Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs GPT-5.6 Luna

GPT-5.6 Luna leads Claude Sonnet 4.6 on coding, 58.0 to 57.3 on the Vibe Coding Index, and GPT-5.6 Luna costs 12.5x less per output token ($1.20 vs $15.00 per million). Updated October 22, 2026; 99 benchmarks have a result for both.

Replace Claude Sonnet 4.6 Replace GPT-5.6 Luna
Claude Sonnet 4.6Anthropic
Coding
57.3
Overall
60.3
Output $/M
$15.00
63
GPT-5.6 LunaOpenAI
Coding
58.0
Overall
61.6
Output $/M
$1.20
34
vs boards won of 99 shared, 2 tied

Claude Sonnet 4.6 or GPT-5.6 Luna: which to pick

Claude Sonnet 4.6 and GPT-5.6 Luna are level for coding, 57.3 against 58.0 on the Vibe Coding Index, so price and context decide.

Pick Claude Sonnet 4.6 for work measured by LMArena WebDev or ProgramBench (Vals AI), where it leads. Pick GPT-5.6 Luna for output tokens 12.5x cheaper ($1.20 vs $15.00 per million) and a lower cost per solved task ($0.04 against $1.68).

Model AClaude Sonnet 4.6Anthropic57.3/1005 independent benchmarks$1.68 per solved taskModel BGPT-5.6 LunaOpenAI58.0/1006 independent benchmarks$0.04 per solved task
Shared results
99
Claude Sonnet 4.6 only
19
GPT-5.6 Luna 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 4.6 57.3 from 5 benchmarks, GPT-5.6 Luna 58.0 from 6 benchmarks.
Widest category
Coding, 8.2 points apart on average over 17 shared benchmarks.
Widest single gap
FrontierCode: Claude Sonnet 4.6 24.3% against GPT-5.6 Luna 39.8%, 23.8 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against GPT-5.6 Luna $1.20 per million output tokens, 12.5x apart.
Context window
Claude Sonnet 4.6 takes 1M tokens, GPT-5.6 Luna 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-5.6 LunaTies
Coding89
Intelligence02
Agentic work442 ties
Reasoning78
Math22
Knowledge92
Web design81
General256
All shared boards63342 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index89
Coding benchmarks for Claude Sonnet 4.6 and GPT-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
LiveBench coding66.6%73.6%GPT-5.6 Luna
LMArena WebDev15231518Claude Sonnet 4.6
AA Coding Index63.071.4GPT-5.6 Luna
LiveCodeBench (Vals AI)82.1%Not measuredOnly Claude Sonnet 4.6 measured
SWE-bench Verified (Vals AI)77.4%93.0%GPT-5.6 Luna
Terminal-Bench 4 (Vals AI)Not measured11.6%Only GPT-5.6 Luna measured
Vibe Code Bench (Vals AI)55.8%77.1%GPT-5.6 Luna
Code migration (Vals AI)39.9%44.5%GPT-5.6 Luna
ProgramBench (Vals AI)0.5%0.0%Claude Sonnet 4.6
IOI (Vals AI)Not measured61.8%Only GPT-5.6 Luna measured
Terminal-Bench 2.1 (Vals AI)57.3%79.0%GPT-5.6 Luna
Vibe Code Bench 1-100 (Vals AI)Not measured22.6%Only GPT-5.6 Luna measured
SkillsBench (Vals AI)49.0%60.5%GPT-5.6 Luna
CyberBench (Vals AI)Not measured73.6%Only GPT-5.6 Luna measured
SciCode50.1%53.6%GPT-5.6 Luna
Terminal-Bench Hard (Artificial Analysis run)53.0%Not measuredOnly Claude Sonnet 4.6 measured
Terminal-Bench53.4%Not measuredOnly Claude Sonnet 4.6 measured
FrontierCode24.3%39.8%GPT-5.6 Luna
WeirdML66.1%60.9%Claude Sonnet 4.6
ALE-BenchNot measured1667.4Only GPT-5.6 Luna measured
LMArena Text: coding15031466Claude Sonnet 4.6
LMArena Text: software and IT14911463Claude Sonnet 4.6
LMArena WebDev: React15121508Claude Sonnet 4.6
LMArena WebDev: HTML15271520Claude Sonnet 4.6
LMArena WebDev: from an image15291517Claude Sonnet 4.6
SciCodeNot measured6.2%Only GPT-5.6 Luna measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.6 and GPT-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
AA Intelligence Index30.137.3GPT-5.6 Luna
Epoch Capabilities Index152.8156.5GPT-5.6 Luna
Agentic workLike-for-likePublic boards, shown as published, kept out of the index44
Agentic work benchmarks for Claude Sonnet 4.6 and GPT-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
AA Agentic Index31.842.1GPT-5.6 Luna
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%51.0%Claude Sonnet 4.6
LiveBench browser68.0%68.0%Tie
LiveBench long agentic23.1%30.4%GPT-5.6 Luna
SREBench (Vals AI)Not measured1.5%Only GPT-5.6 Luna measured
Finance Agent (Vals AI)51.0%55.0%GPT-5.6 Luna
Tax Agent Bench (Vals AI)25.8%24.8%Claude Sonnet 4.6
Legal Research Bench (Vals AI)38.5%36.5%Claude Sonnet 4.6
Excel Modeling Benchmark (Vals AI)60.2%67.1%GPT-5.6 Luna
BioMysteryBench (Vals AI)Not measured61.5%Only GPT-5.6 Luna measured
Terminal-Bench-Science (Vals AI)Not measured0.0%Only GPT-5.6 Luna measured
Vals Science IndexNot measured25.3%Only GPT-5.6 Luna measured
τ²-Bench Telecom79.5%Not measuredOnly Claude Sonnet 4.6 measured
APEX-Agents43.0%43.0%Tie
OSWorld 2.09.3%Not measuredOnly Claude Sonnet 4.6 measured
BALROGNot measured45.6%Only GPT-5.6 Luna measured
DeepResearch Bench54.9%Not measuredOnly Claude Sonnet 4.6 measured
OSWorld72.1%Not measuredOnly Claude Sonnet 4.6 measured
Vending-Bench 2$7,204$4,095Claude Sonnet 4.6
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index78
Reasoning benchmarks for Claude Sonnet 4.6 and GPT-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
GPQA Diamond85.6%91.7%GPT-5.6 Luna
LiveBench reasoning86.4%85.6%Claude Sonnet 4.6
