Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs GPT-5.5

GPT-5.5 leads Claude Sonnet 4.6 on coding, 71.3 to 57.3 on the Vibe Coding Index, and Claude Sonnet 4.6 costs 2.0x less per output token ($15.00 vs $30.00 per million). Updated October 22, 2026; 115 benchmarks have a result for both.

Replace Claude Sonnet 4.6 Replace GPT-5.5
Claude Sonnet 4.6Anthropic
Coding
57.3
Overall
60.3
Output $/M
$15.00
24
GPT-5.5OpenAI
Coding
71.3
Overall
69.2
Output $/M
$30.00
90
vs boards won of 115 shared, 1 tied

Claude Sonnet 4.6 or GPT-5.5: which to pick

Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 57.3 for Claude Sonnet 4.6.

Pick Claude Sonnet 4.6 for output tokens 2.0x cheaper ($15.00 vs $30.00 per million) and work measured by LMArena WebDev or LMArena Text: coding, where it leads.

Model AClaude Sonnet 4.6Anthropic57.3/1005 independent benchmarks$1.68 per solved taskModel BGPT-5.5OpenAI71.3/1005 independent benchmarks$1.65 per solved task
Shared results
115
Claude Sonnet 4.6 only
3
GPT-5.5 only
19
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 4.6 57.3 from 5 benchmarks, GPT-5.5 71.3 from 5 benchmarks.
Widest category
Reasoning, 10.7 points apart on average over 15 shared benchmarks.
Widest single gap
Mystery game puzzles: Claude Sonnet 4.6 16.0% against GPT-5.5 56.0%, 40.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against GPT-5.5 $30.00 per million output tokens, 2.0x apart.
Context window
Claude Sonnet 4.6 takes 1M tokens, GPT-5.5 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 4.6BarsGPT-5.5Ties
Coding3161 tie
Intelligence02
Agentic work910
Reasoning114
Math13
Knowledge111
Web design63
General331
All shared boards24901 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index316
Coding benchmarks for Claude Sonnet 4.6 and GPT-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
LiveBench coding66.6%85.1%GPT-5.5
LMArena WebDev15231513Claude Sonnet 4.6
AA Coding Index63.074.9GPT-5.5
LiveCodeBench (Vals AI)82.1%85.3%GPT-5.5
SWE-bench Verified (Vals AI)77.4%82.6%GPT-5.5
Vibe Code Bench (Vals AI)55.8%69.8%GPT-5.5
Code migration (Vals AI)39.9%45.2%GPT-5.5
ProgramBench (Vals AI)0.5%0.5%Tie
Terminal-Bench 2.1 (Vals AI)57.3%76.4%GPT-5.5
SkillsBench (Vals AI)49.0%62.5%GPT-5.5
SciCode50.1%56.1%GPT-5.5
Terminal-Bench Hard (Artificial Analysis run)53.0%60.6%GPT-5.5
Terminal-Bench53.4%84.7%GPT-5.5
FrontierCode24.3%43.0%GPT-5.5
GSO-BenchNot measured40.2%Only GPT-5.5 measured
WeirdML66.1%84.9%GPT-5.5
MirrorCodeNot measured10.0%Only GPT-5.5 measured
ALE-BenchNot measured1943.0Only GPT-5.5 measured
LMArena Text: coding15031494Claude Sonnet 4.6
LMArena Text: software and IT14911493GPT-5.5
LMArena WebDev: React15121506Claude Sonnet 4.6
LMArena WebDev: HTML15271543GPT-5.5
LMArena WebDev: from an image15291532GPT-5.5
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.6 and GPT-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
AA Intelligence Index30.138.4GPT-5.5
Epoch Capabilities Index152.8159.7GPT-5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index910
Agentic work benchmarks for Claude Sonnet 4.6 and GPT-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
AA Agentic Index31.836.4GPT-5.5
Design Arena: agents building web apps11901117Claude Sonnet 4.6
Design Arena: agents building full-stack apps12131089Claude Sonnet 4.6
Design Arena: agents building mobile apps12121142Claude Sonnet 4.6
Design Arena: agents building Android apps11971164Claude Sonnet 4.6
Design Arena: agents building Godot games12261173Claude Sonnet 4.6
Design Arena: agents building games11771179GPT-5.5
Design Arena: HTML slidesNot measured1017Only GPT-5.5 measured
Design Arena: PowerPoint slidesNot measured1084Only GPT-5.5 measured
LiveBench research63.6%61.6%Claude Sonnet 4.6
LiveBench browser68.0%48.0%Claude Sonnet 4.6
LiveBench long agentic23.1%44.6%GPT-5.5
SREBench (Vals AI)Not measured3.8%Only GPT-5.5 measured
Finance Agent (Vals AI)51.0%51.8%GPT-5.5
Tax Agent Bench (Vals AI)25.8%21.8%Claude Sonnet 4.6
Legal Research Bench (Vals AI)38.5%40.4%GPT-5.5
Excel Modeling Benchmark (Vals AI)60.2%64.5%GPT-5.5
Time Horizon Index (Vals AI)Not measured8.3%Only GPT-5.5 measured
τ²-Bench Telecom79.5%93.9%GPT-5.5
APEX-Agents43.0%55.1%GPT-5.5
Remote Labor IndexNot measured6.3%Only GPT-5.5 measured
OSWorld 2.09.3%13.0%GPT-5.5
DeepResearch Bench54.9%54.0%Claude Sonnet 4.6
PostTrainBenchNot measured27.2%Only GPT-5.5 measured
OSWorld72.1%Not measuredOnly Claude Sonnet 4.6 measured
Vending-Bench 2$7,204$7,524GPT-5.5
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index114
Reasoning benchmarks for Claude Sonnet 4.6 and GPT-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
