexpoints, 100 = reference group average, higher is better	103.4	65.4
Rank	Rank 20 of 91	Rank 70 of 91
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 second	236	59
Popularity
Popularitysearch, usage and mentions, 0 to 100	77Rank 3 of 875	50Rank 101 of 875
Technical
Context windowhow much text the model reads at once	1 M tokens≈ 1,500 A4 pages	200,000 tokens≈ 300 A4 pages
Knowledge cutoff	June 2026	January 2025
Released	Oct 7, 2026	September 2025
Availability	Active	Discontinued
Open weights	no	no

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 identical51.5%40.6%Vals AIAs of 10/29/2026

MedScribeOverall · higher is betterTest setup not documented as identical89.5%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.

Claude Haiku 5.5vs.Claude Sonnet 4.5

Choose Claude Haiku 5.5 for

Choose Claude Sonnet 4.5 for

Where is the difference?

Which model for which task?

See for yourself: same task, one attempt

SVG short test

Claude Haiku 5.5

Claude Sonnet 4.5

Pelican on a bicycle

Claude Haiku 5.5 and Claude Sonnet 4.5 in the overall index

Overall index (Gradually Meta-Score v4)

Popularity compared

Over time

All data side by side

Is there a better choice?

Shared benchmarks

More comparisons

Compare another matchup

Predecessor and successor

The most popular comparisons