Enter opens the highlighted result. Esc closes.

Claude Opus 5 vs GPT-6 Luna

Claude Opus 5 leads GPT-6 Luna on coding, 83.0 to 57.3 on the Vibe Coding Index, and GPT-6 Luna costs 50.0x less per output token ($0.50 vs $25.00 per million). Updated October 21, 2026; 98 benchmarks have a result for both.

Replace Claude Opus 5 Replace GPT-6 Luna
Claude Opus 5Anthropic
Coding
83.0
Overall
81.6
Output $/M
$25.00
95
GPT-6 LunaOpenAI
Coding
57.3
Overall
59.7
Output $/M
$0.50
2
vs boards won of 98 shared, 1 tied

Claude Opus 5 or GPT-6 Luna: which to pick

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 57.3 for GPT-6 Luna.

Pick GPT-6 Luna for output tokens 50.0x cheaper ($0.50 vs $25.00 per million) and a larger context window (1.05M against 1M tokens).

Model AClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved taskModel BGPT-6 LunaOpenAI57.3/1005 independent benchmarksNo cost per solved task
Shared results
98
Claude Opus 5 only
33
GPT-6 Luna only
5
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 Opus 5 83.0 from 6 benchmarks, GPT-6 Luna 57.3 from 5 benchmarks.
Widest category
Knowledge, 21.8 points apart on average over 6 shared benchmarks.
Widest single gap
Terminal-Bench 4 (Vals AI): Claude Opus 5 53.5% against GPT-6 Luna 13.6%, 53.2 points apart on a 0 to 100 scale.
Output price
Claude Opus 5 $25.00 against GPT-6 Luna $0.50 per million output tokens, 50.0x apart.
Context window
Claude Opus 5 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 Opus 5BarsGPT-6 LunaTies
Coding161
Intelligence20
Agentic work150
Reasoning130
Math501 tie
Knowledge60
Web design90
General291
All shared boards9521 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index161
Coding benchmarks for Claude Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-6 LunaLeader
LiveBench coding90.8%84.5%Claude Opus 5
LMArena WebDev16891578Claude Opus 5
AA Coding Index78.0Not measuredOnly Claude Opus 5 measured
LiveCodeBench (Vals AI)89.0%Not measuredOnly Claude Opus 5 measured
SWE-bench Verified (Vals AI)97.0%Not measuredOnly Claude Opus 5 measured
Terminal-Bench 4 (Vals AI)53.5%13.6%Claude Opus 5
Vibe Code Bench (Vals AI)88.4%81.7%Claude Opus 5
Code migration (Vals AI)57.5%42.5%Claude Opus 5
ProgramBench (Vals AI)3.0%0.5%Claude Opus 5
IOI (Vals AI)84.3%55.6%Claude Opus 5
Terminal-Bench 2.1 (Vals AI)84.6%73.0%Claude Opus 5
SWE-bench Multimodal (Vals AI)Not measured37.5%Only GPT-6 Luna measured
Vibe Code Bench 1-100 (Vals AI)28.5%Not measuredOnly Claude Opus 5 measured
SkillsBench (Vals AI)60.4%Not measuredOnly Claude Opus 5 measured
CyberBench (Vals AI)65.4%76.3%GPT-6 Luna
SciCode56.4%54.6%Claude Opus 5
FrontierCode53.4%42.4%Claude Opus 5
FrontierSWE52.0%Not measuredOnly Claude Opus 5 measured
WeirdML91.8%Not measuredOnly Claude Opus 5 measured
ALE-Bench2164.61576.9Claude Opus 5
LMArena Text: coding15331437Claude Opus 5
LMArena Text: software and IT15271423Claude Opus 5
LMArena WebDev: React17111573Claude Opus 5
LMArena WebDev: HTML16801595Claude Opus 5
LMArena WebDev: from an image16621571Claude Opus 5
SciCode13.8%Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-6 LunaLeader
AA Intelligence Index50.838.1Claude Opus 5
Epoch Capabilities Index163.9156.8Claude Opus 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index150
Agentic work benchmarks for Claude Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-6 LunaLeader
AA Agentic Index56.5Not measuredOnly Claude Opus 5 measured
Design Arena: agents building web apps12661191Claude Opus 5
Design Arena: agents building full-stack apps13061158Claude Opus 5
Design Arena: agents building mobile apps13481128Claude Opus 5
Design Arena: agents building Android apps1254Not measuredOnly Claude Opus 5 measured
