LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 5 vs GPT-5.6 Luna

Updated October 21, 2026. 109 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 5 Replace GPT-5.6 Luna
Claude Sonnet 5Anthropic
Coding
63.5
Overall
38.2
Output $/M
$10.00
75
GPT-5.6 LunaOpenAI
Coding
61.5
Overall
37.3
Output $/M
$1.20
31
vs boards won of 109 shared, 3 tied

Decision reading

Pick Claude Sonnet 5 for coding: it scores 63.5 on the Vibe Coding Index against 61.5 for GPT-5.6 Luna.

Pick GPT-5.6 Luna when output tokens cost 8.3x less, or when a solved task costs $0.04 against $1.87.

Model AClaude Sonnet 5Anthropic63.5/1002 independent benchmarks$1.87 per solved taskModel BGPT-5.6 LunaOpenAI61.5/1002 independent benchmarks$0.04 per solved task
Shared results
109
Claude Sonnet 5 only
11
GPT-5.6 Luna only
7
Like-for-like categories
8 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 5 63.5 from 2 benchmarks, GPT-5.6 Luna 61.5 from 2 benchmarks.
Widest category
Math, 12.0 points apart on average over 6 shared benchmarks.
Widest single gap
LiveBench research: Claude Sonnet 5 82.8% against GPT-5.6 Luna 51.0%, 31.8 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5 $10.00 against GPT-5.6 Luna $1.20 per million output tokens, 8.3x apart.
Context window
Claude Sonnet 5 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 5BarsGPT-5.6 LunaTies
Coding1291 tie
Intelligence20
Agentic work93
Reasoning1031 tie
Math33
Knowledge74
Web design801 tie
General249
All shared boards75313 ties
CodingLike-for-likeFour of these boards feed the Vibe Coding Index129
Coding benchmarks for Claude Sonnet 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-5.6 LunaLeader
LiveBench coding74.7%73.6%Claude Sonnet 5
LMArena WebDev15401518Claude Sonnet 5
AA Coding Index71.571.4Claude Sonnet 5
LiveCodeBench (Vals AI)82.4%Not measuredOnly Claude Sonnet 5 measured
SWE-bench Verified (Vals AI)79.6%93.0%GPT-5.6 Luna
Terminal-Bench 4 (Vals AI)10.6%11.6%GPT-5.6 Luna
Vibe Code Bench (Vals AI)81.3%77.1%Claude Sonnet 5
Code migration (Vals AI)44.4%44.5%GPT-5.6 Luna
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)45.0%61.8%GPT-5.6 Luna
Terminal-Bench 2.1 (Vals AI)74.5%79.0%GPT-5.6 Luna
Vibe Code Bench 1-100 (Vals AI)13.8%22.6%GPT-5.6 Luna
SkillsBench (Vals AI)46.5%60.5%GPT-5.6 Luna
CyberBench (Vals AI)70.3%73.6%GPT-5.6 Luna
SciCode54.3%53.6%Claude Sonnet 5
FrontierCode42.7%39.8%Claude Sonnet 5
GSO-Bench37.3%Not measuredOnly Claude Sonnet 5 measured
WeirdML68.8%60.9%Claude Sonnet 5
ALE-Bench1463.11667.4GPT-5.6 Luna
LMArena Text: coding14831466Claude Sonnet 5
LMArena Text: software and IT14741463Claude Sonnet 5
LMArena WebDev: React15411508Claude Sonnet 5
LMArena WebDev: HTML15271520Claude Sonnet 5
LMArena WebDev: from an image15401517Claude Sonnet 5
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-5.6 LunaLeader
AA Intelligence Index38.237.3Claude Sonnet 5
Epoch Capabilities Index156.9156.5Claude Sonnet 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index93
Agentic work benchmarks for Claude Sonnet 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-5.6 LunaLeader
AA Agentic Index43.642.1Claude Sonnet 5
Design Arena: agents building web apps1245Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building full-stack apps1249Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building mobile apps1215Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building Android apps1231Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building Godot games1225Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building games1227Not measuredOnly Claude Sonnet 5 measured
