Skip to main content

AnthropicOpenAILLM matchup

Claude Sonnet 5vs.GPT-5.4 mini

Which one is better?

Claude Sonnet 5 performs better than GPT-5.4 mini, but costs 2.7 times (input) and 2.2 times (output) as much.

Sonnet 5 ahead
IntelligenceOverall index, 100 points = average
92.0

Claude Sonnet 5

Rank 45

75.1

GPT-5.4 mini

Rank 62

GPT-5.4 mini faster
SpeedTokens per second
72

Claude Sonnet 5

90

GPT-5.4 mini

GPT-5.4 mini cheaper
Price$ per 1M tokens
$4

Claude Sonnet 5

$1.69

GPT-5.4 mini

Popularity0 to 100
80

Claude Sonnet 5

Rank 21 of 511

n/a

GPT-5.4 mini

Choose Claude Sonnet 5 for

FinanceCodingAgentsMultimodalGeneral

No clear advantage for GPT-5.4 mini.

Where is the difference?

Strengths at a glance

Sonnet 5GPT-5.4 miniMedian of all ranked models

809010011070CodingSonnet 5AgentsSonnet 5GeneralSonnet 5MultimodalSonnet 5FinanceSonnet 5
CodingSonnet 5 ahead
Sonnet 594.1Rank 48
GPT-5.4 mini75.7Rank 71
Median of ranked models87.5

95 % range: Sonnet 5 89.7 to 98.4, GPT-5.4 mini 70.9 to 80.5.

AreaSonnet 5GPT-5.4 mini

The same values and verdicts as the bars below. In the close-up the net starts at 70 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Reasoning, Mathematics, Knowledge, Legal, Health.

Sonnet 5 is ahead in 5 of 10 areas, GPT-5.4 mini in none.

Sonnet 5 ahead: 5too little data: 5

Areas in the overall index
CodingSonnet 5 +1894.1 to 75.7
AgentsSonnet 5 +1694.7 to 78.7
MultimodalSonnet 5 +1489.1 to 75.1
GeneralSonnet 5 +887.5 to 79.3
Reasoningtoo little data90.2 to 72.9
Knowledgetoo little data84.3 to 73.8
Mathematicsonly Sonnet 5 has a score
Specialist fields
FinanceSonnet 5 +27102.0 to 75.1
Legaltoo little data97.8 to 71.3
Healthonly Sonnet 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 2 more areas that do not count toward the overall index
Cybersecurityonly Sonnet 5 has a score
Productivityonly Sonnet 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 codeSonnet 5Coding 94.1 to 75.7
Maths and data analysisopenMathematics without a score for GPT-5.4 mini, Reasoning 90.2 to 72.9 (too little data)
Facts and researchopenKnowledge 84.3 to 73.8 (too little data)
Agents and workflowsSonnet 5Agents 94.7 to 78.7
Fast chat repliesGPT-5.4 mini72 to 90 tokens per second
Security analysisopenCybersecurity without a score for GPT-5.4 mini
Many requests on a small budgetGPT-5.4 mini$4 to $1.69 per 1M tokens
Finance, legal and medical textsSonnet 5Finance 102.0 to 75.1, Legal 97.8 to 71.3 (too little data), Health without a score for GPT-5.4 mini
Images, screenshots and PDFsSonnet 5Multimodal 89.1 to 75.1

Claude Sonnet 5 vs. GPT-5.4 mini in our own test

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 Sonnet 5

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

Sep 7, 2026 · 48 s · $0.03

Test details
Run date
Sep 7, 2026
API provider
openrouter
Requested API model
anthropic/claude-sonnet-5
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
3,394 tokens
Cost of the attempt
$0.0340
Response time
47.9 s
API model reported in response
anthropic/claude-sonnet-5
Pinned endpoint
Anthropic | anthropic/claude-sonnet-5-20260630
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.

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 Sonnet 5

Unavailable in this round

GPT-5.4 mini

Unavailable in this round

Claude Sonnet 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 v6)

20 of 95 models

Claude Fable 5.2max130.9
Gemini 4 Carbonhigh127.0
Claude Opus 5.5max125.7
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.9
Gemini 4 Argonhigh121.2
GPT-6 Astramax119.6
Muse Wonder Fullmax118.4
GPT-6.1 Solmax117.5
Claude Opus 5max117.3
Muse Wondermax113.7
Claude Fable 5max112.8
Kimi K3.1 Promax112.6
Muse Ember 1.0max110.5
GPT-5.6 Solmax109.3
GPT-6 Solmax108.4
Gemini 3.7 Flashhigh107.7
DeepSeek V4.1 Flash 1017max107.1
Claude Sonnet 5max92.0
GPT-5.4 minixhigh75.1

Popularity compared

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

GPT-5.4 mini has no popularity score yet.

