Enter opens the highlighted result. Esc closes.

Claude Opus 4.7 vs GPT-5.6 Luna

Claude Opus 4.7 leads GPT-5.6 Luna on coding, 67.5 to 58.0 on the Vibe Coding Index, and GPT-5.6 Luna costs 20.8x less per output token ($1.20 vs $25.00 per million). Updated October 22, 2026; 88 benchmarks have a result for both.

Replace Claude Opus 4.7 Replace GPT-5.6 Luna
Claude Opus 4.7Anthropic
Coding
67.5
Overall
71.6
Output $/M
$25.00
66
GPT-5.6 LunaOpenAI
Coding
58.0
Overall
61.6
Output $/M
$1.20
21
vs boards won of 88 shared, 1 tied

Claude Opus 4.7 or GPT-5.6 Luna: which to pick

Pick Claude Opus 4.7 for coding: it scores 67.5 on the Vibe Coding Index against 58.0 for GPT-5.6 Luna, though on 4 benchmarks against 6.

Pick GPT-5.6 Luna for output tokens 20.8x cheaper ($1.20 vs $25.00 per million) and a lower cost per solved task ($0.04 against $2.95).

Model AClaude Opus 4.7Anthropic67.5/1004 independent benchmarks$2.95 per solved taskModel BGPT-5.6 LunaOpenAI58.0/1006 independent benchmarks$0.04 per solved task
Shared results
88
Claude Opus 4.7 only
15
GPT-5.6 Luna only
31
Like-for-like categories
7 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 4.7 67.5 from 4 benchmarks, GPT-5.6 Luna 58.0 from 6 benchmarks.
Widest category
Math, 10.1 points apart on average over 6 shared benchmarks.
Widest single gap
Vending-Bench 2: Claude Opus 4.7 $10,937 against GPT-5.6 Luna $4,095, 42.8 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.7 $25.00 against GPT-5.6 Luna $1.20 per million output tokens, 20.8x apart.
Context window
Claude Opus 4.7 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 Opus 4.7BarsGPT-5.6 LunaTies
Coding851 tie
Intelligence20
Agentic work34
Reasoning133
Math24
Knowledge111
General274
All shared boards66211 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index85
Coding benchmarks for Claude Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-5.6 LunaLeader
LiveBench codingNot measured73.6%Only GPT-5.6 Luna measured
LMArena WebDev15581518Claude Opus 4.7
AA Coding Index73.671.4Claude Opus 4.7
LiveCodeBench (Vals AI)85.1%Not measuredOnly Claude Opus 4.7 measured
SWE-bench Verified (Vals AI)82.0%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)71.0%77.1%GPT-5.6 Luna
Code migration (Vals AI)43.9%44.5%GPT-5.6 Luna
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)Not measured61.8%Only GPT-5.6 Luna measured
Terminal-Bench 2.1 (Vals AI)68.5%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)Not measured60.5%Only GPT-5.6 Luna measured
CyberBench (Vals AI)Not measured73.6%Only GPT-5.6 Luna measured
SciCodeNot measured53.6%Only GPT-5.6 Luna measured
Terminal-Bench Hard (Artificial Analysis run)54.5%Not measuredOnly Claude Opus 4.7 measured
Terminal-Bench80.2%Not measuredOnly Claude Opus 4.7 measured
FrontierCode38.5%39.8%GPT-5.6 Luna
GSO-Bench44.1%Not measuredOnly Claude Opus 4.7 measured
WeirdML76.4%60.9%Claude Opus 4.7
MirrorCode31.1%Not measuredOnly Claude Opus 4.7 measured
ALE-BenchNot measured1667.4Only GPT-5.6 Luna measured
LMArena Text: coding15191466Claude Opus 4.7
LMArena Text: software and IT15161463Claude Opus 4.7
LMArena WebDev: React15601508Claude Opus 4.7
LMArena WebDev: HTML15541520Claude Opus 4.7
LMArena WebDev: from an image15771517Claude Opus 4.7
SciCodeNot measured6.2%Only GPT-5.6 Luna measured
Neither model has a result on the other 11 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-5.6 LunaLeader
AA Intelligence Index40.737.3Claude Opus 4.7
Epoch Capabilities Index156.8156.5Claude Opus 4.7
Agentic workLike-for-likePublic boards, shown as published, kept out of the index34
Agentic work benchmarks for Claude Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-5.6 LunaLeader
AA Agentic Index38.642.1GPT-5.6 Luna
LiveBench researchNot measured51.0%Only GPT-5.6 Luna measured
