LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs GPT-6 Luna

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-6 Luna
Claude Sonnet 4.6Anthropic
Coding
57.8
Overall
30.1
Output $/M
$15.00
53
GPT-6 LunaOpenAI
Coding
71.4
Overall
38.1
Output $/M
$0.50
29
vs boards won of 84 shared, 2 tied

Decision reading

Pick GPT-6 Luna for coding: it scores 71.4 on the Vibe Coding Index against 57.8 for Claude Sonnet 4.6.

Pick Claude Sonnet 4.6 when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AClaude Sonnet 4.6Anthropic57.8/1002 independent benchmarks$1.68 per solved taskModel BGPT-6 LunaOpenAI71.4/1002 independent benchmarksNo cost per solved task
Shared results
84
Claude Sonnet 4.6 only
33
GPT-6 Luna only
18
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 4.6 57.8 from 2 benchmarks, GPT-6 Luna 71.4 from 2 benchmarks.
Widest category
Math, 12.6 points apart on average over 4 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Sonnet 4.6 55.8% against GPT-6 Luna 81.7%, 25.9 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against GPT-6 Luna $0.50 per million output tokens, 30.0x apart.
Context window
Claude Sonnet 4.6 takes 1M tokens, GPT-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-6 LunaTies
Coding2101 tie
Intelligence02
Agentic work74
Reasoning84
Math22
Knowledge41
Web design531 tie
General253
All shared boards53292 ties
CodingLike-for-likeFour of these boards feed the Vibe Coding Index210
Coding benchmarks for Claude Sonnet 4.6 and GPT-6 Luna
BenchmarkClaude Sonnet 4.6GPT-6 LunaLeader
LiveBench coding66.6%84.5%GPT-6 Luna
LMArena WebDev15231578GPT-6 Luna
AA Coding Index63.0Not measuredOnly Claude Sonnet 4.6 measured
LiveCodeBench (Vals AI)82.1%Not measuredOnly Claude Sonnet 4.6 measured
SWE-bench Verified (Vals AI)77.4%Not measuredOnly Claude Sonnet 4.6 measured
Terminal-Bench 4 (Vals AI)Not measured13.6%Only GPT-6 Luna measured
Vibe Code Bench (Vals AI)55.8%81.7%GPT-6 Luna
Code migration (Vals AI)39.9%42.5%GPT-6 Luna
ProgramBench (Vals AI)0.5%0.5%Tie
IOI (Vals AI)Not measured55.6%Only GPT-6 Luna measured
Terminal-Bench 2.1 (Vals AI)57.3%73.0%GPT-6 Luna
SWE-bench Multimodal (Vals AI)Not measured37.5%Only GPT-6 Luna measured
SkillsBench (Vals AI)49.0%Not measuredOnly Claude Sonnet 4.6 measured
CyberBench (Vals AI)Not measured76.3%Only GPT-6 Luna measured
SciCode50.1%54.6%GPT-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%42.4%GPT-6 Luna
WeirdML66.1%Not measuredOnly Claude Sonnet 4.6 measured
ALE-BenchNot measured1576.9Only GPT-6 Luna measured
LMArena Text: coding15031437Claude Sonnet 4.6
LMArena Text: software and IT14911423Claude Sonnet 4.6
LMArena WebDev: React15121573GPT-6 Luna
LMArena WebDev: HTML15271595GPT-6 Luna
LMArena WebDev: from an image15291571GPT-6 Luna
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-6 Luna
BenchmarkClaude Sonnet 4.6GPT-6 LunaLeader
AA Intelligence Index30.138.1GPT-6 Luna
Epoch Capabilities Index152.8156.8GPT-6 Luna
Agentic workLike-for-likePublic boards, shown as published, kept out of the index74
Agentic work benchmarks for Claude Sonnet 4.6 and GPT-6 Luna
BenchmarkClaude Sonnet 4.6GPT-6 LunaLeader
AA Agentic Index31.8Not measuredOnly Claude Sonnet 4.6 measured
Design Arena: agents building web apps11901189Claude Sonnet 4.6
Design Arena: agents building full-stack apps12131158Claude Sonnet 4.6
Design Arena: agents building mobile apps12121133Claude Sonnet 4.6
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%43.5%Claude Sonnet 4.6
LiveBench browser68.0%72.0%GPT-6 Luna
LiveBench long agentic23.1%48.1%GPT-6 Luna
SREBench (Vals AI)Not measured2.7%Only GPT-6 Luna measured
Finance Agent (Vals AI)51.0%49.9%Claude Sonnet 4.6
Tax Agent Bench (Vals AI)25.8%19.9%Claude Sonnet 4.6
