Skip to main content

AnthropicOpenAILLM matchup

Claude Haiku 5.5vs.GPT-5.4 mini

Which one is better?

Claude Haiku 5.5 performs better than GPT-5.4 mini and is cheaper: GPT-5.4 mini costs 7.5 times (input) and 9 times (output) as much.

Haiku 5.5 ahead
IntelligenceOverall index, 100 points = average
103.4

Claude Haiku 5.5

Rank 20

75.6

GPT-5.4 mini

Rank 56

Haiku 5.5 faster
SpeedTokens per second
236

Claude Haiku 5.5

191

GPT-5.4 mini

Haiku 5.5 cheaper
Price$ per 1M tokens
$0.20

Claude Haiku 5.5

$1.69

GPT-5.4 mini

Haiku 5.5 more popular
Popularity0 to 100
77

Claude Haiku 5.5

Rank 3 of 875

59

GPT-5.4 mini

Rank 41 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

ReasoningCodingFinanceAgentsGeneralLegalKnowledge

Choose GPT-5.4 mini for

No clear advantage

Where is the difference?

Strengths at a glance

Haiku 5.5GPT-5.4 mini

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

105110100CodingHaiku 5.5ReasoningHaiku 5.5KnowledgeHaiku 5.5AgentsHaiku 5.5GeneralHaiku 5.5FinanceHaiku 5.5LegalHaiku 5.5
CodingHaiku 5.5 ahead
Haiku 5.5106.2Rank 18
GPT-5.4 mini75.9Rank 65
Median of ranked models83.7

95 % range: Haiku 5.5 102.5 to 109.9, GPT-5.4 mini 71.9 to 79.8.

AreaHaiku 5.5GPT-5.4 mini

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, Multimodal, Health.

Haiku 5.5 is ahead in 7 of 10 areas, GPT-5.4 mini in none.

Haiku 5.5 ahead: 7too little data: 3

Areas in the overall index
ReasoningHaiku 5.5 +31105.2 to 74.4
CodingHaiku 5.5 +30106.2 to 75.9
AgentsHaiku 5.5 +27106.1 to 79.0
GeneralHaiku 5.5 +26106.4 to 80.4
KnowledgeHaiku 5.5 +1185.5 to 75.0
Mathematicsonly Haiku 5.5 has a score
Multimodalonly GPT-5.4 mini has a score
Specialist fields
FinanceHaiku 5.5 +29104.7 to 75.7
LegalHaiku 5.5 +2194.4 to 73.1
Healthonly 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.

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 75.9
Maths and data analysisHaiku 5.5Mathematics without a score for GPT-5.4 mini, Reasoning 105.2 to 74.4
Facts and researchHaiku 5.5Knowledge 85.5 to 75.0
Agents and workflowsHaiku 5.5Agents 106.1 to 79.0
Fast chat repliesHaiku 5.5236 to 191 tokens per second
Security analysisopenCybersecurity without a score for GPT-5.4 mini
Many requests on a small budgetHaiku 5.5$0.20 to $1.69 per 1M tokens
Finance, legal and medical textsHaiku 5.5Finance 104.7 to 75.7, Legal 94.4 to 73.1, Health without a score for GPT-5.4 mini
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 mini

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

Oct 2, 2026 · 14 s · $0.01

Test details
Run date
Oct 2, 2026
API provider
openrouter
Requested API model
openai/gpt-5.4-mini
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
3,142 tokens
Cost of the attempt
$0.0142
Response time
13.5 s
API model reported in response
openai/gpt-5.4-mini
Pinned endpoint
OpenAI | openai/gpt-5.4-mini-20260317
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 (2)

  • Oct 1, 2026API request failedReasoning setting: high
  • 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 mini

Unavailable in this round

Claude Haiku 5.5 and GPT-5.4 mini 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-5.4 minixhigh75.6

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 mini: 77 to 59 out of 100.

Over time

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

Claude Haiku 5.5GPT-5.4 mini

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 mini
Intelligence
Overall indexpoints, 100 = reference group average, higher is better103.475.6
RankRank 20 of 91Rank 56 of 91
Price per 1M tokens
Inputwhat you send$0.10above 100,000 tokens: $0.50$0.75
Outputwhat the model writes$0.50above 100,000 tokens: $2.50$4.50
Speed
Tokens per second236191
Popularity
Popularitysearch, usage and mentions, 0 to 10077Rank 3 of 87559Rank 41 of 875
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages400,000 tokens≈ 600 A4 pages
Knowledge cutoffJune 2026Aug 31, 2025
ReleasedOct 7, 2026Mar 17, 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?

