Enter opens the highlighted result. Esc closes.

Claude Sonnet 5 vs GPT-5.5

GPT-5.5 leads Claude Sonnet 5 on coding, 71.3 to 57.7 on the Vibe Coding Index, and Claude Sonnet 5 costs 3.0x less per output token ($10.00 vs $30.00 per million). Updated October 22, 2026; 114 benchmarks have a result for both.

Replace Claude Sonnet 5 Replace GPT-5.5
Claude Sonnet 5Anthropic
Coding
57.7
Overall
63.2
Output $/M
$10.00
30
GPT-5.5OpenAI
Coding
71.3
Overall
69.2
Output $/M
$30.00
84
vs boards won of 114 shared

Claude Sonnet 5 or GPT-5.5: which to pick

Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 57.7 for Claude Sonnet 5, though on 5 benchmarks against 6.

Pick Claude Sonnet 5 for output tokens 3.0x cheaper ($10.00 vs $30.00 per million) and work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.

Model AClaude Sonnet 5Anthropic57.7/1006 independent benchmarks$1.87 per solved taskModel BGPT-5.5OpenAI71.3/1005 independent benchmarks$1.65 per solved task
Shared results
114
Claude Sonnet 5 only
7
GPT-5.5 only
20
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 5 57.7 from 6 benchmarks, GPT-5.5 71.3 from 5 benchmarks.
Widest category
Math, 17.7 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Claude Sonnet 5 29.3% against GPT-5.5 72.5%, 43.2 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5 $10.00 against GPT-5.5 $30.00 per million output tokens, 3.0x apart.
Context window
Claude Sonnet 5 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 5BarsGPT-5.5Ties
Coding416
Intelligence02
Agentic work154
Reasoning014
Math24
Knowledge29
Web design54
General231
All shared boards3084
CodingLike-for-likeSix of these boards feed the Vibe Coding Index416
Coding benchmarks for Claude Sonnet 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-5.5Leader
LiveBench coding74.7%85.1%GPT-5.5
LMArena WebDev15401513Claude Sonnet 5
AA Coding Index71.574.9GPT-5.5
LiveCodeBench (Vals AI)82.4%85.3%GPT-5.5
SWE-bench Verified (Vals AI)79.6%82.6%GPT-5.5
Terminal-Bench 4 (Vals AI)10.6%Not measuredOnly Claude Sonnet 5 measured
Vibe Code Bench (Vals AI)81.3%69.8%Claude Sonnet 5
Code migration (Vals AI)44.4%45.2%GPT-5.5
ProgramBench (Vals AI)0.0%0.5%GPT-5.5
IOI (Vals AI)45.0%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 2.1 (Vals AI)74.5%76.4%GPT-5.5
Vibe Code Bench 1-100 (Vals AI)13.8%Not measuredOnly Claude Sonnet 5 measured
SkillsBench (Vals AI)46.5%62.5%GPT-5.5
CyberBench (Vals AI)70.3%Not measuredOnly Claude Sonnet 5 measured
SciCode54.3%56.1%GPT-5.5
Terminal-Bench Hard (Artificial Analysis run)Not measured60.6%Only GPT-5.5 measured
Terminal-BenchNot measured84.7%Only GPT-5.5 measured
FrontierCode42.7%43.0%GPT-5.5
GSO-Bench37.3%40.2%GPT-5.5
WeirdML68.8%84.9%GPT-5.5
MirrorCodeNot measured10.0%Only GPT-5.5 measured
ALE-Bench1463.11943.0GPT-5.5
LMArena Text: coding14831494GPT-5.5
LMArena Text: software and IT14741493GPT-5.5
LMArena WebDev: React15411506Claude Sonnet 5
LMArena WebDev: HTML15271543GPT-5.5
LMArena WebDev: from an image15401532Claude Sonnet 5
SciCode10.7%Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 11 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-5.5Leader
AA Intelligence Index38.238.4GPT-5.5
Epoch Capabilities Index156.9159.7GPT-5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index154
Agentic work benchmarks for Claude Sonnet 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-5.5Leader
AA Agentic Index43.636.4Claude Sonnet 5
Design Arena: agents building web apps12451117Claude Sonnet 5
Design Arena: agents building full-stack apps12491089Claude Sonnet 5
Design Arena: agents building mobile apps12151142Claude Sonnet 5
Design Arena: agents building Android apps12271164Claude Sonnet 5
Design Arena: agents building Godot games12251173Claude Sonnet 5
Design Arena: agents building games12271179Claude Sonnet 5
Design Arena: HTML slides11681017Claude Sonnet 5
Design Arena: PowerPoint slides11911084Claude Sonnet 5
Design Arena: spreadsheets1035Not measuredOnly Claude Sonnet 5 measured
LiveBench research82.8%61.6%Claude Sonnet 5
LiveBench browser72.0%48.0%Claude Sonnet 5
LiveBench long agentic39.0%44.6%GPT-5.5
SREBench (Vals AI)0.4%3.8%GPT-5.5
Finance Agent (Vals AI)53.9%51.8%Claude Sonnet 5
Tax Agent Bench (Vals AI)29.4%21.8%Claude Sonnet 5
Legal Research Bench (Vals AI)41.8%40.4%Claude Sonnet 5
Excel Modeling Benchmark (Vals AI)66.3%64.5%Claude Sonnet 5
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly Claude Sonnet 5 measured
Time Horizon Index (Vals AI)Not measured8.3%Only GPT-5.5 measured
τ²-Bench TelecomNot measured93.9%Only GPT-5.5 measured
APEX-Agents54.5%55.1%GPT-5.5
Remote Labor IndexNot measured6.3%Only GPT-5.5 measured