Design Arena: agents building Godot games1279Not measuredOnly Claude Opus 5 measured
Design Arena: agents building games1261Not measuredOnly Claude Opus 5 measured
Design Arena: PowerPoint slides1265Not measuredOnly Claude Opus 5 measured
LiveBench research88.9%43.5%Claude Opus 5
LiveBench browser84.0%72.0%Claude Opus 5
LiveBench long agentic62.1%48.1%Claude Opus 5
SREBench (Vals AI)12.2%2.7%Claude Opus 5
Finance Agent (Vals AI)58.6%49.9%Claude Opus 5
Tax Agent Bench (Vals AI)45.5%19.9%Claude Opus 5
Legal Research Bench (Vals AI)55.3%30.3%Claude Opus 5
Harvey's Legal Agent Benchmark (Vals AI)Not measured4.2%Only GPT-6 Luna measured
Excel Modeling Benchmark (Vals AI)73.6%68.5%Claude Opus 5
BioMysteryBench (Vals AI)79.3%61.5%Claude Opus 5
Terminal-Bench-Science (Vals AI)27.1%4.3%Claude Opus 5
Vals Science Index47.9%28.4%Claude Opus 5
Time Horizon Index (Vals AI)18.8%Not measuredOnly Claude Opus 5 measured
CUA-bench (Vals AI)9.0%Not measuredOnly Claude Opus 5 measured
APEX-Agents65.8%44.3%Claude Opus 5
OSWorld 2.031.4%Not measuredOnly Claude Opus 5 measured
BALROG63.4%Not measuredOnly Claude Opus 5 measured
PostTrainBench35.0%Not measuredOnly Claude Opus 5 measured
SpireClimbNot measured0.0%Only GPT-6 Luna measured
Vending-Bench 2$11,182Not measuredOnly Claude Opus 5 measured
LMArena Search1242Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index130
Reasoning benchmarks for Claude Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-6 LunaLeader
GPQA Diamond93.4%Not measuredOnly Claude Opus 5 measured
LiveBench reasoning91.2%81.8%Claude Opus 5
MysteryMechanism (Vals AI)37.4%19.4%Claude Opus 5
MMMU Pro (Vals AI)89.9%Not measuredOnly Claude Opus 5 measured
GPQA Diamond (Artificial Analysis run)93.7%Not measuredOnly Claude Opus 5 measured
Humanity's Last Exam (Artificial Analysis run)54.9%38.5%Claude Opus 5
GPQA Diamond (Epoch AI run)93.9%90.5%Claude Opus 5
ARC-AGI97.5%86.7%Claude Opus 5
ARC-AGI-290.4%59.3%Claude Opus 5
SimpleBench80.6%Not measuredOnly Claude Opus 5 measured
Chess puzzles43.0%36.0%Claude Opus 5
Mystery game puzzles59.0%7.0%Claude Opus 5
EBR-bench45.7%Not measuredOnly Claude Opus 5 measured
LMArena Text: hard prompts15271410Claude Opus 5
LMArena Text: expert15541442Claude Opus 5
LMArena Text: hard prompts in English15231410Claude Opus 5
LMArena Vision: diagrams13481245Claude Opus 5
LMArena Vision: homework13381261Claude Opus 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for Claude Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-6 LunaLeader
OTIS Mock AIME98.9%98.9%Tie
FrontierMath, tiers 1 to 385.6%78.9%Claude Opus 5
FrontierMath, tier 473.2%56.1%Claude Opus 5
ProofBench99.0%64.0%Claude Opus 5
LMArena Text: math15331409Claude Opus 5
LMArena Text: mathematical work15441427Claude Opus 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Claude Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-6 LunaLeader
MMLU Pro91.6%Not measuredOnly Claude Opus 5 measured
LegalBench (Vals AI)87.0%Not measuredOnly Claude Opus 5 measured
CorpFin (Vals AI)73.2%Not measuredOnly Claude Opus 5 measured
TaxEval (Vals AI)75.1%Not measuredOnly Claude Opus 5 measured
MortgageTax (Vals AI)72.1%Not measuredOnly Claude Opus 5 measured
MedCode (Vals AI)63.6%44.7%Claude Opus 5
SimpleQA Verified59.9%41.4%Claude Opus 5
LMArena Text: science15311386Claude Opus 5
LMArena Text: medicine and healthcare15251352Claude Opus 5
LMArena Text: legal and government15301400Claude Opus 5
LMArena Text: business and finance15011388Claude Opus 5
FACTS Benchmark SuiteNot measured63.3%Only GPT-6 Luna measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for Claude Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-6 LunaLeader
