Skip to main content

AnthropicOpenAILLM matchup

Claude Haiku 5.5vs.GPT-5.4

Which one is better?

Claude Haiku 5.5 performs better than GPT-5.4 and is cheaper: GPT-5.4 costs 25 times (input) and 30 times (output) as much.

Haiku 5.5 ahead
IntelligenceOverall index, 100 points = average
103.4

Claude Haiku 5.5

Rank 20

85.4

GPT-5.4

Rank 45

Haiku 5.5 faster
SpeedTokens per second
236

Claude Haiku 5.5

64

GPT-5.4

Haiku 5.5 cheaper
Price$ per 1M tokens
$0.20

Claude Haiku 5.5

$5.63

GPT-5.4

Haiku 5.5 more popular
Popularity0 to 100
77

Claude Haiku 5.5

Rank 3 of 875

39

GPT-5.4

Rank 279 of 875

Above 100,000 tokens of context, Claude Haiku 5.5 costs more: $0.50 input and $2.50 output per 1M tokens. Above 272,000 tokens of context, GPT-5.4 costs more: $5 input and $22.50 output per 1M tokens.

Choose Claude Haiku 5.5 for

HealthCodingGeneralReasoningFinanceAgentsLegal (not certain)

Choose GPT-5.4 for

No clear advantage

Where is the difference?

Strengths at a glance

Haiku 5.5GPT-5.4

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

105110100CodingHaiku 5.5ReasoningHaiku 5.5AgentsHaiku 5.5GeneralHaiku 5.5FinanceHaiku 5.5Legalslightly Haiku 5.5HealthHaiku 5.5
CodingHaiku 5.5 ahead
Haiku 5.5106.2Rank 18
GPT-5.484.9Rank 54
Median of ranked models83.7

95 % range: Haiku 5.5 102.5 to 109.9, GPT-5.4 76.5 to 93.2.

AreaHaiku 5.5GPT-5.4

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: Mathematics, Knowledge, Multimodal.

Haiku 5.5 is ahead in 6 of 10 areas, GPT-5.4 in none.

Haiku 5.5 ahead: 6Haiku 5.5 slightly ahead: 1too little data: 3

Areas in the overall index
CodingHaiku 5.5 +21106.2 to 84.9
GeneralHaiku 5.5 +20106.4 to 86.4
ReasoningHaiku 5.5 +19105.2 to 85.7
AgentsHaiku 5.5 +17106.1 to 89.3
Knowledgetoo little data85.5 to 86.0
Mathematicsonly Haiku 5.5 has a score
Multimodalonly GPT-5.4 has a score
Specialist fields
HealthHaiku 5.5 +28108.9 to 81.2
FinanceHaiku 5.5 +19104.7 to 85.6
Legalleaning Haiku 5.5not certain · 3 and 2 tests

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
Cybersecurityonly Haiku 5.5 has a score
Productivityonly 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 84.9
Maths and data analysisHaiku 5.5Mathematics without a score for GPT-5.4, Reasoning 105.2 to 85.7
Facts and researchopenKnowledge 85.5 to 86.0 (too little data)
Agents and workflowsHaiku 5.5Agents 106.1 to 89.3
Fast chat repliesHaiku 5.5236 to 64 tokens per second
Security analysisopenCybersecurity without a score for GPT-5.4
Many requests on a small budgetHaiku 5.5$0.20 to $5.63 per 1M tokens
Finance, legal and medical textsHaiku 5.5Finance 104.7 to 85.6, Legal 94.4 to 84.2, Health 108.9 to 81.2
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

GPT-5.4

GPT-5.4: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 1, 2026 · 117 s · $0.11

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
openai/gpt-5.4
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
7,339 tokens
Cost of the attempt
$0.1101
Response time
116.8 s
API model reported in response
openai/gpt-5.4
Pinned endpoint
OpenAI | openai/gpt-5.4-20260305
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.

Earlier attempts (1)

  • Sep 7, 2026API request failedReasoning setting: high
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

GPT-5.4

Unavailable in this round

Claude Haiku 5.5 and GPT-5.4 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

5 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
GPT-5.4xhigh85.4

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 GPT-5.4: 77 to 39 out of 100.

