Enter opens the highlighted result. Esc closes.

GPT-6.1 Sol vs GPT-6 Luna

GPT-6.1 Sol leads GPT-6 Luna on coding, 82.4 to 57.3 on the Vibe Coding Index, and GPT-6 Luna costs 20.0x less per output token ($0.50 vs $10.00 per million). Updated October 22, 2026; 94 benchmarks have a result for both.

Replace GPT-6.1 Sol Replace GPT-6 Luna
GPT-6.1 SolOpenAI
Coding
82.4
Overall
81.4
Output $/M
$10.00
91
GPT-6 LunaOpenAI
Coding
57.3
Overall
59.7
Output $/M
$0.50
3
vs boards won of 94 shared

GPT-6.1 Sol or GPT-6 Luna: which to pick

Pick GPT-6.1 Sol for coding: it scores 82.4 on the Vibe Coding Index against 57.3 for GPT-6 Luna.

Pick GPT-6 Luna for output tokens 20.0x cheaper ($0.50 vs $10.00 per million) and work measured by CyberBench (Vals AI) or LiveBench design, where it leads.

Model AGPT-6.1 SolOpenAI82.4/1005 independent benchmarksNo cost per solved taskModel BGPT-6 LunaOpenAI57.3/1005 independent benchmarksNo cost per solved task
Shared results
94
GPT-6.1 Sol only
4
GPT-6 Luna only
9
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
GPT-6.1 Sol 82.4 from 5 benchmarks, GPT-6 Luna 57.3 from 5 benchmarks.
Widest category
Math, 20.4 points apart on average over 6 shared benchmarks.
Widest single gap
Mystery game puzzles: GPT-6.1 Sol 80.0% against GPT-6 Luna 7.0%, 73.0 points apart on a 0 to 100 scale.
Output price
GPT-6.1 Sol $10.00 against GPT-6 Luna $0.50 per million output tokens, 20.0x apart.
Context window
Both take 1.05M tokens.