Design Arena: websites13091272Claude Opus 5
Design Arena: UI components13491297Claude Opus 5
Design Arena: game dev13381260Claude Opus 5
Design Arena: data viz13291215Claude Opus 5
Design Arena: 3D13351217Claude Opus 5
Design Arena: all code categories13241271Claude Opus 5
Design Arena: SVG13111251Claude Opus 5
Design Arena: ASCII art13521153Claude Opus 5
LiveBench design83.0%82.5%Claude Opus 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index291
General benchmarks for Claude Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-6 LunaLeader
Vals IndexNot measured52.3%Only GPT-6 Luna measured
LiveBench data analysis74.6%73.4%Claude Opus 5
Public Benefits Bench (Vals AI)76.9%57.6%Claude Opus 5
SAGE (Vals AI)49.4%48.1%Claude Opus 5
MedScribe (Vals AI)91.0%83.7%Claude Opus 5
Vals Multimodal Index73.9%Not measuredOnly Claude Opus 5 measured
Long context reasoning (AA-LCR)82.0%83.3%GPT-6 Luna
DTBench97.9%90.1%Claude Opus 5
LMCA64.5%44.5%Claude Opus 5
Furniture assembly60.8%44.2%Claude Opus 5
LMArena Text15091389Claude Opus 5
LMArena Text: instruction following15181408Claude Opus 5
LMArena Text: creative writing14931363Claude Opus 5
LMArena Vision13201216Claude Opus 5
LMArena Text: English15081393Claude Opus 5
LMArena Text: non-English15021381Claude Opus 5
LMArena Text: Chinese15731427Claude Opus 5
LMArena Text: German15271376Claude Opus 5
LMArena Text: Japanese15201369Claude Opus 5
LMArena Text: Korean15171359Claude Opus 5
LMArena Text: French15191408Claude Opus 5
LMArena Text: Spanish15231391Claude Opus 5
LMArena Text: Russian15071392Claude Opus 5
LMArena Text: Polish15221383Claude Opus 5
LMArena Text: multi-turn15001392Claude Opus 5
LMArena Text: longer queries15171408Claude Opus 5
LMArena Text: writing and language14991384Claude Opus 5
LMArena Text: entertainment and media14811364Claude Opus 5
LMArena Vision: English13151204Claude Opus 5
LMArena Vision: Chinese14001266Claude Opus 5
LMArena Vision: reading text13291225Claude Opus 5
LMArena Vision: humor1293Not measuredOnly Claude Opus 5 measured
LMArena Vision: creative writing13131205Claude Opus 5
LMArena Document1516Not measuredOnly Claude Opus 5 measured
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 Opus 5 and GPT-6 Luna
BenchmarkClaude Opus 5GPT-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 Opus 5$0.018Fits in one request
GPT-6 Luna$0.0003Fits in one request

GPT-6 Luna costs less

Repository review

50K input + 3K output tokens

Claude Opus 5$0.325Fits in one request
GPT-6 Luna$0.0065Fits in one request

GPT-6 Luna costs less

Agent loop

200K input + 10K output tokens

Claude Opus 5$1.25Fits 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 Opus 5 and GPT-6 Luna
SpecificationAnthropic Claude Opus 5OpenAI GPT-6 Luna
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJuly 24, 2026September 22, 2026
Context window1M1.05M
Input $/Mtok$5.00$0.10
Output $/Mtok$25.00$0.50
Coding index83.057.3
Independent measurements behind it65
Cost per solved task$1.33Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 5 better than GPT-6 Luna for coding?

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 57.3 for GPT-6 Luna. Pick GPT-6 Luna for output tokens 50.0x cheaper ($0.50 vs $25.00 per million) and a larger context window (1.05M against 1M tokens).

Which is cheaper, Claude Opus 5 or GPT-6 Luna?

Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for Claude Opus 5 only.

Which has the bigger context window, Claude Opus 5 or GPT-6 Luna?

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

How many benchmarks is the Claude Opus 5 vs GPT-6 Luna comparison based on?

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