LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs GPT-5.4 Mini

Updated October 21, 2026. 84 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 4.6 Replace GPT-5.4 Mini
Claude Sonnet 4.6Anthropic
Coding
57.8
Overall
30.1
Output $/M
$15.00
74
GPT-5.4 MiniOpenAI
Coding
28.2
Overall
24.1
Output $/M
$4.50
8
vs boards won of 84 shared, 2 tied

Decision reading

Pick Claude Sonnet 4.6 for coding: it scores 57.8 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.

Pick GPT-5.4 Mini when output tokens cost 3.3x less, or when a solved task costs $0.70 against $1.68.

Model AClaude Sonnet 4.6Anthropic57.8/1002 independent benchmarks$1.68 per solved taskModel BGPT-5.4 MiniOpenAI28.2/1001 independent benchmark$0.70 per solved task
Shared results
84
Claude Sonnet 4.6 only
33
GPT-5.4 Mini only
4
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 57.8 from 2 benchmarks, GPT-5.4 Mini 28.2 from 1 benchmark.
Widest category
Agentic work, 14.2 points apart on average over 7 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Sonnet 4.6 60.4% against GPT-5.4 Mini 18.9%, 41.5 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against GPT-5.4 Mini $4.50 per million output tokens, 3.3x apart.
Context window
Claude Sonnet 4.6 takes 1M tokens, GPT-5.4 Mini 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 MiniTies
Coding142
Intelligence20
Agentic work61
Reasoning1202 ties
Math32
Knowledge100
General273
All shared boards7482 ties
CodingLike-for-likeFour of these boards feed the Vibe Coding Index142
Coding benchmarks for Claude Sonnet 4.6 and GPT-5.4 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
LiveBench coding66.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena WebDev15231397Claude Sonnet 4.6
AA Coding Index63.056.1Claude Sonnet 4.6
LiveCodeBench (Vals AI)82.1%81.5%Claude Sonnet 4.6
SWE-bench Verified (Vals AI)77.4%73.0%Claude Sonnet 4.6
Terminal-Bench 4 (Vals AI)Not measured2.5%Only GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)55.8%48.0%Claude Sonnet 4.6
Code migration (Vals AI)39.9%12.9%Claude Sonnet 4.6
ProgramBench (Vals AI)0.5%0.0%Claude Sonnet 4.6
Terminal-Bench 2.1 (Vals AI)57.3%54.7%Claude Sonnet 4.6
SkillsBench (Vals AI)49.0%Not measuredOnly Claude Sonnet 4.6 measured
SciCode50.1%52.1%GPT-5.4 Mini
Terminal-Bench Hard (Artificial Analysis run)53.0%52.3%Claude Sonnet 4.6
Terminal-Bench53.4%Not measuredOnly Claude Sonnet 4.6 measured
FrontierCode24.3%27.0%GPT-5.4 Mini
WeirdML66.1%60.3%Claude Sonnet 4.6
ALE-BenchNot measured1188.6Only GPT-5.4 Mini measured
LMArena Text: coding15031438Claude Sonnet 4.6
LMArena Text: software and IT14911436Claude Sonnet 4.6
LMArena WebDev: React15121386Claude Sonnet 4.6
LMArena WebDev: HTML15271419Claude Sonnet 4.6
LMArena WebDev: from an image1529Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 16 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 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
AA Intelligence Index30.124.1Claude Sonnet 4.6
Epoch Capabilities Index152.8148.7Claude Sonnet 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index61
Agentic work benchmarks for Claude Sonnet 4.6 and GPT-5.4 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
AA Agentic Index31.817.9Claude 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 apps1202Not 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%45.4%Claude Sonnet 4.6
Tax Agent Bench (Vals AI)25.8%8.8%Claude Sonnet 4.6
Legal Research Bench (Vals AI)38.5%12.5%Claude Sonnet 4.6
Excel Modeling Benchmark (Vals AI)60.2%45.4%Claude Sonnet 4.6
τ²-Bench Telecom79.5%83.3%GPT-5.4 Mini
APEX-Agents43.0%Not measuredOnly Claude Sonnet 4.6 measured
OSWorld 2.09.3%Not measuredOnly Claude Sonnet 4.6 measured
DeepResearch Bench54.9%36.3%Claude Sonnet 4.6
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 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
Reasoning benchmarks for Claude Sonnet 4.6 and GPT-5.4 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
GPQA Diamond85.6%83.1%Claude Sonnet 4.6
LiveBench reasoning86.4%Not measuredOnly Claude Sonnet 4.6 measured
MMMU Pro (Vals AI)83.6%79.3%Claude Sonnet 4.6
GPQA Diamond (Artificial Analysis run)87.5%87.5%Tie
Humanity's Last Exam (Artificial Analysis run)33.6%28.1%Claude Sonnet 4.6
GPQA Diamond (Epoch AI run)87.4%86.9%Claude Sonnet 4.6
ARC-AGI86.5%63.7%Claude Sonnet 4.6
ARC-AGI-260.4%18.9%Claude Sonnet 4.6
Chess puzzles23.0%23.0%Tie
Mystery game puzzles16.0%11.0%Claude Sonnet 4.6
LMArena Text: hard prompts14851424Claude Sonnet 4.6
LMArena Text: expert15001435Claude Sonnet 4.6
LMArena Text: hard prompts in English14931420Claude Sonnet 4.6
LMArena Vision: diagrams13061266Claude Sonnet 4.6
LMArena Vision: homework13111285Claude Sonnet 4.6
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index32
Math benchmarks for Claude Sonnet 4.6 and GPT-5.4 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