MysteryMechanism (Vals AI)Not measured14.4%Only GPT-5.6 Luna measured
MMMU Pro (Vals AI)83.6%85.0%GPT-5.6 Luna
GPQA Diamond (Artificial Analysis run)87.5%91.1%GPT-5.6 Luna
Humanity's Last Exam (Artificial Analysis run)33.6%39.5%GPT-5.6 Luna
GPQA Diamond (Epoch AI run)87.4%91.6%GPT-5.6 Luna
ARC-AGI86.5%88.0%GPT-5.6 Luna
ARC-AGI-260.4%59.5%Claude Sonnet 4.6
SimpleBenchNot measured46.8%Only GPT-5.6 Luna measured
Chess puzzles23.0%43.0%GPT-5.6 Luna
Mystery game puzzles16.0%21.0%GPT-5.6 Luna
LMArena Text: hard prompts14851451Claude Sonnet 4.6
LMArena Text: expert15001478Claude Sonnet 4.6
LMArena Text: hard prompts in English14931460Claude Sonnet 4.6
LMArena Vision: diagrams13061273Claude Sonnet 4.6
LMArena Vision: homework13111282Claude Sonnet 4.6
Kagi LLM BenchmarkNot measured49.1%Only GPT-5.6 Luna measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for Claude Sonnet 4.6 and GPT-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
AIME92.3%Not measuredOnly Claude Sonnet 4.6 measured
OTIS Mock AIME85.8%98.3%GPT-5.6 Luna
FrontierMath, tiers 1 to 3Not measured82.1%Only GPT-5.6 Luna measured
FrontierMath, tier 4Not measured61.0%Only GPT-5.6 Luna measured
ProofBench45.0%60.0%GPT-5.6 Luna
LMArena Text: math14621459Claude Sonnet 4.6
LMArena Text: mathematical work14831470Claude 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 index92
Knowledge benchmarks for Claude Sonnet 4.6 and GPT-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
MMLU Pro87.3%86.0%Claude Sonnet 4.6
LegalBench (Vals AI)82.1%84.0%GPT-5.6 Luna
CaseLaw (Vals AI)64.0%Not measuredOnly Claude Sonnet 4.6 measured
CorpFin (Vals AI)65.3%64.2%Claude Sonnet 4.6
TaxEval (Vals AI)77.1%76.2%Claude Sonnet 4.6
MortgageTax (Vals AI)67.7%67.3%Claude Sonnet 4.6
MedQA (Vals AI)92.1%Not measuredOnly Claude Sonnet 4.6 measured
MedCode (Vals AI)Not measured42.4%Only GPT-5.6 Luna measured
SimpleQA Verified35.5%41.0%GPT-5.6 Luna
LMArena Text: science14741433Claude Sonnet 4.6
LMArena Text: medicine and healthcare14511399Claude Sonnet 4.6
LMArena Text: legal and government14701446Claude Sonnet 4.6
LMArena Text: business and finance14641439Claude Sonnet 4.6
FACTS Benchmark Suite37.0%35.0%Claude Sonnet 4.6
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index81
Web design benchmarks for Claude Sonnet 4.6 and GPT-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
Design Arena: websites12841255Claude Sonnet 4.6
Design Arena: UI components12691248Claude Sonnet 4.6
Design Arena: game dev12581194Claude Sonnet 4.6
Design Arena: data viz12781211Claude Sonnet 4.6
Design Arena: 3D12341121Claude Sonnet 4.6
Design Arena: all code categories12751231Claude Sonnet 4.6
Design Arena: SVG11961194Claude Sonnet 4.6
Design Arena: ASCII art12351142Claude Sonnet 4.6
LiveBench design71.8%76.0%GPT-5.6 Luna
GeneralLike-for-likePublic boards, shown as published, kept out of the index256
General benchmarks for Claude Sonnet 4.6 and GPT-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
LiveBench data analysis76.1%78.0%GPT-5.6 Luna
Public Benefits Bench (Vals AI)62.5%61.2%Claude Sonnet 4.6
SAGE (Vals AI)46.6%44.2%Claude Sonnet 4.6
MedScribe (Vals AI)Not measured84.4%Only GPT-5.6 Luna measured
Vals Multimodal Index60.6%69.1%GPT-5.6 Luna
IFBench56.6%Not measuredOnly Claude Sonnet 4.6 measured
Long context reasoning (AA-LCR)80.0%83.7%GPT-5.6 Luna
DTBench89.9%89.1%Claude Sonnet 4.6
LMCA46.5%48.5%GPT-5.6 Luna
Surface Evolver BenchNot measured61.9%Only GPT-5.6 Luna measured
Furniture assemblyNot measured42.5%Only GPT-5.6 Luna measured
ExploitBench23.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text14581431Claude Sonnet 4.6
LMArena Text: instruction following14761437Claude Sonnet 4.6
LMArena Text: creative writing14351396Claude Sonnet 4.6
LMArena Vision12831257Claude Sonnet 4.6
LMArena Text: English14721441Claude Sonnet 4.6
LMArena Text: non-English14401417Claude Sonnet 4.6
LMArena Text: Chinese14911470Claude Sonnet 4.6
LMArena Text: German14281455GPT-5.6 Luna
LMArena Text: Japanese14201415Claude Sonnet 4.6
LMArena Text: Korean14101415GPT-5.6 Luna
LMArena Text: French14651458Claude Sonnet 4.6
LMArena Text: Spanish14641446Claude Sonnet 4.6
LMArena Text: Russian14401427Claude Sonnet 4.6
LMArena Text: Polish14431405Claude Sonnet 4.6
LMArena Text: multi-turn14641434Claude Sonnet 4.6
LMArena Text: longer queries14791436Claude Sonnet 4.6
LMArena Text: writing and language14441419Claude Sonnet 4.6
LMArena Text: entertainment and media14311402Claude Sonnet 4.6
LMArena Vision: English12981263Claude Sonnet 4.6
LMArena Vision: Chinese13071294Claude Sonnet 4.6
LMArena Vision: reading text12961264Claude Sonnet 4.6
LMArena Vision: humor12481190Claude Sonnet 4.6
LMArena Vision: recognizing things1195Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: creative writing12721257Claude Sonnet 4.6
LMArena Document14821457Claude Sonnet 4.6
Neither model has a result on the other 9 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-5.6 Luna
BenchmarkClaude Sonnet 4.6GPT-5.6 LunaLeader
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-5.6 Luna$0.0008Fits in one request