Over time

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

Claude Haiku 5.5GPT-5.4

All data side by side

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

MetricClaude Haiku 5.5GPT-5.4
Intelligence
Overall indexpoints, 100 = reference group average, higher is better103.485.4
RankRank 20 of 91Rank 45 of 91
Price per 1M tokens
Inputwhat you send$0.10above 100,000 tokens: $0.50$2.50above 272,000 tokens: $5
Outputwhat the model writes$0.50above 100,000 tokens: $2.50$15above 272,000 tokens: $22.50
Speed
Tokens per second23664
Popularity
Popularitysearch, usage and mentions, 0 to 10077Rank 3 of 87539Rank 279 of 875
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages1.05 M tokens≈ 1,580 A4 pages
Knowledge cutoffJune 2026Aug 31, 2025
ReleasedOct 7, 2026Mar 5, 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 GPT-5.4GPT-5.5

Overall index 100.9, rank 24. $5 input and $30 output per 1M tokens.

Haiku 5.5 vs. GPT-5.5
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: GPT-5.4

Code MigrationOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44.6%GPT-5.4: 35%Vals AIAs of 10/29/2026
GDPval-AAOverall · higher is betterClaude Haiku 5.5: 1,521.54 eloGPT-5.4: 1,255.65 eloArtificial AnalysisAs of 11/06/2026
LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,589GPT-5.4: 1,401LMArenaAs of 10/28/2026
LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,425GPT-5.4: 1,465LMArenaAs of 10/28/2026
MedCodeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 51.5%GPT-5.4: 41.3%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89.5%GPT-5.4: 77.5%Vals AIAs of 10/29/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%GPT-5.4: 0%Vals AIAs of 11/05/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 90.4%GPT-5.4: 67.4%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.1%GPT-5.4: 23.8%Vals AIAs of 10/29/2026
LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,568GPT-5.4: 1,428LMArenaAs of 10/28/2026
Show 54 more benchmarks
LMArena Text, Style ControlOverall · higher is betterClaude Haiku 5.5: 1,425GPT-5.4: 1,475LMArenaAs of 10/28/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 29.5%GPT-5.4: 7%Vals AIAs of 11/05/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 70%GPT-5.4: 68.6%Vals AIAs of 10/29/2026
LMArena Code Arena WebDevReact development · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,608GPT-5.4: 1,389LMArenaAs of 10/28/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,435GPT-5.4: 1,474LMArenaAs of 10/28/2026
ProgramBenchFully Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%GPT-5.4: 0%Vals AIAs of 11/05/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 4.825 / 5GPT-5.4: 3.632 / 5Vals AIAs of 10/29/2026
LMArena Code Arena WebDevWeb development · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,589GPT-5.4: 1,401LMArenaAs of 10/28/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterClaude Haiku 5.5: 1,435GPT-5.4: 1,482LMArenaAs of 10/28/2026
ProgramBenchRaw Pass Rate · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 78.7%GPT-5.4: 68.6%Vals AIAs of 11/05/2026
LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,468GPT-5.4: 1,494LMArenaAs of 10/28/2026
LMArena Text, Style ControlChinese · higher is betterClaude Haiku 5.5: 1,468GPT-5.4: 1,506LMArenaAs of 10/28/2026
LMArena Text, Style ControlCoding · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,489GPT-5.4: 1,511LMArenaAs of 10/28/2026
LMArena Text, Style ControlCoding · higher is betterClaude Haiku 5.5: 1,489GPT-5.4: 1,520LMArenaAs of 10/28/2026
LMArena Text, Style ControlCreative writing · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,361GPT-5.4: 1,434LMArenaAs of 10/28/2026
LMArena Text, Style ControlCreative writing · higher is betterClaude Haiku 5.5: 1,361GPT-5.4: 1,442LMArenaAs of 10/28/2026
LMArena Text, Style ControlEnglish · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,438GPT-5.4: 1,468LMArenaAs of 10/28/2026
LMArena Text, Style ControlEnglish · higher is betterClaude Haiku 5.5: 1,438GPT-5.4: 1,476LMArenaAs of 10/28/2026
LMArena Text, Style ControlEntertainment, sports and media · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,378GPT-5.4: 1,432LMArenaAs of 10/28/2026
LMArena Text, Style ControlEntertainment, sports and media · higher is betterClaude Haiku 5.5: 1,378GPT-5.4: 1,441LMArenaAs of 10/28/2026
LMArena Text, Style ControlExcluding ties · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,417GPT-5.4: 1,471LMArenaAs of 10/28/2026