Design Arena: HTML slides1218Not measuredOnly Claude Sonnet 5 measured
Design Arena: PowerPoint slides1216Not measuredOnly Claude Sonnet 5 measured
Design Arena: spreadsheets1004Not measuredOnly Claude Sonnet 5 measured
LiveBench research82.8%51.0%Claude Sonnet 5
LiveBench browser72.0%68.0%Claude Sonnet 5
LiveBench long agentic39.0%30.4%Claude Sonnet 5
SREBench (Vals AI)0.4%1.5%GPT-5.6 Luna
Finance Agent (Vals AI)53.9%55.0%GPT-5.6 Luna
Tax Agent Bench (Vals AI)29.4%24.8%Claude Sonnet 5
Legal Research Bench (Vals AI)41.8%36.5%Claude Sonnet 5
Excel Modeling Benchmark (Vals AI)66.3%67.1%GPT-5.6 Luna
BioMysteryBench (Vals AI)Not measured61.5%Only GPT-5.6 Luna measured
Terminal-Bench-Science (Vals AI)5.7%0.0%Claude Sonnet 5
Vals Science IndexNot measured25.3%Only GPT-5.6 Luna measured
APEX-Agents54.5%43.0%Claude Sonnet 5
BALROGNot measured45.6%Only GPT-5.6 Luna measured
Vending-Bench 2$6,378$4,095Claude Sonnet 5
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index103
Reasoning benchmarks for Claude Sonnet 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-5.6 LunaLeader
GPQA Diamond88.9%91.7%GPT-5.6 Luna
LiveBench reasoning88.7%85.6%Claude Sonnet 5
MysteryMechanism (Vals AI)Not measured14.4%Only GPT-5.6 Luna measured
MMMU Pro (Vals AI)83.0%85.0%GPT-5.6 Luna
GPQA Diamond (Artificial Analysis run)91.1%91.1%Tie
Humanity's Last Exam (Artificial Analysis run)41.3%39.5%Claude Sonnet 5
GPQA Diamond (Epoch AI run)90.5%91.6%GPT-5.6 Luna
ARC-AGINot measured88.0%Only GPT-5.6 Luna measured
ARC-AGI-2Not measured59.5%Only GPT-5.6 Luna measured
SimpleBench60.6%46.8%Claude Sonnet 5
Chess puzzles45.0%43.0%Claude Sonnet 5
Mystery game puzzles35.0%21.0%Claude Sonnet 5
LMArena Text: hard prompts14611451Claude Sonnet 5
LMArena Text: expert14891478Claude Sonnet 5
LMArena Text: hard prompts in English14641460Claude Sonnet 5
LMArena Vision: diagrams12931273Claude Sonnet 5
LMArena Vision: homework13111282Claude Sonnet 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for Claude Sonnet 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-5.6 LunaLeader
OTIS Mock AIME94.7%98.3%GPT-5.6 Luna
FrontierMath, tiers 1 to 365.6%82.1%GPT-5.6 Luna
FrontierMath, tier 429.3%61.0%GPT-5.6 Luna
ProofBench77.0%60.0%Claude Sonnet 5
LMArena Text: math14671459Claude Sonnet 5
LMArena Text: mathematical work14811470Claude Sonnet 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index74
Knowledge benchmarks for Claude Sonnet 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-5.6 LunaLeader
MMLU Pro87.5%86.0%Claude Sonnet 5
LegalBench (Vals AI)83.9%84.0%GPT-5.6 Luna
CorpFin (Vals AI)67.0%64.2%Claude Sonnet 5
TaxEval (Vals AI)75.6%76.2%GPT-5.6 Luna
MortgageTax (Vals AI)70.0%67.3%Claude Sonnet 5
MedCode (Vals AI)47.5%42.4%Claude Sonnet 5
SimpleQA Verified33.7%41.0%GPT-5.6 Luna
LMArena Text: science14601433Claude Sonnet 5
LMArena Text: medicine and healthcare14421399Claude Sonnet 5
LMArena Text: legal and government14541446Claude Sonnet 5
LMArena Text: business and finance14361439GPT-5.6 Luna
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Sonnet 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-5.6 LunaLeader
Design Arena: websites12741256Claude Sonnet 5
Design Arena: UI components12791250Claude Sonnet 5
Design Arena: game dev12781196Claude Sonnet 5
Design Arena: data viz12511212Claude Sonnet 5
Design Arena: 3D12611121Claude Sonnet 5
Design Arena: all code categories12761231Claude Sonnet 5
Design Arena: SVG11931193Tie
