Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.5 vs GPT-5.4

GPT-5.4 leads Claude Sonnet 4.5 on coding, 64.4 to 39.5 on the Vibe Coding Index, at about the same output price ($15.00 vs $15.00 per million). Updated October 22, 2026; 82 benchmarks have a result for both.

Replace Claude Sonnet 4.5 Replace GPT-5.4
Claude Sonnet 4.5Anthropic
Coding
39.5
Overall
49.5
Output $/M
$15.00
12
GPT-5.4OpenAI
Coding
64.4
Overall
69.6
Output $/M
$15.00
70
vs boards won of 82 shared

Claude Sonnet 4.5 or GPT-5.4: which to pick

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5.

Pick Claude Sonnet 4.5 for work measured by Design Arena: agents building web apps or Design Arena: agents building full-stack apps, where it leads.

Model AClaude Sonnet 4.5Anthropic39.5/1003 independent benchmarks$1.16 per solved taskModel BGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved task
Shared results
82
Claude Sonnet 4.5 only
13
GPT-5.4 only
28
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Sonnet 4.5 39.5 from 3 benchmarks, GPT-5.4 64.4 from 3 benchmarks.
Widest category
Math, 25.6 points apart on average over 7 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Sonnet 4.5 13.6% against GPT-5.4 74.0%, 60.3 points apart on a 0 to 100 scale.
Output price
Both cost $15.00 per million output tokens.
Context window
Claude Sonnet 4.5 takes 1M tokens, GPT-5.4 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Sonnet 4.5BarsGPT-5.4Ties
Coding012
Intelligence02
Agentic work42
Reasoning012
Math07
Knowledge112
Web design35
General418
All shared boards1270
CodingLike-for-likeSix of these boards feed the Vibe Coding Index012
Coding benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
SWE-bench Verified74.8%Not measuredOnly Claude Sonnet 4.5 measured
SWE-bench Multilingual67.0%Not measuredOnly Claude Sonnet 4.5 measured
LMArena WebDev13941464GPT-5.4
AA Coding Index52.171.1GPT-5.4
LiveCodeBench (Vals AI)73.0%84.1%GPT-5.4
SWE-bench Verified (Vals AI)70.0%78.2%GPT-5.4
Vibe Code Bench (Vals AI)22.6%67.4%GPT-5.4
Code migration (Vals AI)Not measured35.0%Only GPT-5.4 measured
ProgramBench (Vals AI)Not measured0.5%Only GPT-5.4 measured
SkillsBench (Vals AI)Not measured51.7%Only GPT-5.4 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured57.6%Only GPT-5.4 measured
Terminal-Bench46.5%81.8%GPT-5.4
GSO-Bench14.7%31.4%GPT-5.4
WeirdML47.7%77.7%GPT-5.4
MirrorCodeNot measured15.6%Only GPT-5.4 measured
Cybench60.0%Not measuredOnly Claude Sonnet 4.5 measured
ALE-BenchNot measured1607.0Only GPT-5.4 measured
LMArena Text: coding14881496GPT-5.4
LMArena Text: software and IT14731491GPT-5.4
LMArena WebDev: React13861454GPT-5.4
LMArena WebDev: HTML13991478GPT-5.4
LMArena WebDev: from an imageNot measured1436Only GPT-5.4 measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
AA Intelligence Index20.739.0GPT-5.4
Epoch Capabilities Index146.7157.3GPT-5.4
Agentic workLike-for-likePublic boards, shown as published, kept out of the index42
Agentic work benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
AA Agentic Index15.8Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building web apps10601059Claude Sonnet 4.5
Design Arena: agents building full-stack apps10501017Claude Sonnet 4.5
Design Arena: agents building mobile apps11371087Claude Sonnet 4.5
Design Arena: agents building Android appsNot measured1031Only GPT-5.4 measured
Design Arena: agents building Godot gamesNot measured1135Only GPT-5.4 measured
τ²-Bench TelecomNot measured87.1%Only GPT-5.4 measured
APEX-AgentsNot measured52.4%Only GPT-5.4 measured
METR time horizons67.4%74.3%GPT-5.4
Remote Labor Index2.1%Not measuredOnly Claude Sonnet 4.5 measured
GDPval42.5%Not measuredOnly Claude Sonnet 4.5 measured
DeepResearch Bench52.6%35.1%Claude Sonnet 4.5
PostTrainBenchNot measured19.0%Only GPT-5.4 measured
OSWorld62.9%Not measuredOnly Claude Sonnet 4.5 measured
Vending-Bench 2$3,839$6,144GPT-5.4
Berkeley Function Calling Leaderboard (BFCL)73.2%Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index012
Reasoning benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
GPQA Diamond81.6%91.7%GPT-5.4
MMMU Pro (Vals AI)79.3%87.5%GPT-5.4
GPQA Diamond (Artificial Analysis run)Not measured92.0%Only GPT-5.4 measured
Humanity's Last Exam (Artificial Analysis run)Not measured43.7%Only GPT-5.4 measured
GPQA Diamond (Epoch AI run)82.3%93.3%GPT-5.4
ARC-AGI63.7%93.7%GPT-5.4
ARC-AGI-213.6%74.0%GPT-5.4
SimpleBench54.3%Not measuredOnly Claude Sonnet 4.5 measured
Chess puzzles10.0%48.0%GPT-5.4
Mystery game puzzles17.0%37.0%GPT-5.4
EBR-bench2.4%25.4%GPT-5.4
VPCT39.8%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: hard prompts14621485GPT-5.4
LMArena Text: expert14831507GPT-5.4
LMArena Text: hard prompts in English14711479GPT-5.4
LMArena Vision: diagramsNot measured1327Only GPT-5.4 measured
LMArena Vision: homeworkNot measured1336Only GPT-5.4 measured
Kagi LLM Benchmark57.9%63.8%GPT-5.4
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index07
Math benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
AIME88.2%96.7%GPT-5.4
MGSM (Vals AI)94.3%Not measuredOnly Claude Sonnet 4.5 measured
OTIS Mock AIME77.8%97.8%GPT-5.4
FrontierMath, tiers 1 to 323.9%78.6%GPT-5.4
FrontierMath, tier 42.4%49.0%GPT-5.4
ProofBench19.0%56.0%GPT-5.4
MATH level 597.7%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: math14491488GPT-5.4
LMArena Text: mathematical work14621497GPT-5.4
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index112
Knowledge benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
MMLU Pro87.4%87.5%GPT-5.4
LegalBench (Vals AI)84.1%86.0%GPT-5.4
CaseLaw (Vals AI)62.2%63.8%GPT-5.4
CorpFin (Vals AI)62.0%65.3%GPT-5.4
TaxEval (Vals AI)73.3%74.0%GPT-5.4
MortgageTax (Vals AI)64.0%68.3%GPT-5.4
MedQA (Vals AI)94.7%96.1%GPT-5.4
MedCode (Vals AI)44.1%41.3%Claude Sonnet 4.5
SimpleQA Verified30.7%45.1%GPT-5.4
LMArena Text: science14481479GPT-5.4
LMArena Text: medicine and healthcare14441458GPT-5.4
LMArena Text: legal and government14511486GPT-5.4
LMArena Text: business and finance14401474GPT-5.4
FACTS Benchmark Suite40.6%Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index35
Web design benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
Design Arena: websites11891198GPT-5.4
Design Arena: UI components11701212GPT-5.4
Design Arena: game dev11661194GPT-5.4
Design Arena: data viz11671196GPT-5.4
Design Arena: 3D11571065Claude Sonnet 4.5
Design Arena: all code categories11821179Claude Sonnet 4.5
Design Arena: SVG11151141GPT-5.4
Design Arena: ASCII art12051188Claude Sonnet 4.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index418
General benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
SAGE (Vals AI)36.1%43.3%GPT-5.4
MedScribe (Vals AI)84.5%77.5%Claude Sonnet 4.5
IFBenchNot measured73.9%Only GPT-5.4 measured
Long context reasoning (AA-LCR)Not measured82.0%Only GPT-5.4 measured
DTBench83.2%94.4%GPT-5.4
LMCA38.8%52.0%GPT-5.4
CL-benchNot measured27.9%Only GPT-5.4 measured
Furniture assemblyNot measured37.5%Only GPT-5.4 measured
CL-bench LifeNot measured21.7%Only GPT-5.4 measured
LMArena Text14381469GPT-5.4
LMArena Text: instruction following14591469GPT-5.4
LMArena Text: creative writing14421439Claude Sonnet 4.5
LMArena VisionNot measured1303Only GPT-5.4 measured
LMArena Text: English14501467GPT-5.4
LMArena Text: non-English14251465GPT-5.4
LMArena Text: Chinese14601520GPT-5.4
LMArena Text: German14271472GPT-5.4
LMArena Text: Japanese13901485GPT-5.4
LMArena Text: Korean14021449GPT-5.4
LMArena Text: French14591493GPT-5.4
LMArena Text: Spanish14581452Claude Sonnet 4.5
LMArena Text: Russian14371480GPT-5.4
LMArena Text: Polish14231472GPT-5.4
LMArena Text: multi-turn14651482GPT-5.4
LMArena Text: longer queries14751473Claude Sonnet 4.5
LMArena Text: writing and language14421458GPT-5.4
LMArena Text: entertainment and media14281438GPT-5.4
LMArena Vision: EnglishNot measured1301Only GPT-5.4 measured
LMArena Vision: ChineseNot measured1354Only GPT-5.4 measured
LMArena Vision: reading textNot measured1312Only GPT-5.4 measured
LMArena Vision: humorNot measured1284Only GPT-5.4 measured
LMArena Vision: recognizing thingsNot measured1251Only GPT-5.4 measured
LMArena Vision: creative writingNot measured1283Only GPT-5.4 measured
LMArena Document14501471GPT-5.4
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 4.5 and GPT-5.4
BenchmarkClaude Sonnet 4.5GPT-5.4Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Sonnet 4.5$0.011Fits in one request
GPT-5.4$0.010Fits in one request