LMArena Text, Style ControlExcluding ties · higher is betterClaude Haiku 5.5: 1,417GPT-5.4: 1,484LMArenaAs of 10/28/2026
LMArena Text, Style ControlExpert prompts · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,479GPT-5.4: 1,491LMArenaAs of 10/28/2026
LMArena Text, Style ControlExpert prompts · higher is betterClaude Haiku 5.5: 1,479GPT-5.4: 1,514LMArenaAs of 10/28/2026
LMArena Text, Style ControlFrench prompts · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,457GPT-5.4: 1,485LMArenaAs of 10/28/2026
LMArena Text, Style ControlFrench prompts · higher is betterClaude Haiku 5.5: 1,457GPT-5.4: 1,501LMArenaAs of 10/28/2026
LMArena Text, Style ControlHard prompts · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,452GPT-5.4: 1,487LMArenaAs of 10/28/2026
LMArena Text, Style ControlHard prompts · higher is betterClaude Haiku 5.5: 1,452GPT-5.4: 1,497LMArenaAs of 10/28/2026
LMArena Text, Style ControlHard prompts, English · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,460GPT-5.4: 1,486LMArenaAs of 10/28/2026
LMArena Text, Style ControlHard prompts, English · higher is betterClaude Haiku 5.5: 1,460GPT-5.4: 1,493LMArenaAs of 10/28/2026
LMArena Text, Style ControlInstruction following · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,429GPT-5.4: 1,461LMArenaAs of 10/28/2026
LMArena Text, Style ControlInstruction following · higher is betterClaude Haiku 5.5: 1,429GPT-5.4: 1,471LMArenaAs of 10/28/2026
LMArena Text, Style ControlLegal and government · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,413GPT-5.4: 1,475LMArenaAs of 10/28/2026
LMArena Text, Style ControlLegal and government · higher is betterClaude Haiku 5.5: 1,413GPT-5.4: 1,490LMArenaAs of 10/28/2026
LMArena Text, Style ControlLife, physical and social science · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,444GPT-5.4: 1,478LMArenaAs of 10/28/2026
LMArena Text, Style ControlLife, physical and social science · higher is betterClaude Haiku 5.5: 1,444GPT-5.4: 1,488LMArenaAs of 10/28/2026
LMArena Text, Style ControlLonger queries · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,424GPT-5.4: 1,477LMArenaAs of 10/28/2026
LMArena Text, Style ControlLonger queries · higher is betterClaude Haiku 5.5: 1,424GPT-5.4: 1,481LMArenaAs of 10/28/2026
LMArena Text, Style ControlMath · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,449GPT-5.4: 1,460LMArenaAs of 10/28/2026
LMArena Text, Style ControlMath · higher is betterClaude Haiku 5.5: 1,449GPT-5.4: 1,491LMArenaAs of 10/28/2026
LMArena Text, Style ControlMathematical professions · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,452GPT-5.4: 1,472LMArenaAs of 10/28/2026
LMArena Text, Style ControlMathematical professions · higher is betterClaude Haiku 5.5: 1,452GPT-5.4: 1,499LMArenaAs of 10/28/2026
LMArena Text, Style ControlMedicine and healthcare · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,412GPT-5.4: 1,465LMArenaAs of 10/28/2026
LMArena Text, Style ControlMedicine and healthcare · higher is betterClaude Haiku 5.5: 1,412GPT-5.4: 1,474LMArenaAs of 10/28/2026
LMArena Text, Style ControlMulti-turn · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,422GPT-5.4: 1,480LMArenaAs of 10/28/2026
LMArena Text, Style ControlMulti-turn · higher is betterClaude Haiku 5.5: 1,422GPT-5.4: 1,493LMArenaAs of 10/28/2026
LMArena Text, Style ControlNon-English · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,409GPT-5.4: 1,457LMArenaAs of 10/28/2026
LMArena Text, Style ControlNon-English · higher is betterClaude Haiku 5.5: 1,409GPT-5.4: 1,468LMArenaAs of 10/28/2026
LMArena Text, Style ControlRussian prompts · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,394GPT-5.4: 1,470LMArenaAs of 10/28/2026
LMArena Text, Style ControlRussian prompts · higher is betterClaude Haiku 5.5: 1,394GPT-5.4: 1,487LMArenaAs of 10/28/2026
LMArena Text, Style ControlSoftware and IT services · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,481GPT-5.4: 1,499LMArenaAs of 10/28/2026
LMArena Text, Style ControlSoftware and IT services · higher is betterClaude Haiku 5.5: 1,481GPT-5.4: 1,507LMArenaAs of 10/28/2026
LMArena Text, Style ControlSpanish prompts · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,404GPT-5.4: 1,461LMArenaAs of 10/28/2026
LMArena Text, Style ControlSpanish prompts · higher is betterClaude Haiku 5.5: 1,404GPT-5.4: 1,454LMArenaAs of 10/28/2026