GPT-5.6 Luna costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
GPT-5.6 Luna$0.014Fits in one request

GPT-5.6 Luna costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
GPT-5.6 Luna$0.052Fits in one request

GPT-5.6 Luna 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-5.6 Luna
SpecificationAnthropic Claude Sonnet 4.6OpenAI GPT-5.6 Luna
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 17, 2026July 9, 2026
Context window1M1.05M
Input $/Mtok$3.00$0.20
Output $/Mtok$15.00$1.20
Coding index57.358.0
Independent measurements behind it56
Cost per solved task$1.68$0.04
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.6 better than GPT-5.6 Luna for coding?

Claude Sonnet 4.6 and GPT-5.6 Luna are level for coding, 57.3 against 58.0 on the Vibe Coding Index, so price and context decide. Pick Claude Sonnet 4.6 for work measured by LMArena WebDev or ProgramBench (Vals AI), where it leads. Pick GPT-5.6 Luna for output tokens 12.5x cheaper ($1.20 vs $15.00 per million) and a lower cost per solved task ($0.04 against $1.68).

Which is cheaper, Claude Sonnet 4.6 or GPT-5.6 Luna?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and GPT-5.6 Luna $0.04.

Which has the bigger context window, Claude Sonnet 4.6 or GPT-5.6 Luna?

GPT-5.6 Luna, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.6 vs GPT-5.6 Luna comparison based on?

99 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-5.6 Luna's on 6. 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-5-6-luna" title="Claude Sonnet 4.6 vs GPT-5.6 Luna, 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-5-6-luna">LLMBenchmark.ai, Claude Sonnet 4.6 vs GPT-5.6 Luna</a></p>