OSWorld 2.0Not measured13.0%Only GPT-5.5 measured
DeepResearch BenchNot measured54.0%Only GPT-5.5 measured
PostTrainBenchNot measured27.2%Only GPT-5.5 measured
Vending-Bench 2$6,378$7,524GPT-5.5
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index014
Reasoning benchmarks for Claude Sonnet 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-5.5Leader
GPQA Diamond88.9%93.2%GPT-5.5
LiveBench reasoning88.7%89.7%GPT-5.5
MMMU Pro (Vals AI)83.0%88.3%GPT-5.5
GPQA Diamond (Artificial Analysis run)91.1%93.5%GPT-5.5
Humanity's Last Exam (Artificial Analysis run)41.3%45.8%GPT-5.5
GPQA Diamond (Epoch AI run)90.5%90.7%GPT-5.5
ARC-AGINot measured95.0%Only GPT-5.5 measured
ARC-AGI-2Not measured85.0%Only GPT-5.5 measured
SimpleBench60.6%69.0%GPT-5.5
Chess puzzles45.0%63.0%GPT-5.5
Mystery game puzzles35.0%56.0%GPT-5.5
EBR-benchNot measured34.3%Only GPT-5.5 measured
LMArena Text: hard prompts14611489GPT-5.5
LMArena Text: expert14891507GPT-5.5
LMArena Text: hard prompts in English14641483GPT-5.5
LMArena Vision: diagrams12931325GPT-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 index24
Math benchmarks for Claude Sonnet 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-5.5Leader
OTIS Mock AIME94.7%84.4%Claude Sonnet 5
FrontierMath, tiers 1 to 365.6%85.3%GPT-5.5
FrontierMath, tier 429.3%72.5%GPT-5.5
ProofBench77.0%50.0%Claude Sonnet 5
LMArena Text: math14671487GPT-5.5
LMArena Text: mathematical work14811496GPT-5.5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index29
Knowledge benchmarks for Claude Sonnet 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-5.5Leader
MMLU Pro87.5%88.1%GPT-5.5
LegalBench (Vals AI)83.9%86.5%GPT-5.5
CaseLaw (Vals AI)Not measured66.2%Only GPT-5.5 measured
CorpFin (Vals AI)67.0%68.4%GPT-5.5
TaxEval (Vals AI)75.6%75.0%Claude Sonnet 5
MortgageTax (Vals AI)70.0%68.8%Claude Sonnet 5
MedCode (Vals AI)47.5%49.1%GPT-5.5
SimpleQA Verified33.7%63.0%GPT-5.5
LMArena Text: science14601485GPT-5.5
LMArena Text: medicine and healthcare14421465GPT-5.5
LMArena Text: legal and government14541491GPT-5.5
LMArena Text: business and finance14361478GPT-5.5
FACTS Benchmark SuiteNot measured66.7%Only GPT-5.5 measured
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index54
Web design benchmarks for Claude Sonnet 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-5.5Leader
Design Arena: websites12741256Claude Sonnet 5
Design Arena: UI components12771257Claude Sonnet 5
Design Arena: game dev12771293GPT-5.5
Design Arena: data viz12511264GPT-5.5
Design Arena: 3D12611197Claude Sonnet 5
Design Arena: all code categories12751260Claude Sonnet 5
Design Arena: SVG11921234GPT-5.5
Design Arena: ASCII art12071255GPT-5.5
LiveBench design82.0%70.3%Claude Sonnet 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index231
General benchmarks for Claude Sonnet 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-5.5Leader
LiveBench data analysis71.7%81.6%GPT-5.5
Public Benefits Bench (Vals AI)66.0%60.9%Claude Sonnet 5
SAGE (Vals AI)48.9%51.5%GPT-5.5
MedScribe (Vals AI)76.0%86.9%GPT-5.5
Vals Multimodal Index68.8%68.1%Claude Sonnet 5
IFBenchNot measured75.9%Only GPT-5.5 measured
Long context reasoning (AA-LCR)82.0%84.3%GPT-5.5
DTBench92.5%96.0%GPT-5.5
LMCA50.0%54.3%GPT-5.5
Surface Evolver Bench60.0%88.1%GPT-5.5
Furniture assemblyNot measured44.2%Only GPT-5.5 measured
ExploitBenchNot measured47.4%Only GPT-5.5 measured
CL-bench LifeNot measured22.2%Only GPT-5.5 measured
LMArena Text14421471GPT-5.5
LMArena Text: instruction following14521478GPT-5.5
LMArena Text: creative writing14161455GPT-5.5
LMArena Vision12731297GPT-5.5
LMArena Text: English14501470GPT-5.5
LMArena Text: non-English14311467GPT-5.5
LMArena Text: Chinese14781534GPT-5.5
LMArena Text: German14421480GPT-5.5
LMArena Text: Japanese14221499GPT-5.5
LMArena Text: Korean14121460GPT-5.5
LMArena Text: French14631485GPT-5.5
LMArena Text: Spanish14381468GPT-5.5
LMArena Text: Russian14501473GPT-5.5
LMArena Text: Polish14251465GPT-5.5
LMArena Text: multi-turn14531476GPT-5.5
LMArena Text: longer queries14621484GPT-5.5
LMArena Text: writing and language14361466GPT-5.5
LMArena Text: entertainment and media14111449GPT-5.5
LMArena Vision: English12751292GPT-5.5
LMArena Vision: Chinese13311360GPT-5.5
LMArena Vision: reading text12881306GPT-5.5
LMArena Vision: humor12611293GPT-5.5
LMArena Vision: recognizing thingsNot measured1231Only GPT-5.5 measured
LMArena Vision: creative writing12461301GPT-5.5
LMArena Document14661486GPT-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 5 and GPT-5.5
BenchmarkClaude Sonnet 5GPT-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 5$0.0070Fits in one request
GPT-5.5$0.020Fits in one request