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 mini

Code MigrationOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44.6%GPT-5.4 mini: 12.9%Vals AIAs of 10/29/2026
EMBOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 59%GPT-5.4 mini: 45.4%Vals AIAs of 10/20/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 54.1%GPT-5.4 mini: 45.4%Vals AIAs of 10/29/2026
GDPval-AAOverall · higher is betterClaude Haiku 5.5: 1,521.54 eloGPT-5.4 mini: 1,021.79 eloArtificial AnalysisAs of 11/06/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 43.8%GPT-5.4 mini: 12.5%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevOverall · higher is betterClaude Haiku 5.5: 1,589GPT-5.4 mini: 1,397LMArenaAs of 10/28/2026
LMArena Text, Style ControlOverall · higher is betterClaude Haiku 5.5: 1,425GPT-5.4 mini: 1,447LMArenaAs of 10/28/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 31.9%GPT-5.4 mini: 8.8%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.4%GPT-5.4 mini: 2.5%Vals AIAs of 11/05/2026
Show 54 more benchmarks
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 90.4%GPT-5.4 mini: 48%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.1%GPT-5.4 mini: 8.2%Vals AIAs of 10/29/2026
EMBComps · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 77.9%GPT-5.4 mini: 40.5%Vals AIAs of 10/20/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 49.6%GPT-5.4 mini: 45.4%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 50%GPT-5.4 mini: 15.2%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevHTML development · higher is betterClaude Haiku 5.5: 1,568GPT-5.4 mini: 1,419LMArenaAs of 10/28/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterClaude Haiku 5.5: 1,435GPT-5.4 mini: 1,459LMArenaAs of 10/28/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 29.5%GPT-5.4 mini: 3%Vals AIAs of 11/05/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 6.7%GPT-5.4 mini: 3.3%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 20%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 70%GPT-5.4 mini: 27.1%Vals AIAs of 10/29/2026
EMBDataroom · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 85.5%GPT-5.4 mini: 48.3%Vals AIAs of 10/20/2026
Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 42.9%GPT-5.4 mini: 32.4%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%GPT-5.4 mini: 69.7%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevReact development · higher is betterClaude Haiku 5.5: 1,608GPT-5.4 mini: 1,386LMArenaAs of 10/28/2026
LMArena Text, Style ControlChinese · higher is betterClaude Haiku 5.5: 1,468GPT-5.4 mini: 1,474LMArenaAs of 10/28/2026
ProgramBenchFully Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 54.1%GPT-5.4 mini: 32.2%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 25%GPT-5.4 mini: 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 mini: 3.053 / 5Vals AIAs of 10/29/2026
EMBDCF · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 55.1%GPT-5.4 mini: 40.6%Vals AIAs of 10/20/2026
Finance Agent (v2)Comparables · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 45.3%GPT-5.4 mini: 40.3%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%GPT-5.4 mini: 11.6%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevWeb development · higher is betterClaude Haiku 5.5: 1,589GPT-5.4 mini: 1,397LMArenaAs of 10/28/2026
LMArena Text, Style ControlCoding · higher is betterClaude Haiku 5.5: 1,489GPT-5.4 mini: 1,495LMArenaAs of 10/28/2026
ProgramBenchRaw Pass Rate · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 78.7%GPT-5.4 mini: 54.4%Vals AIAs of 11/05/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.7%GPT-5.4 mini: 10%Vals AIAs of 11/05/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 63.6%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
EMBLBO · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 28.2%GPT-5.4 mini: 41.6%Vals AIAs of 10/20/2026
Finance Agent (v2)Disclosure Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 64.3%GPT-5.4 mini: 48.3%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%GPT-5.4 mini: 71.2%Vals AIAs of 11/05/2026
LMArena Text, Style ControlCreative writing · higher is betterClaude Haiku 5.5: 1,361GPT-5.4 mini: 1,402LMArenaAs of 10/28/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 56.2%GPT-5.4 mini: 38.6%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 18.5%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
EMBM&A · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 57.8%GPT-5.4 mini: 49.8%Vals AIAs of 10/20/2026
Finance Agent (v2)Earnings Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 73.5%GPT-5.4 mini: 65.3%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%GPT-5.4 mini: 14.8%Vals AIAs of 11/05/2026
LMArena Text, Style ControlEnglish · higher is betterClaude Haiku 5.5: 1,438GPT-5.4 mini: 1,450LMArenaAs of 10/28/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 30.2%GPT-5.4 mini: 7%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Science · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 21.4%GPT-5.4 mini: 2.4%Vals AIAs of 11/05/2026
EMBMisc · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 52.3%GPT-5.4 mini: 46.3%Vals AIAs of 10/20/2026
Finance Agent (v2)Financial Modeling · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 28.3%GPT-5.4 mini: 19.6%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%GPT-5.4 mini: 67.3%Vals AIAs of 11/05/2026
LMArena Text, Style ControlEntertainment, sports and media · higher is betterClaude Haiku 5.5: 1,378GPT-5.4 mini: 1,409LMArenaAs of 10/28/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 59.2%GPT-5.4 mini: 36.5%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Security · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 40%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
EMBOperating · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 56.4%GPT-5.4 mini: 50.8%Vals AIAs of 10/20/2026
Finance Agent (v2)General Qualitative Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 61.9%GPT-5.4 mini: 46.4%Vals AIAs of 10/29/2026
Legal Research BenchConstitutional / Civil Rights · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44.7%GPT-5.4 mini: 13.2%Vals AIAs of 11/05/2026
LMArena Text, Style ControlExcluding ties · higher is betterClaude Haiku 5.5: 1,417GPT-5.4 mini: 1,449LMArenaAs of 10/28/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 20%GPT-5.4 mini: 3.3%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Software · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 46.3%GPT-5.4 mini: 7.4%Vals AIAs of 11/05/2026
EMBScratch · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 53.5%GPT-5.4 mini: 54.7%Vals AIAs of 10/20/2026
Finance Agent (v2)General Quantitative Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 74.4%GPT-5.4 mini: 64%Vals AIAs of 10/29/2026

More comparisons

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