LiveBench browserNot measured68.0%Only GPT-5.6 Luna measured
LiveBench long agenticNot measured30.4%Only GPT-5.6 Luna measured
SREBench (Vals AI)Not measured1.5%Only GPT-5.6 Luna measured
Finance Agent (Vals AI)51.5%55.0%GPT-5.6 Luna
Tax Agent Bench (Vals AI)23.7%24.8%GPT-5.6 Luna
Legal Research Bench (Vals AI)38.5%36.5%Claude Opus 4.7
Excel Modeling Benchmark (Vals AI)63.7%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 Telecom88.6%Not measuredOnly Claude Opus 4.7 measured
APEX-Agents49.2%43.0%Claude Opus 4.7
OSWorld 2.018.2%Not measuredOnly Claude Opus 4.7 measured
BALROGNot measured45.6%Only GPT-5.6 Luna measured
PostTrainBench28.6%Not measuredOnly Claude Opus 4.7 measured
Vending-Bench 2$10,937$4,095Claude Opus 4.7
LMArena Search1230Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index133
Reasoning benchmarks for Claude Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-5.6 LunaLeader
GPQA Diamond90.2%91.7%GPT-5.6 Luna
LiveBench reasoningNot measured85.6%Only GPT-5.6 Luna measured
MysteryMechanism (Vals AI)Not measured14.4%Only GPT-5.6 Luna measured
MMMU Pro (Vals AI)85.5%85.0%Claude Opus 4.7
GPQA Diamond (Artificial Analysis run)91.4%91.1%Claude Opus 4.7
Humanity's Last Exam (Artificial Analysis run)42.3%39.5%Claude Opus 4.7
GPQA Diamond (Epoch AI run)90.2%91.6%GPT-5.6 Luna
ARC-AGI93.5%88.0%Claude Opus 4.7
ARC-AGI-275.8%59.5%Claude Opus 4.7
SimpleBench61.7%46.8%Claude Opus 4.7
Chess puzzles41.0%43.0%GPT-5.6 Luna
Mystery game puzzles28.0%21.0%Claude Opus 4.7
EBR-bench19.0%Not measuredOnly Claude Opus 4.7 measured
LMArena Text: hard prompts15061451Claude Opus 4.7
LMArena Text: expert15211478Claude Opus 4.7
LMArena Text: hard prompts in English15081460Claude Opus 4.7
LMArena Vision: diagrams13361273Claude Opus 4.7
LMArena Vision: homework13371282Claude Opus 4.7
Kagi LLM Benchmark80.7%49.1%Claude Opus 4.7
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for Claude Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-5.6 LunaLeader
AIME96.3%Not measuredOnly Claude Opus 4.7 measured
OTIS Mock AIME97.8%98.3%GPT-5.6 Luna
FrontierMath, tiers 1 to 370.2%82.1%GPT-5.6 Luna
FrontierMath, tier 431.7%61.0%GPT-5.6 Luna
ProofBench54.0%60.0%GPT-5.6 Luna
LMArena Text: math14981459Claude Opus 4.7
LMArena Text: mathematical work15091470Claude Opus 4.7
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
Knowledge benchmarks for Claude Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-5.6 LunaLeader
MMLU Pro89.9%86.0%Claude Opus 4.7
LegalBench (Vals AI)85.3%84.0%Claude Opus 4.7
CaseLaw (Vals AI)68.4%Not measuredOnly Claude Opus 4.7 measured
CorpFin (Vals AI)66.1%64.2%Claude Opus 4.7
TaxEval (Vals AI)75.3%76.2%GPT-5.6 Luna
MortgageTax (Vals AI)70.3%67.3%Claude Opus 4.7
MedCode (Vals AI)54.9%42.4%Claude Opus 4.7
SimpleQA Verified51.7%41.0%Claude Opus 4.7
LMArena Text: science15081433Claude Opus 4.7
LMArena Text: medicine and healthcare14951399Claude Opus 4.7
LMArena Text: legal and government15041446Claude Opus 4.7
LMArena Text: business and finance14901439Claude Opus 4.7
FACTS Benchmark Suite45.5%35.0%Claude Opus 4.7
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Claude Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-5.6 LunaLeader
Design Arena: websitesNot measured1255Only GPT-5.6 Luna measured
Design Arena: UI componentsNot measured1248Only GPT-5.6 Luna measured
Design Arena: game devNot measured1194Only GPT-5.6 Luna measured
Design Arena: data vizNot measured1211Only GPT-5.6 Luna measured
Design Arena: 3DNot measured1121Only GPT-5.6 Luna measured
Design Arena: all code categoriesNot measured1231Only GPT-5.6 Luna measured
Design Arena: SVGNot measured1194Only GPT-5.6 Luna measured
Design Arena: ASCII artNot measured1142Only GPT-5.6 Luna measured
LiveBench designNot measured76.0%Only GPT-5.6 Luna measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index274
