Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs GPT-5.4 Nano

Claude Sonnet 4.6 leads GPT-5.4 Nano on coding, 57.3 to 44.8 on the Vibe Coding Index, and GPT-5.4 Nano costs 12.0x less per output token ($1.25 vs $15.00 per million). Updated October 22, 2026; 79 benchmarks have a result for both.

Replace Claude Sonnet 4.6 Replace GPT-5.4 Nano
Claude Sonnet 4.6Anthropic
Coding
57.3
Overall
60.3
Output $/M
$15.00
75
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
4
vs boards won of 79 shared

Claude Sonnet 4.6 or GPT-5.4 Nano: which to pick

Pick Claude Sonnet 4.6 for coding: it scores 57.3 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano.

Pick GPT-5.4 Nano for output tokens 12.0x cheaper ($1.25 vs $15.00 per million) and a lower cost per solved task ($0.14 against $1.68).

Model AClaude Sonnet 4.6Anthropic57.3/1005 independent benchmarks$1.68 per solved taskModel BGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved task
Shared results
79
Claude Sonnet 4.6 only
39
GPT-5.4 Nano only
6
Like-for-like categories
7 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 4.6 57.3 from 5 benchmarks, GPT-5.4 Nano 44.8 from 2 benchmarks.
Widest category
Reasoning, 17.1 points apart on average over 14 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Sonnet 4.6 60.4% against GPT-5.4 Nano 5.7%, 54.7 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against GPT-5.4 Nano $1.25 per million output tokens, 12.0x apart.
Context window
Claude Sonnet 4.6 takes 1M tokens, GPT-5.4 Nano 400K.