More comparisons

Compare Claude Haiku 5.5 and GPT-5.4 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. 9GPT-5.4 vs. GLM-5.3-Flash
Show all 42 comparisons
  1. 10Claude Haiku 5.5 vs. Gemini 3.8 Flash
  2. 11Claude Haiku 5.5 vs. Claude Sonnet 4.5
  3. 12GPT-6 Luna vs. GPT-5.4
  4. 13Claude Haiku 5.5 vs. Claude Sonnet 5
  5. 14GPT-6 Sol vs. GPT-5.4
  6. 15Claude Haiku 5.5 vs. Claude Opus 5
  7. 16Claude Haiku 5.5 vs. GPT-6 Astra
  8. 17Claude Haiku 5.5 vs. Gemini 3.5 Flash
  9. 18Claude Haiku 5.5 vs. Claude Opus 4.8
  10. 19Claude Haiku 5.5 vs. Gemini 4 Argon
  11. 20Claude Haiku 5.5 vs. Grok 4.7
  12. 21Claude Haiku 5.5 vs. GPT-5.6 Luna
  13. 22Claude Haiku 5.5 vs. Qwen 3.8 Max 0902
  14. 23Claude Haiku 5.5 vs. Muse Spark 1.3
  15. 24Claude Haiku 5.5 vs. Claude Sonnet 4.6
  16. 25Claude Haiku 5.5 vs. Gemini 3.7 Flash
  17. 26Claude Haiku 5.5 vs. Mistral Large 4
  18. 27Claude Haiku 5.5 vs. GPT-6.1 Sol
  19. 28Claude Haiku 5.5 vs. Gemini 3.1 Pro Preview
  20. 29Claude Haiku 5.5 vs. GLM-5.3-Flash
  21. 30Claude Haiku 5.5 vs. DeepSeek-V4-Pro
  22. 31Claude Haiku 5.5 vs. GPT-5.6 Sol
  23. 32Claude Haiku 5.5 vs. Gemini 3.6 Flash
  24. 33Claude Haiku 5.5 vs. Claude Opus 4.6
  25. 34Claude Haiku 5.5 vs. Kimi K2.6
  26. 35Claude Opus 5.5 vs. GPT-5.4
  27. 36GPT-6.1 Sol vs. GPT-5.4
  28. 37Claude Haiku 5.5 vs. Claude Opus 4.7
  29. 38GPT-5.4 vs. Kimi K3
  30. 39Claude Haiku 5.5 vs. Mistral Large 3
  31. 40Claude Haiku 5.5 vs. GPT-5.5
  32. 41GPT-5.4 vs. GLM-5.3
  33. 42Claude Haiku 5.5 vs. GPT-6.1 Terra