GPQA Diamond85.6%93.2%GPT-5.5
LiveBench reasoning86.4%89.7%GPT-5.5
MMMU Pro (Vals AI)83.6%88.3%GPT-5.5
GPQA Diamond (Artificial Analysis run)87.5%93.5%GPT-5.5
Humanity's Last Exam (Artificial Analysis run)33.6%45.8%GPT-5.5
GPQA Diamond (Epoch AI run)87.4%90.7%GPT-5.5
ARC-AGI86.5%95.0%GPT-5.5
ARC-AGI-260.4%85.0%GPT-5.5
SimpleBenchNot measured69.0%Only GPT-5.5 measured
Chess puzzles23.0%63.0%GPT-5.5
Mystery game puzzles16.0%56.0%GPT-5.5
EBR-benchNot measured34.3%Only GPT-5.5 measured
LMArena Text: hard prompts14851489GPT-5.5
LMArena Text: expert15001507GPT-5.5
LMArena Text: hard prompts in English14931483Claude Sonnet 4.6
LMArena Vision: diagrams13061325GPT-5.5
LMArena Vision: homework13111332GPT-5.5
Kagi LLM BenchmarkNot measured88.8%Only GPT-5.5 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index13
Math benchmarks for Claude Sonnet 4.6 and GPT-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
AIME92.3%Not measuredOnly Claude Sonnet 4.6 measured
OTIS Mock AIME85.8%84.4%Claude Sonnet 4.6
FrontierMath, tiers 1 to 3Not measured85.3%Only GPT-5.5 measured
FrontierMath, tier 4Not measured72.5%Only GPT-5.5 measured
ProofBench45.0%50.0%GPT-5.5
LMArena Text: math14621487GPT-5.5
LMArena Text: mathematical work14831496GPT-5.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
Knowledge benchmarks for Claude Sonnet 4.6 and GPT-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
MMLU Pro87.3%88.1%GPT-5.5
LegalBench (Vals AI)82.1%86.5%GPT-5.5
CaseLaw (Vals AI)64.0%66.2%GPT-5.5
CorpFin (Vals AI)65.3%68.4%GPT-5.5
TaxEval (Vals AI)77.1%75.0%Claude Sonnet 4.6
MortgageTax (Vals AI)67.7%68.8%GPT-5.5
MedQA (Vals AI)92.1%Not measuredOnly Claude Sonnet 4.6 measured
MedCode (Vals AI)Not measured49.1%Only GPT-5.5 measured
SimpleQA Verified35.5%63.0%GPT-5.5
LMArena Text: science14741485GPT-5.5
LMArena Text: medicine and healthcare14511465GPT-5.5
LMArena Text: legal and government14701491GPT-5.5
LMArena Text: business and finance14641478GPT-5.5
FACTS Benchmark Suite37.0%66.7%GPT-5.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index63
Web design benchmarks for Claude Sonnet 4.6 and GPT-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
Design Arena: websites12841256Claude Sonnet 4.6
Design Arena: UI components12691257Claude Sonnet 4.6
Design Arena: game dev12581293GPT-5.5
Design Arena: data viz12781264Claude Sonnet 4.6
Design Arena: 3D12341197Claude Sonnet 4.6
Design Arena: all code categories12751260Claude Sonnet 4.6
Design Arena: SVG11961234GPT-5.5
Design Arena: ASCII art12351255GPT-5.5
LiveBench design71.8%70.3%Claude Sonnet 4.6
GeneralLike-for-likePublic boards, shown as published, kept out of the index331
General benchmarks for Claude Sonnet 4.6 and GPT-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
LiveBench data analysis76.1%81.6%GPT-5.5
Public Benefits Bench (Vals AI)62.5%60.9%Claude Sonnet 4.6
SAGE (Vals AI)46.6%51.5%GPT-5.5
MedScribe (Vals AI)Not measured86.9%Only GPT-5.5 measured
Vals Multimodal Index60.6%68.1%GPT-5.5
IFBench56.6%75.9%GPT-5.5
Long context reasoning (AA-LCR)80.0%84.3%GPT-5.5
DTBench89.9%96.0%GPT-5.5
LMCA46.5%54.3%GPT-5.5
Surface Evolver BenchNot measured88.1%Only GPT-5.5 measured
Furniture assemblyNot measured44.2%Only GPT-5.5 measured
ExploitBench23.6%47.4%GPT-5.5
CL-bench LifeNot measured22.2%Only GPT-5.5 measured
LMArena Text14581471GPT-5.5
LMArena Text: instruction following14761478GPT-5.5
LMArena Text: creative writing14351455GPT-5.5
LMArena Vision12831297GPT-5.5
LMArena Text: English14721470Claude Sonnet 4.6
LMArena Text: non-English14401467GPT-5.5
LMArena Text: Chinese14911534GPT-5.5
LMArena Text: German14281480GPT-5.5
LMArena Text: Japanese14201499GPT-5.5
LMArena Text: Korean14101460GPT-5.5
LMArena Text: French14651485GPT-5.5
LMArena Text: Spanish14641468GPT-5.5
LMArena Text: Russian14401473GPT-5.5
LMArena Text: Polish14431465GPT-5.5
LMArena Text: multi-turn14641476GPT-5.5
LMArena Text: longer queries14791484GPT-5.5
LMArena Text: writing and language14441466GPT-5.5
LMArena Text: entertainment and media14311449GPT-5.5
LMArena Vision: English12981292Claude Sonnet 4.6
LMArena Vision: Chinese13071360GPT-5.5
LMArena Vision: reading text12961306GPT-5.5
LMArena Vision: humor12481293GPT-5.5
LMArena Vision: recognizing things11951231GPT-5.5
LMArena Vision: creative writing12721301GPT-5.5
LMArena Document14821486GPT-5.5
Neither model has a result on the other 8 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-5.5
BenchmarkClaude Sonnet 4.6GPT-5.5Leader
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-5.5$0.020Fits in one request