Legal Research Bench (Vals AI)38.5%30.3%Claude Sonnet 4.6
Harvey's Legal Agent Benchmark (Vals AI)Not measured4.2%Only GPT-6 Luna measured
Excel Modeling Benchmark (Vals AI)60.2%68.5%GPT-6 Luna
BioMysteryBench (Vals AI)Not measured61.5%Only GPT-6 Luna measured
Terminal-Bench-Science (Vals AI)Not measured4.3%Only GPT-6 Luna measured
Vals Science IndexNot measured28.4%Only GPT-6 Luna measured
τ²-Bench Telecom79.5%Not measuredOnly Claude Sonnet 4.6 measured
APEX-Agents43.0%44.3%GPT-6 Luna
OSWorld 2.09.3%Not measuredOnly Claude Sonnet 4.6 measured
DeepResearch Bench54.9%Not measuredOnly Claude Sonnet 4.6 measured
OSWorld72.1%Not measuredOnly Claude Sonnet 4.6 measured
SpireClimbNot measured0.0%Only GPT-6 Luna measured
Vending-Bench 2$7,204Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 13 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index84
Reasoning benchmarks for Claude Sonnet 4.6 and GPT-6 Luna
BenchmarkClaude Sonnet 4.6GPT-6 LunaLeader
GPQA Diamond85.6%Not measuredOnly Claude Sonnet 4.6 measured
LiveBench reasoning86.4%81.8%Claude Sonnet 4.6
MysteryMechanism (Vals AI)Not measured19.4%Only GPT-6 Luna measured
MMMU Pro (Vals AI)83.6%Not measuredOnly Claude Sonnet 4.6 measured
GPQA Diamond (Artificial Analysis run)87.5%Not measuredOnly Claude Sonnet 4.6 measured
Humanity's Last Exam (Artificial Analysis run)33.6%38.5%GPT-6 Luna
GPQA Diamond (Epoch AI run)87.4%90.5%GPT-6 Luna
ARC-AGI86.5%86.7%GPT-6 Luna
ARC-AGI-260.4%59.3%Claude Sonnet 4.6
Chess puzzles23.0%36.0%GPT-6 Luna
Mystery game puzzles16.0%7.0%Claude Sonnet 4.6
LMArena Text: hard prompts14851410Claude Sonnet 4.6
LMArena Text: expert15001442Claude Sonnet 4.6
LMArena Text: hard prompts in English14931410Claude Sonnet 4.6
LMArena Vision: diagrams13061245Claude Sonnet 4.6
LMArena Vision: homework13111261Claude Sonnet 4.6
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for Claude Sonnet 4.6 and GPT-6 Luna
BenchmarkClaude Sonnet 4.6GPT-6 LunaLeader
AIME92.3%Not measuredOnly Claude Sonnet 4.6 measured
OTIS Mock AIME85.8%98.9%GPT-6 Luna
FrontierMath, tiers 1 to 3Not measured78.9%Only GPT-6 Luna measured
FrontierMath, tier 4Not measured56.1%Only GPT-6 Luna measured
ProofBench45.0%64.0%GPT-6 Luna
LMArena Text: math14621409Claude Sonnet 4.6
LMArena Text: mathematical work14831427Claude 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 index41
Knowledge benchmarks for Claude Sonnet 4.6 and GPT-6 Luna
BenchmarkClaude Sonnet 4.6GPT-6 LunaLeader
MMLU Pro87.3%Not measuredOnly Claude Sonnet 4.6 measured
LegalBench (Vals AI)82.1%Not measuredOnly Claude Sonnet 4.6 measured
CaseLaw (Vals AI)64.0%Not measuredOnly Claude Sonnet 4.6 measured
CorpFin (Vals AI)65.3%Not measuredOnly Claude Sonnet 4.6 measured
TaxEval (Vals AI)77.1%Not measuredOnly Claude Sonnet 4.6 measured
MortgageTax (Vals AI)67.7%Not measuredOnly Claude Sonnet 4.6 measured
MedQA (Vals AI)92.1%Not measuredOnly Claude Sonnet 4.6 measured
MedCode (Vals AI)Not measured44.7%Only GPT-6 Luna measured
SimpleQA Verified35.5%41.4%GPT-6 Luna
LMArena Text: science14741386Claude Sonnet 4.6
LMArena Text: medicine and healthcare14511352Claude Sonnet 4.6
LMArena Text: legal and government14701400Claude Sonnet 4.6
LMArena Text: business and finance14641388Claude 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 index53
Web design benchmarks for Claude Sonnet 4.6 and GPT-6 Luna
BenchmarkClaude Sonnet 4.6GPT-6 LunaLeader
Design Arena: websites12851272Claude Sonnet 4.6
Design Arena: UI components12711297GPT-6 Luna
Design Arena: game dev12591259Tie
Design Arena: data viz12781215Claude Sonnet 4.6
Design Arena: 3D12341217Claude Sonnet 4.6
Design Arena: all code categories12761271Claude Sonnet 4.6
Design Arena: SVG11961253GPT-6 Luna
Design Arena: ASCII art12351156Claude Sonnet 4.6