General benchmarks for Claude Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-5.6 LunaLeader
LiveBench data analysisNot measured78.0%Only GPT-5.6 Luna measured
Public Benefits Bench (Vals AI)Not measured61.2%Only GPT-5.6 Luna measured
SAGE (Vals AI)56.1%44.2%Claude Opus 4.7
MedScribe (Vals AI)83.0%84.4%GPT-5.6 Luna
Vals Multimodal Index67.4%69.1%GPT-5.6 Luna
IFBench58.6%Not measuredOnly Claude Opus 4.7 measured
Long context reasoning (AA-LCR)78.7%83.7%GPT-5.6 Luna
DTBench94.7%89.1%Claude Opus 4.7
LMCA52.2%48.5%Claude Opus 4.7
Surface Evolver BenchNot measured61.9%Only GPT-5.6 Luna measured
Furniture assembly33.3%42.5%GPT-5.6 Luna
ExploitBench26.5%Not measuredOnly Claude Opus 4.7 measured
LMArena Text14901431Claude Opus 4.7
LMArena Text: instruction following14981437Claude Opus 4.7
LMArena Text: creative writing14861396Claude Opus 4.7
LMArena Vision13171257Claude Opus 4.7
LMArena Text: English14961441Claude Opus 4.7
LMArena Text: non-English14801417Claude Opus 4.7
LMArena Text: Chinese15311470Claude Opus 4.7
LMArena Text: German14951455Claude Opus 4.7
LMArena Text: Japanese14741415Claude Opus 4.7
LMArena Text: Korean14641415Claude Opus 4.7
LMArena Text: French15031458Claude Opus 4.7
LMArena Text: Spanish14941446Claude Opus 4.7
LMArena Text: Russian14941427Claude Opus 4.7
LMArena Text: Polish14891405Claude Opus 4.7
LMArena Text: multi-turn15051434Claude Opus 4.7
LMArena Text: longer queries15051436Claude Opus 4.7
LMArena Text: writing and language14921419Claude Opus 4.7
LMArena Text: entertainment and media14741402Claude Opus 4.7
LMArena Vision: English13221263Claude Opus 4.7
LMArena Vision: Chinese13711294Claude Opus 4.7
LMArena Vision: reading text13271264Claude Opus 4.7
LMArena Vision: humor13091190Claude Opus 4.7
LMArena Vision: recognizing things1278Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: creative writing13261257Claude Opus 4.7
LMArena Document14951457Claude Opus 4.7
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 Opus 4.7 and GPT-5.6 Luna
BenchmarkClaude Opus 4.7GPT-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 Opus 4.7$0.018Fits 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 Opus 4.7$0.325Fits 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 Opus 4.7$1.25Fits 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 Opus 4.7 and GPT-5.6 Luna
SpecificationAnthropic Claude Opus 4.7OpenAI GPT-5.6 Luna
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 16, 2026July 9, 2026
Context window1M1.05M
Input $/Mtok$5.00$0.20
Output $/Mtok$25.00$1.20
Coding index67.558.0
Independent measurements behind it46
Cost per solved task$2.95$0.04
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.7 better than GPT-5.6 Luna for coding?

Pick Claude Opus 4.7 for coding: it scores 67.5 on the Vibe Coding Index against 58.0 for GPT-5.6 Luna, though on 4 benchmarks against 6. Pick GPT-5.6 Luna for output tokens 20.8x cheaper ($1.20 vs $25.00 per million) and a lower cost per solved task ($0.04 against $2.95).

Which is cheaper, Claude Opus 4.7 or GPT-5.6 Luna?

Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.6 Luna costs $0.20 and $1.20. Per solved SWE-bench Verified task, Claude Opus 4.7 costs $2.95 and GPT-5.6 Luna $0.04.

Which has the bigger context window, Claude Opus 4.7 or GPT-5.6 Luna?

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

How many benchmarks is the Claude Opus 4.7 vs GPT-5.6 Luna comparison based on?

88 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.7's coding index rests on 4 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-opus-4-7-vs-gpt-5-6-luna" title="Claude Opus 4.7 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-opus-4-7-vs-gpt-5-6-luna">LLMBenchmark.ai, Claude Opus 4.7 vs GPT-5.6 Luna</a></p>