Claude Sonnet 4.6 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
GPT-5.5$0.340Fits in one request

Claude Sonnet 4.6 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
GPT-5.5$1.30Fits in one request

Claude Sonnet 4.6 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-5.5
SpecificationAnthropic Claude Sonnet 4.6OpenAI GPT-5.5
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 17, 2026April 24, 2026
Context window1M1.05M
Input $/Mtok$3.00$5.00
Output $/Mtok$15.00$30.00
Coding index57.371.3
Independent measurements behind it55
Cost per solved task$1.68$1.65
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.6 better than GPT-5.5 for coding?

Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 57.3 for Claude Sonnet 4.6. Pick Claude Sonnet 4.6 for output tokens 2.0x cheaper ($15.00 vs $30.00 per million) and work measured by LMArena WebDev or LMArena Text: coding, where it leads.

Which is cheaper, Claude Sonnet 4.6 or GPT-5.5?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.5 costs $5.00 and $30.00. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and GPT-5.5 $1.65.

Which has the bigger context window, Claude Sonnet 4.6 or GPT-5.5?

GPT-5.5, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.6 vs GPT-5.5 comparison based on?

115 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-5.5's on 5. 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-5-5" title="Claude Sonnet 4.6 vs GPT-5.5, 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-5-5">LLMBenchmark.ai, Claude Sonnet 4.6 vs GPT-5.5</a></p>