Over time

Weekly values from October 18, 2026 to November 17, 2026

Claude Sonnet 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 Sonnet 5GPT-5.4 mini
Intelligence
Overall indexpoints, 100 = reference group average, higher is better92.075.1
RankRank 45 of 95Rank 62 of 95
Price per 1M tokens
Inputwhat you send$2$0.75
Outputwhat the model writes$10$4.50
Cost per task (own tests)average of 1 original-protocol task both models passed (SVG short test not included)$0.034$0.014
Speed
Tokens per second7290
Popularity
Popularitysearch, usage and mentions, 0 to 10080Rank 21 of 511n/a
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages400,000 tokens≈ 600 A4 pages
Knowledge cutoffJanuary 2026Aug 31, 2025
ReleasedJun 30, 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?

Successor of Sonnet 5Claude Sonnet 5.5

Overall index 121.9, rank 5$2 input and $10 output per 1M tokens

GPT-5.4 mini vs. Claude Sonnet 5.5
Cheaper than GPT-5.4 miniMuse Ember 1.0

Overall index 110.5, rank 14$0.10 input and $0.50 output per 1M tokens

View profile
Best model in the overall indexClaude Fable 5.2

Overall index 130.9, rank 1$8 input and $40 output per 1M tokens

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 Sonnet 5B: GPT-5.4 mini

Code MigrationOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 44.4%GPT-5.4 mini: 12.9%Vals AIAs of 10/29/2026
CorpFin v2Overall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 67.0%GPT-5.4 mini: 60.9%Vals AIAs of 08/12/2026
EMBOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 66.3%GPT-5.4 mini: 45.4%Vals AIAs of 10/20/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 53.9%GPT-5.4 mini: 45.4%Vals AIAs of 10/29/2026
GDPval-AAOverall · higher is betterClaude Sonnet 5: 1,366.1 eloGPT-5.4 mini: 1,021.8 eloArtificial AnalysisAs of 11/07/2026
GPQA DiamondOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 88.9%GPT-5.4 mini: 83.1%Vals AIAs of 09/01/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalClaude Sonnet 5: 41.8%GPT-5.4 mini: 12.5%Vals AIAs of 11/05/2026
LiveCodeBenchOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 82.4%GPT-5.4 mini: 81.5%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevOverall · higher is betterClaude Sonnet 5: 1,539GPT-5.4 mini: 1,398LMArenaAs of 11/15/2026
LMArena Text, Style ControlOverall · higher is betterClaude Sonnet 5: 1,461GPT-5.4 mini: 1,447LMArenaAs of 11/11/2026
Show 54 more benchmarks
LMArena Vision, Style ControlOverall · higher is betterClaude Sonnet 5: 1,261GPT-5.4 mini: 1,250LMArenaAs of 11/09/2026
MMLU ProOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 87.5%GPT-5.4 mini: 84.6%Vals AIAs of 09/01/2026
MMMU ProOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 83.0%GPT-5.4 mini: 79.2%Vals AIAs of 09/01/2026
MortgageTaxOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 70.0%GPT-5.4 mini: 63.5%Vals AIAs of 09/01/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 0%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
SWE-bench VerifiedOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 79.6%GPT-5.4 mini: 73.0%Vals AIAs of 09/01/2026
Taste-BenchOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 51.6%GPT-5.4 mini: 40.1%Taste-Bench paperAs of 09/23/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 29.4%GPT-5.4 mini: 8.8%Vals AIAs of 11/05/2026
TaxEval v2Overall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 75.6%GPT-5.4 mini: 71.2%Vals AIAs of 09/01/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 10.6%GPT-5.4 mini: 2.5%Vals AIAs of 11/05/2026
Vals Multimodal IndexOverall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 68.8%GPT-5.4 mini: 54.2%Vals AIAs of 08/11/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Sonnet 5: 81.3%GPT-5.4 mini: 48.0%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalClaude Sonnet 5: 36.3%GPT-5.4 mini: 8.2%Vals AIAs of 10/29/2026
CorpFin v2Exact Pages · higher is betterTest setup not documented as identicalClaude Sonnet 5: 63.9%GPT-5.4 mini: 61.5%Vals AIAs of 08/12/2026
EMBComps · higher is betterTest setup not documented as identicalClaude Sonnet 5: 69.4%GPT-5.4 mini: 40.5%Vals AIAs of 10/20/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalClaude Sonnet 5: 48.7%GPT-5.4 mini: 45.4%Vals AIAs of 10/29/2026
GPQA DiamondFew-Shot CoT · higher is betterTest setup not documented as identicalClaude Sonnet 5: 87.4%GPT-5.4 mini: 84.8%Vals AIAs of 09/01/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalClaude Sonnet 5: 54.5%GPT-5.4 mini: 15.2%Vals AIAs of 11/05/2026