GPT-5.4 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.5$0.195Fits in one request
GPT-5.4$0.170Fits in one request

GPT-5.4 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.5$0.750Fits in one request
GPT-5.4$0.650Fits in one request

GPT-5.4 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Sonnet 4.5 and GPT-5.4
SpecificationAnthropic Claude Sonnet 4.5OpenAI GPT-5.4
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 29, 2025March 5, 2026
Context window1M1.05M
Input $/Mtok$3.00$2.50
Output $/Mtok$15.00$15.00
Coding index39.564.4
Independent measurements behind it33
Cost per solved task$1.16$1.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.5 better than GPT-5.4 for coding?

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5. Pick Claude Sonnet 4.5 for work measured by Design Arena: agents building web apps or Design Arena: agents building full-stack apps, where it leads.

Which is cheaper, Claude Sonnet 4.5 or GPT-5.4?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and GPT-5.4 $1.02.

Which has the bigger context window, Claude Sonnet 4.5 or GPT-5.4?

GPT-5.4, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.5 vs GPT-5.4 comparison based on?

82 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.5's coding index rests on 3 independent benchmarks and GPT-5.4's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-sonnet-4-5-vs-gpt-5-4" title="Claude Sonnet 4.5 vs GPT-5.4, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-sonnet-4-5-vs-gpt-5-4">LLMBenchmark.ai, Claude Sonnet 4.5 vs GPT-5.4</a></p>