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 4.6BarsGPT-5.4 NanoTies
Coding101
Intelligence20
Agentic work60
Reasoning131
Math41
Knowledge110
General291
All shared boards754
CodingLike-for-likeSix of these boards feed the Vibe Coding Index101
Coding benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
LiveBench coding66.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena WebDev1523Not measuredOnly Claude Sonnet 4.6 measured
AA Coding Index63.056.1Claude Sonnet 4.6
LiveCodeBench (Vals AI)82.1%84.0%GPT-5.4 Nano
SWE-bench Verified (Vals AI)77.4%69.8%Claude Sonnet 4.6
Vibe Code Bench (Vals AI)55.8%26.1%Claude Sonnet 4.6
Code migration (Vals AI)39.9%14.5%Claude Sonnet 4.6
ProgramBench (Vals AI)0.5%Not measuredOnly Claude Sonnet 4.6 measured
Terminal-Bench 2.1 (Vals AI)57.3%41.6%Claude Sonnet 4.6
SkillsBench (Vals AI)49.0%Not measuredOnly Claude Sonnet 4.6 measured
SciCode50.1%47.2%Claude Sonnet 4.6
Terminal-Bench Hard (Artificial Analysis run)53.0%42.4%Claude Sonnet 4.6
Terminal-Bench53.4%Not measuredOnly Claude Sonnet 4.6 measured
FrontierCode24.3%Not measuredOnly Claude Sonnet 4.6 measured
WeirdML66.1%49.2%Claude Sonnet 4.6
ALE-BenchNot measured1004.5Only GPT-5.4 Nano measured
LMArena Text: coding15031404Claude Sonnet 4.6
LMArena Text: software and IT14911402Claude Sonnet 4.6
LMArena WebDev: React1512Not measuredOnly Claude Sonnet 4.6 measured
LMArena WebDev: HTML1527Not measuredOnly Claude Sonnet 4.6 measured
LMArena WebDev: from an image1529Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
AA Intelligence Index30.120.7Claude Sonnet 4.6
Epoch Capabilities Index152.8146.0Claude Sonnet 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
AA Agentic Index31.816.0Claude Sonnet 4.6
Design Arena: agents building web apps1190Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building full-stack apps1213Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building mobile apps1212Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building Android apps1197Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building Godot games1226Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building games1177Not measuredOnly Claude Sonnet 4.6 measured
LiveBench research63.6%Not measuredOnly Claude Sonnet 4.6 measured
LiveBench browser68.0%Not measuredOnly Claude Sonnet 4.6 measured
LiveBench long agentic23.1%Not measuredOnly Claude Sonnet 4.6 measured
Finance Agent (Vals AI)51.0%38.2%Claude Sonnet 4.6
Tax Agent Bench (Vals AI)25.8%5.0%Claude Sonnet 4.6
Legal Research Bench (Vals AI)38.5%6.3%Claude Sonnet 4.6
Excel Modeling Benchmark (Vals AI)60.2%44.8%Claude Sonnet 4.6
τ²-Bench Telecom79.5%76.0%Claude Sonnet 4.6
APEX-Agents43.0%Not measuredOnly Claude Sonnet 4.6 measured
OSWorld 2.09.3%Not measuredOnly Claude Sonnet 4.6 measured
DeepResearch Bench54.9%Not measuredOnly Claude Sonnet 4.6 measured
OSWorld72.1%Not measuredOnly Claude Sonnet 4.6 measured
Vending-Bench 2$7,204Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index131
Reasoning benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
GPQA Diamond85.6%77.5%Claude Sonnet 4.6
LiveBench reasoning86.4%Not measuredOnly Claude Sonnet 4.6 measured
MMMU Pro (Vals AI)83.6%73.6%Claude Sonnet 4.6
GPQA Diamond (Artificial Analysis run)87.5%81.7%Claude Sonnet 4.6
Humanity's Last Exam (Artificial Analysis run)33.6%28.3%Claude Sonnet 4.6
GPQA Diamond (Epoch AI run)87.4%78.5%Claude Sonnet 4.6
ARC-AGI86.5%51.5%Claude Sonnet 4.6
ARC-AGI-260.4%5.7%Claude Sonnet 4.6
Chess puzzles23.0%45.0%GPT-5.4 Nano
Mystery game puzzles16.0%9.0%Claude Sonnet 4.6
LMArena Text: hard prompts14851381Claude Sonnet 4.6
LMArena Text: expert15001396Claude Sonnet 4.6
LMArena Text: hard prompts in English14931387Claude Sonnet 4.6
LMArena Vision: diagrams13061210Claude Sonnet 4.6
LMArena Vision: homework13111225Claude Sonnet 4.6
Kagi LLM BenchmarkNot measured39.7%Only GPT-5.4 Nano measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index41
Math benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
AIME92.3%88.8%Claude Sonnet 4.6
OTIS Mock AIME85.8%87.8%GPT-5.4 Nano
FrontierMath, tiers 1 to 3Not measured44.9%Only GPT-5.4 Nano measured
FrontierMath, tier 4Not measured12.2%Only GPT-5.4 Nano measured
ProofBench45.0%5.0%Claude Sonnet 4.6
LMArena Text: math14621405Claude Sonnet 4.6
LMArena Text: mathematical work14831409Claude Sonnet 4.6
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
MMLU Pro87.3%77.2%Claude Sonnet 4.6
LegalBench (Vals AI)82.1%77.9%Claude Sonnet 4.6
CaseLaw (Vals AI)64.0%51.9%Claude Sonnet 4.6
CorpFin (Vals AI)65.3%61.2%Claude Sonnet 4.6
TaxEval (Vals AI)77.1%67.4%Claude Sonnet 4.6
MortgageTax (Vals AI)67.7%59.1%Claude Sonnet 4.6
MedQA (Vals AI)92.1%Not measuredOnly Claude Sonnet 4.6 measured
MedCode (Vals AI)Not measured41.0%Only GPT-5.4 Nano measured
SimpleQA Verified35.5%11.7%Claude Sonnet 4.6
LMArena Text: science14741374Claude Sonnet 4.6
LMArena Text: medicine and healthcare14511369Claude Sonnet 4.6
LMArena Text: legal and government14701368Claude Sonnet 4.6
LMArena Text: business and finance14641366Claude Sonnet 4.6
FACTS Benchmark Suite37.0%Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
Design Arena: websites1284Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: UI components1269Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: game dev1258Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: data viz1278Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: 3D1234Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: all code categories1275Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: SVG1196Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: ASCII art1235Not measuredOnly Claude Sonnet 4.6 measured
LiveBench design71.8%Not measuredOnly Claude Sonnet 4.6 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index291
General benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
LiveBench data analysis76.1%Not measuredOnly Claude Sonnet 4.6 measured
Public Benefits Bench (Vals AI)62.5%Not measuredOnly Claude Sonnet 4.6 measured
SAGE (Vals AI)46.6%38.1%Claude Sonnet 4.6
MedScribe (Vals AI)Not measured77.1%Only GPT-5.4 Nano measured
Vals Multimodal Index60.6%47.6%Claude Sonnet 4.6
IFBench56.6%75.9%GPT-5.4 Nano
Long context reasoning (AA-LCR)80.0%76.7%Claude Sonnet 4.6
DTBench89.9%80.3%Claude Sonnet 4.6
LMCA46.5%36.9%Claude Sonnet 4.6
ExploitBench23.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text14581372Claude Sonnet 4.6
LMArena Text: instruction following14761362Claude Sonnet 4.6
LMArena Text: creative writing14351315Claude Sonnet 4.6
LMArena Vision12831196Claude Sonnet 4.6
LMArena Text: English14721381Claude Sonnet 4.6
LMArena Text: non-English14401359Claude Sonnet 4.6
LMArena Text: Chinese14911391Claude Sonnet 4.6
LMArena Text: German14281368Claude Sonnet 4.6
LMArena Text: Japanese14201343Claude Sonnet 4.6
LMArena Text: Korean14101321Claude Sonnet 4.6
LMArena Text: French14651395Claude Sonnet 4.6
LMArena Text: Spanish14641371Claude Sonnet 4.6
LMArena Text: Russian14401363Claude Sonnet 4.6
LMArena Text: Polish14431366Claude Sonnet 4.6
LMArena Text: multi-turn14641382Claude Sonnet 4.6
LMArena Text: longer queries14791365Claude Sonnet 4.6
LMArena Text: writing and language14441338Claude Sonnet 4.6
LMArena Text: entertainment and media14311325Claude Sonnet 4.6
LMArena Vision: English12981202Claude Sonnet 4.6
LMArena Vision: Chinese13071232Claude Sonnet 4.6
LMArena Vision: reading text12961204Claude Sonnet 4.6
LMArena Vision: humor12481161Claude Sonnet 4.6
LMArena Vision: recognizing things11951141Claude Sonnet 4.6
LMArena Vision: creative writing12721159Claude Sonnet 4.6
LMArena Document1482Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 4.6 and GPT-5.4 Nano
BenchmarkClaude Sonnet 4.6GPT-5.4 NanoLeader
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 4.6$0.011Fits in one request
GPT-5.4 Nano$0.0008Fits in one request