Design Arena: ASCII art12071144Claude Sonnet 5
LiveBench design82.0%76.0%Claude Sonnet 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index249
General benchmarks for Claude Sonnet 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-5.6 LunaLeader
LiveBench data analysis71.7%78.0%GPT-5.6 Luna
Public Benefits Bench (Vals AI)66.0%61.2%Claude Sonnet 5
SAGE (Vals AI)48.9%44.2%Claude Sonnet 5
MedScribe (Vals AI)76.0%84.4%GPT-5.6 Luna
Vals Multimodal Index68.8%69.1%GPT-5.6 Luna
Long context reasoning (AA-LCR)82.0%83.7%GPT-5.6 Luna
DTBench92.5%89.1%Claude Sonnet 5
LMCA50.0%48.5%Claude Sonnet 5
Surface Evolver Bench60.0%61.9%GPT-5.6 Luna
Furniture assemblyNot measured42.5%Only GPT-5.6 Luna measured
LMArena Text14421431Claude Sonnet 5
LMArena Text: instruction following14521437Claude Sonnet 5
LMArena Text: creative writing14161396Claude Sonnet 5
LMArena Vision12731257Claude Sonnet 5
LMArena Text: English14501441Claude Sonnet 5
LMArena Text: non-English14311417Claude Sonnet 5
LMArena Text: Chinese14781470Claude Sonnet 5
LMArena Text: German14421455GPT-5.6 Luna
LMArena Text: Japanese14221415Claude Sonnet 5
LMArena Text: Korean14121415GPT-5.6 Luna
LMArena Text: French14631458Claude Sonnet 5
LMArena Text: Spanish14381446GPT-5.6 Luna
LMArena Text: Russian14501427Claude Sonnet 5
LMArena Text: Polish14251405Claude Sonnet 5
LMArena Text: multi-turn14531434Claude Sonnet 5
LMArena Text: longer queries14621436Claude Sonnet 5
LMArena Text: writing and language14361419Claude Sonnet 5
LMArena Text: entertainment and media14111402Claude Sonnet 5
LMArena Vision: English12751263Claude Sonnet 5
LMArena Vision: Chinese13311294Claude Sonnet 5
LMArena Vision: reading text12881264Claude Sonnet 5
LMArena Vision: humor12611190Claude Sonnet 5
LMArena Vision: creative writing12461257GPT-5.6 Luna
LMArena Document14661457Claude Sonnet 5
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 5 and GPT-5.6 Luna
BenchmarkClaude Sonnet 5GPT-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 5$0.0070Fits 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 5$0.130Fits 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 5$0.500Fits 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 5 and GPT-5.6 Luna
SpecificationAnthropic Claude Sonnet 5OpenAI GPT-5.6 Luna
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJune 30, 2026July 9, 2026
Context window1M1.05M
Input $/Mtok$2.00$0.20
Output $/Mtok$10.00$1.20
Coding index63.561.5
Independent measurements behind it22
Cost per solved task$1.87$0.04
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5 better than GPT-5.6 Luna for coding?

Pick Claude Sonnet 5 for coding: it scores 63.5 on the Vibe Coding Index against 61.5 for GPT-5.6 Luna. Pick GPT-5.6 Luna when output tokens cost 8.3x less, or when a solved task costs $0.04 against $1.87.

Which is cheaper, Claude Sonnet 5 or GPT-5.6 Luna?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. Per solved SWE-bench Verified task, Claude Sonnet 5 costs $1.87 and GPT-5.6 Luna $0.04.

Which has the bigger context window, Claude Sonnet 5 or GPT-5.6 Luna?

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

How many benchmarks is the Claude Sonnet 5 vs GPT-5.6 Luna comparison based on?

109 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5's coding index rests on 2 independent benchmarks and GPT-5.6 Luna'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-5-vs-gpt-5-6-luna" title="Claude Sonnet 5 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-5-vs-gpt-5-6-luna">LLMBenchmark.ai, Claude Sonnet 5 vs GPT-5.6 Luna</a></p>