LiveCodeBenchEasy · higher is betterTest setup not documented as identicalClaude Sonnet 5: 98.4%GPT-5.4 mini: 97.8%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevHTML development · higher is betterClaude Sonnet 5: 1,526GPT-5.4 mini: 1,420LMArenaAs of 11/15/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterClaude Sonnet 5: 1,466GPT-5.4 mini: 1,459LMArenaAs of 11/11/2026
LMArena Vision, Style ControlChinese · higher is betterClaude Sonnet 5: 1,319GPT-5.4 mini: 1,285LMArenaAs of 11/09/2026
MMLU ProBiology · higher is betterTest setup not documented as identicalClaude Sonnet 5: 93.6%GPT-5.4 mini: 91.4%Vals AIAs of 09/01/2026
MortgageTaxNumerical Extraction · higher is betterTest setup not documented as identicalClaude Sonnet 5: 78.7%GPT-5.4 mini: 79.4%Vals AIAs of 09/01/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalClaude Sonnet 5: 13.5%GPT-5.4 mini: 3.0%Vals AIAs of 11/05/2026
SWE-bench Verified<15 min fix · higher is betterTest setup not documented as identicalClaude Sonnet 5: 83.5%GPT-5.4 mini: 85.6%Vals AIAs of 09/01/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Sonnet 5: 10.0%GPT-5.4 mini: 3.3%Vals AIAs of 11/05/2026
TaxEval v2Correctness · higher is betterTest setup not documented as identicalClaude Sonnet 5: 64%GPT-5.4 mini: 63%Vals AIAs of 09/01/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalClaude Sonnet 5: 0%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
Vals Multimodal IndexCorpFin v2 · higher is betterTest setup not documented as identicalClaude Sonnet 5: 67.9%GPT-5.4 mini: 60.3%Vals AIAs of 08/11/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalClaude Sonnet 5: 68.6%GPT-5.4 mini: 27.1%Vals AIAs of 10/29/2026
CorpFin v2Max Fitting Context · higher is betterTest setup not documented as identicalClaude Sonnet 5: 69.1%GPT-5.4 mini: 61.0%Vals AIAs of 08/12/2026
EMBDataroom · higher is betterTest setup not documented as identicalClaude Sonnet 5: 84.9%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 Sonnet 5: 42.1%GPT-5.4 mini: 32.4%Vals AIAs of 10/29/2026
GPQA DiamondZero-Shot CoT · higher is betterTest setup not documented as identicalClaude Sonnet 5: 90.4%GPT-5.4 mini: 81.3%Vals AIAs of 09/01/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identicalClaude Sonnet 5: 87.8%GPT-5.4 mini: 69.7%Vals AIAs of 11/05/2026
LiveCodeBenchHard · higher is betterTest setup not documented as identicalClaude Sonnet 5: 66.9%GPT-5.4 mini: 61.7%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevReact development · higher is betterClaude Sonnet 5: 1,539GPT-5.4 mini: 1,386LMArenaAs of 11/15/2026
LMArena Text, Style ControlChinese · higher is betterClaude Sonnet 5: 1,497GPT-5.4 mini: 1,473LMArenaAs of 11/11/2026
LMArena Vision, Style ControlCreative writing with images · higher is betterClaude Sonnet 5: 1,237GPT-5.4 mini: 1,225LMArenaAs of 11/09/2026
MMLU ProBusiness · higher is betterTest setup not documented as identicalClaude Sonnet 5: 91.6%GPT-5.4 mini: 89.7%Vals AIAs of 09/01/2026
MortgageTaxSemantic Extraction · higher is betterTest setup not documented as identicalClaude Sonnet 5: 61.4%GPT-5.4 mini: 47.6%Vals AIAs of 09/01/2026
ProgramBenchFully Resolved · higher is betterTest setup not documented as identicalClaude Sonnet 5: 0%GPT-5.4 mini: 0%Vals AIAs of 11/05/2026
SWE-bench Verified>4 hours · higher is betterTest setup not documented as identicalClaude Sonnet 5: 66.7%GPT-5.4 mini: 0.0%Vals AIAs of 09/01/2026
Tax Agent BenchControversy & Precedence Analysis (weighted pass) · higher is betterTest setup not documented as identicalClaude Sonnet 5: 57.4%GPT-5.4 mini: 32.2%Vals AIAs of 11/05/2026
TaxEval v2Stepwise Reasoning · higher is betterTest setup not documented as identicalClaude Sonnet 5: 87.2%GPT-5.4 mini: 79.4%Vals AIAs of 09/01/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalClaude Sonnet 5: 8.3%GPT-5.4 mini: 0.0%Vals AIAs of 11/05/2026
Vals Multimodal IndexFinance Agent v2 · higher is betterTest setup not documented as identicalClaude Sonnet 5: 52.0%GPT-5.4 mini: 45.4%Vals AIAs of 08/11/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalClaude Sonnet 5: 4.898 / 5GPT-5.4 mini: 3.053 / 5Vals AIAs of 10/29/2026
CorpFin v2Shared Max Context · higher is betterTest setup not documented as identicalClaude Sonnet 5: 67.9%GPT-5.4 mini: 60.3%Vals AIAs of 08/12/2026
EMBDCF · higher is betterTest setup not documented as identicalClaude Sonnet 5: 56.4%GPT-5.4 mini: 40.6%Vals AIAs of 10/20/2026
Finance Agent (v2)Comparables · higher is betterTest setup not documented as identicalClaude Sonnet 5: 45.8%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 Sonnet 5: 32.6%GPT-5.4 mini: 11.6%Vals AIAs of 11/05/2026
LiveCodeBenchMedium · higher is betterTest setup not documented as identicalClaude Sonnet 5: 82.0%GPT-5.4 mini: 84.9%Vals AIAs of 09/01/2026