AIME92.3%95.6%GPT-5.4 Mini
OTIS Mock AIME85.8%88.9%GPT-5.4 Mini
FrontierMath, tiers 1 to 3Not measured51.2%Only GPT-5.4 Mini measured
FrontierMath, tier 4Not measured9.8%Only GPT-5.4 Mini measured
ProofBench45.0%21.0%Claude Sonnet 4.6
LMArena Text: math14621418Claude Sonnet 4.6
LMArena Text: mathematical work14831429Claude 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 index100
Knowledge benchmarks for Claude Sonnet 4.6 and GPT-5.4 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
MMLU Pro87.3%84.5%Claude Sonnet 4.6
LegalBench (Vals AI)82.1%Not measuredOnly Claude Sonnet 4.6 measured
CaseLaw (Vals AI)64.0%51.7%Claude Sonnet 4.6
CorpFin (Vals AI)65.3%60.9%Claude Sonnet 4.6
TaxEval (Vals AI)77.1%71.2%Claude Sonnet 4.6
MortgageTax (Vals AI)67.7%63.5%Claude Sonnet 4.6
MedQA (Vals AI)92.1%Not measuredOnly Claude Sonnet 4.6 measured
SimpleQA Verified35.5%29.4%Claude Sonnet 4.6
LMArena Text: science14741417Claude Sonnet 4.6
LMArena Text: medicine and healthcare14511395Claude Sonnet 4.6
LMArena Text: legal and government14701414Claude Sonnet 4.6
LMArena Text: business and finance14641418Claude Sonnet 4.6
Neither model has a result on the other 5 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 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
Design Arena: websites1285Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: UI components1271Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: game dev1259Not 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 categories1276Not 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 index273
General benchmarks for Claude Sonnet 4.6 and GPT-5.4 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
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%50.8%GPT-5.4 Mini
Vals Multimodal Index60.6%54.2%Claude Sonnet 4.6
IFBench56.6%73.3%GPT-5.4 Mini
Long context reasoning (AA-LCR)80.0%77.0%Claude Sonnet 4.6
DTBench89.9%80.0%Claude Sonnet 4.6
LMCA46.5%40.8%Claude Sonnet 4.6
ExploitBench23.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text14581412Claude Sonnet 4.6
LMArena Text: instruction following14761405Claude Sonnet 4.6
LMArena Text: creative writing14351370Claude Sonnet 4.6
LMArena Vision12831245Claude Sonnet 4.6
LMArena Text: English14721412Claude Sonnet 4.6
LMArena Text: non-English14401405Claude Sonnet 4.6
LMArena Text: Chinese14911446Claude Sonnet 4.6
LMArena Text: German14281408Claude Sonnet 4.6
LMArena Text: Japanese14201375Claude Sonnet 4.6
LMArena Text: Korean14101370Claude Sonnet 4.6
LMArena Text: French14651441Claude Sonnet 4.6
LMArena Text: Spanish14641405Claude Sonnet 4.6
LMArena Text: Russian14401417Claude Sonnet 4.6
LMArena Text: Polish14431415Claude Sonnet 4.6
LMArena Text: multi-turn14641429Claude Sonnet 4.6
LMArena Text: longer queries14791408Claude Sonnet 4.6
LMArena Text: writing and language14441393Claude Sonnet 4.6
LMArena Text: entertainment and media14311373Claude Sonnet 4.6
LMArena Vision: English12981244Claude Sonnet 4.6
LMArena Vision: Chinese13071286Claude Sonnet 4.6
LMArena Vision: reading text12961253Claude Sonnet 4.6
LMArena Vision: humor12481235Claude Sonnet 4.6
LMArena Vision: recognizing things11951218GPT-5.4 Mini
LMArena Vision: creative writing12721222Claude Sonnet 4.6
LMArena Document1482Not measuredOnly Claude Sonnet 4.6 measured
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 4.6 and GPT-5.4 Mini
BenchmarkClaude Sonnet 4.6GPT-5.4 MiniLeader
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 Mini$0.0030Fits in one request

GPT-5.4 Mini costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
GPT-5.4 Mini$0.051Fits in one request

GPT-5.4 Mini costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
GPT-5.4 Mini$0.195Fits in one request

GPT-5.4 Mini 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 Mini
SpecificationAnthropic Claude Sonnet 4.6OpenAI GPT-5.4 Mini
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 17, 2026March 17, 2026
Context window1M400K
Input $/Mtok$3.00$0.75
Output $/Mtok$15.00$4.50
Coding index57.828.2
Independent measurements behind it21
Cost per solved task$1.68$0.70
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Claude Sonnet 4.6 for coding: it scores 57.8 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when output tokens cost 3.3x less, or when a solved task costs $0.70 against $1.68.

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

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and GPT-5.4 Mini $0.70.

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

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

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

84 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 4.6's coding index rests on 2 independent benchmarks and GPT-5.4 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next