LiveBench design71.8%82.5%GPT-6 Luna
GeneralLike-for-likePublic boards, shown as published, kept out of the index253
General benchmarks for Claude Sonnet 4.6 and GPT-6 Luna
BenchmarkClaude Sonnet 4.6GPT-6 LunaLeader
Vals IndexNot measured52.3%Only GPT-6 Luna measured
LiveBench data analysis76.1%73.4%Claude Sonnet 4.6
Public Benefits Bench (Vals AI)62.5%57.6%Claude Sonnet 4.6
SAGE (Vals AI)46.6%48.1%GPT-6 Luna
MedScribe (Vals AI)Not measured83.7%Only GPT-6 Luna measured
Vals Multimodal Index60.6%Not measuredOnly Claude Sonnet 4.6 measured
IFBench56.6%Not measuredOnly Claude Sonnet 4.6 measured
Long context reasoning (AA-LCR)80.0%83.3%GPT-6 Luna
DTBench89.9%90.1%GPT-6 Luna
LMCA46.5%44.5%Claude Sonnet 4.6
Furniture assemblyNot measured44.2%Only GPT-6 Luna measured
ExploitBench23.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text14581389Claude Sonnet 4.6
LMArena Text: instruction following14761408Claude Sonnet 4.6
LMArena Text: creative writing14351363Claude Sonnet 4.6
LMArena Vision12831216Claude Sonnet 4.6
LMArena Text: English14721393Claude Sonnet 4.6
LMArena Text: non-English14401381Claude Sonnet 4.6
LMArena Text: Chinese14911427Claude Sonnet 4.6
LMArena Text: German14281376Claude Sonnet 4.6
LMArena Text: Japanese14201369Claude Sonnet 4.6
LMArena Text: Korean14101359Claude Sonnet 4.6
LMArena Text: French14651408Claude Sonnet 4.6
LMArena Text: Spanish14641391Claude Sonnet 4.6
LMArena Text: Russian14401392Claude Sonnet 4.6
LMArena Text: Polish14431383Claude Sonnet 4.6
LMArena Text: multi-turn14641392Claude Sonnet 4.6
LMArena Text: longer queries14791408Claude Sonnet 4.6
LMArena Text: writing and language14441384Claude Sonnet 4.6
LMArena Text: entertainment and media14311364Claude Sonnet 4.6
LMArena Vision: English12981204Claude Sonnet 4.6
LMArena Vision: Chinese13071266Claude Sonnet 4.6
LMArena Vision: reading text12961225Claude Sonnet 4.6
LMArena Vision: humor1248Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: recognizing things1195Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: creative writing12721205Claude Sonnet 4.6
LMArena Document1482Not measuredOnly Claude Sonnet 4.6 measured
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-6 Luna
BenchmarkClaude Sonnet 4.6GPT-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-6 Luna$0.0003Fits in one request

GPT-6 Luna costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
GPT-6 Luna$0.0065Fits in one request

GPT-6 Luna costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
GPT-6 Luna$0.025Fits in one request

GPT-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-6 Luna
SpecificationAnthropic Claude Sonnet 4.6OpenAI GPT-6 Luna
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 17, 2026September 22, 2026
Context window1M1.05M
Input $/Mtok$3.00$0.10
Output $/Mtok$15.00$0.50
Coding index57.871.4
Independent measurements behind it22
Cost per solved task$1.68Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.6 better than GPT-6 Luna for coding?

Pick GPT-6 Luna for coding: it scores 71.4 on the Vibe Coding Index against 57.8 for Claude Sonnet 4.6. Pick Claude Sonnet 4.6 when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Claude Sonnet 4.6 or GPT-6 Luna?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for Claude Sonnet 4.6 only.

Which has the bigger context window, Claude Sonnet 4.6 or GPT-6 Luna?

GPT-6 Luna, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.6 vs GPT-6 Luna 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-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-4-6-vs-gpt-6-luna" title="Claude Sonnet 4.6 vs GPT-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-6-luna">LLMBenchmark.ai, Claude Sonnet 4.6 vs GPT-6 Luna</a></p>