More comparisons

Compare Claude Sonnet 5 and GPT-5.4 mini with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1GPT-6 Luna vs. GPT-5.4 mini
  2. 2Claude Sonnet 5 vs. DeepSeek-V4.1-Flash
  3. 3Claude Opus 5.5 vs. Claude Sonnet 5
  4. 4Claude Sonnet 5 vs. GPT-6 Luna
  5. 5Claude Haiku 5.5 vs. Claude Sonnet 5
  6. 6Claude Sonnet 5 vs. GPT-6.1 Sol
  7. 7GPT-5.6 Luna vs. GPT-5.4 mini
  8. 8GPT-6.1 Sol vs. GPT-5.4 mini
  9. 9Claude Sonnet 5 vs. DeepSeek V4.1 Flash 1017
Show all 37 comparisons
  1. 10GPT-6.1 Terra vs. GPT-5.4 mini
  2. 11Claude Sonnet 5 vs. GPT-6.1 Terra
  3. 12Claude Sonnet 5 vs. GPT-6 Astra
  4. 13Claude Sonnet 5 vs. Gemini 4 Carbon
  5. 14Claude Sonnet 5 vs. Gemini 3.8 Flash
  6. 15Claude Haiku 5.5 vs. GPT-5.4 mini
  7. 16Claude Sonnet 5 vs. Kimi K3
  8. 17Claude Sonnet 5 vs. GPT-5.6 Luna
  9. 18GPT-5.4 mini vs. Gemini 3.8 Flash
  10. 19Claude Sonnet 5 vs. GLM-5.3
  11. 20Claude Sonnet 5 vs. Mistral Large 4
  12. 21Claude Opus 5 vs. Claude Sonnet 5
  13. 22Claude Sonnet 5 vs. DeepSeek-V4-Flash
  14. 23Claude Sonnet 5 vs. Qwen 3.8 27B
  15. 24Claude Sonnet 5 vs. GPT-5.6 Sol
  16. 25Claude Sonnet 5 vs. GPT-6 Sol
  17. 26Claude Sonnet 5 vs. Qwen 3.8 Max 0902
  18. 27Claude Sonnet 5 vs. Kimi K3.1 Pro
  19. 28Claude Sonnet 5 vs. DeepSeek-V4-Pro
  20. 29Claude Sonnet 5 vs. MiMo-V2.5
  21. 30GPT-5.4 mini vs. Qwen 3.8 27B
  22. 31GPT-5.4 mini vs. DeepSeek-V4-Flash
  23. 32Claude Sonnet 5.5 vs. GPT-5.4 mini
  24. 33Claude Fable 5.1 vs. Claude Sonnet 5
  25. 34Claude Sonnet 5 vs. Gemini 3.7 Flash
  26. 35Claude Sonnet 5 vs. Claude Haiku 4.5
  27. 36Claude Sonnet 5 vs. GPT-5.5
  28. 37Claude Sonnet 5 vs. Gemini 4 Argon