Claude Sonnet 5 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5$0.130Fits in one request
GPT-5.5$0.340Fits in one request

Claude Sonnet 5 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5$0.500Fits in one request
GPT-5.5$1.30Fits in one request

Claude Sonnet 5 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 5 and GPT-5.5
SpecificationAnthropic Claude Sonnet 5OpenAI GPT-5.5
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJune 30, 2026April 24, 2026
Context window1M1.05M
Input $/Mtok$2.00$5.00
Output $/Mtok$10.00$30.00
Coding index57.771.3
Independent measurements behind it65
Cost per solved task$1.87$1.65
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5 better than GPT-5.5 for coding?

Pick GPT-5.5 for coding: it scores 71.3 on the Vibe Coding Index against 57.7 for Claude Sonnet 5, though on 5 benchmarks against 6. Pick Claude Sonnet 5 for output tokens 3.0x cheaper ($10.00 vs $30.00 per million) and work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.

Which is cheaper, Claude Sonnet 5 or GPT-5.5?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-5.5 costs $5.00 and $30.00. Per solved SWE-bench Verified task, Claude Sonnet 5 costs $1.87 and GPT-5.5 $1.65.

Which has the bigger context window, Claude Sonnet 5 or GPT-5.5?

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

How many benchmarks is the Claude Sonnet 5 vs GPT-5.5 comparison based on?

114 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 5's coding index rests on 6 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-5-vs-gpt-5-5" title="Claude Sonnet 5 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-5-vs-gpt-5-5">LLMBenchmark.ai, Claude Sonnet 5 vs GPT-5.5</a></p>