GPT-5.4 Nano costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
GPT-5.4 Nano$0.014Fits in one request

GPT-5.4 Nano costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
GPT-5.4 Nano$0.052Fits in one request

GPT-5.4 Nano 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 4.6 and GPT-5.4 Nano
SpecificationAnthropic Claude Sonnet 4.6OpenAI GPT-5.4 Nano
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 17, 2026March 17, 2026
Context window1M400K
Input $/Mtok$3.00$0.20
Output $/Mtok$15.00$1.25
Coding index57.344.8
Independent measurements behind it52
Cost per solved task$1.68$0.14
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.6 better than GPT-5.4 Nano for coding?

Pick Claude Sonnet 4.6 for coding: it scores 57.3 on the Vibe Coding Index against 44.8 for GPT-5.4 Nano. Pick GPT-5.4 Nano for output tokens 12.0x cheaper ($1.25 vs $15.00 per million) and a lower cost per solved task ($0.14 against $1.68).

Which is cheaper, Claude Sonnet 4.6 or GPT-5.4 Nano?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.4 Nano costs $0.20 and $1.25. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and GPT-5.4 Nano $0.14.

Which has the bigger context window, Claude Sonnet 4.6 or GPT-5.4 Nano?

Claude Sonnet 4.6, with 1M tokens against 400K.

How many benchmarks is the Claude Sonnet 4.6 vs GPT-5.4 Nano comparison based on?

79 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.6's coding index rests on 5 independent benchmarks and GPT-5.4 Nano's on 2. 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-4-6-vs-gpt-5-4-nano" title="Claude Sonnet 4.6 vs GPT-5.4 Nano, 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-4-6-vs-gpt-5-4-nano">LLMBenchmark.ai, Claude Sonnet 4.6 vs GPT-5.4 Nano</a></p>