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
CategoryGPT-6.1 SolBarsGPT-6 LunaTies
Coding161
Intelligence20
Agentic work160
Reasoning130
Math60
Knowledge70
Web design61
General251
All shared boards913
CodingLike-for-likeSix of these boards feed the Vibe Coding Index161
Coding benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-6 LunaLeader
LiveBench coding96.0%84.5%GPT-6.1 Sol
LMArena WebDev17531578GPT-6.1 Sol
Terminal-Bench 4 (Vals AI)55.0%13.6%GPT-6.1 Sol
Vibe Code Bench (Vals AI)88.9%81.7%GPT-6.1 Sol
Code migration (Vals AI)65.1%42.5%GPT-6.1 Sol
ProgramBench (Vals AI)3.0%0.5%GPT-6.1 Sol
IOI (Vals AI)96.9%55.6%GPT-6.1 Sol
Terminal-Bench 2.1 (Vals AI)Not measured73.0%Only GPT-6 Luna measured
SWE-bench Multimodal (Vals AI)43.5%37.5%GPT-6.1 Sol
CyberBench (Vals AI)39.3%76.3%GPT-6 Luna
SciCode55.8%54.6%GPT-6.1 Sol
FrontierCode50.2%42.4%GPT-6.1 Sol
ALE-Bench2743.81576.9GPT-6.1 Sol
LMArena Text: coding14781437GPT-6.1 Sol
LMArena Text: software and IT14761423GPT-6.1 Sol
LMArena WebDev: React17541573GPT-6.1 Sol
LMArena WebDev: HTML18001595GPT-6.1 Sol
LMArena WebDev: from an image17021571GPT-6.1 Sol
SciCode9.2%Not measuredOnly GPT-6.1 Sol measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-6 LunaLeader
AA Intelligence Index51.838.1GPT-6.1 Sol
Epoch Capabilities Index168.4156.8GPT-6.1 Sol
Agentic workLike-for-likePublic boards, shown as published, kept out of the index160
Agentic work benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-6 LunaLeader
Design Arena: agents building web apps13061191GPT-6.1 Sol
Design Arena: agents building full-stack appsNot measured1158Only GPT-6 Luna measured
Design Arena: agents building mobile apps12131134GPT-6.1 Sol
Design Arena: spreadsheets1259Not measuredOnly GPT-6.1 Sol measured
LiveBench research83.5%43.5%GPT-6.1 Sol
LiveBench browser88.0%72.0%GPT-6.1 Sol
LiveBench long agentic73.0%48.1%GPT-6.1 Sol
SREBench (Vals AI)50.8%2.7%GPT-6.1 Sol
Finance Agent (Vals AI)52.0%49.9%GPT-6.1 Sol
Tax Agent Bench (Vals AI)21.8%19.9%GPT-6.1 Sol
Legal Research Bench (Vals AI)38.5%30.3%GPT-6.1 Sol
Harvey's Legal Agent Benchmark (Vals AI)6.3%4.2%GPT-6.1 Sol
Excel Modeling Benchmark (Vals AI)70.8%68.5%GPT-6.1 Sol
BioMysteryBench (Vals AI)79.6%61.5%GPT-6.1 Sol
Terminal-Bench-Science (Vals AI)52.9%4.3%GPT-6.1 Sol
Vals Science Index59.6%28.4%GPT-6.1 Sol
Robo-bench (Vals AI)28.3%Not measuredOnly GPT-6.1 Sol measured
APEX-Agents60.0%44.3%GPT-6.1 Sol
SpireClimb24.7%0.0%GPT-6.1 Sol
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index130
Reasoning benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-6 LunaLeader
LiveBench reasoning92.6%81.8%GPT-6.1 Sol
MysteryMechanism (Vals AI)46.4%19.4%GPT-6.1 Sol
Humanity's Last Exam (Artificial Analysis run)52.9%38.5%GPT-6.1 Sol
GPQA Diamond (Epoch AI run)95.4%90.5%GPT-6.1 Sol
ARC-AGI98.5%86.7%GPT-6.1 Sol
ARC-AGI-294.2%59.3%GPT-6.1 Sol
Chess puzzles68.0%36.0%GPT-6.1 Sol
Mystery game puzzles80.0%7.0%GPT-6.1 Sol
EBR-bench54.3%Not measuredOnly GPT-6.1 Sol measured
LMArena Text: hard prompts14631410GPT-6.1 Sol
LMArena Text: expert14891442GPT-6.1 Sol
LMArena Text: hard prompts in English14651410GPT-6.1 Sol
LMArena Vision: diagrams13061245GPT-6.1 Sol
LMArena Vision: homework13561261GPT-6.1 Sol
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-6 LunaLeader
OTIS Mock AIME100.0%98.9%GPT-6.1 Sol
FrontierMath, tiers 1 to 393.7%78.9%GPT-6.1 Sol
FrontierMath, tier 4100.0%56.1%GPT-6.1 Sol
ProofBench99.0%64.0%GPT-6.1 Sol
LMArena Text: math14891409GPT-6.1 Sol
LMArena Text: mathematical work15131427GPT-6.1 Sol
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index70
Knowledge benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-6 LunaLeader
MedCode (Vals AI)48.8%44.7%GPT-6.1 Sol
SimpleQA Verified73.9%41.4%GPT-6.1 Sol
LMArena Text: science14441386GPT-6.1 Sol
LMArena Text: medicine and healthcare14331352GPT-6.1 Sol
LMArena Text: legal and government14711400GPT-6.1 Sol
LMArena Text: business and finance14451388GPT-6.1 Sol
FACTS Benchmark Suite75.3%63.3%GPT-6.1 Sol
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index61
Web design benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-6 LunaLeader
Design Arena: websites13211271GPT-6.1 Sol
Design Arena: UI components13171295GPT-6.1 Sol
Design Arena: game dev13891257GPT-6.1 Sol
Design Arena: data viz12811216GPT-6.1 Sol
Design Arena: 3D14601218GPT-6.1 Sol
Design Arena: all code categories13451270GPT-6.1 Sol
Design Arena: SVGNot measured1252Only GPT-6 Luna measured
Design Arena: ASCII artNot measured1153Only GPT-6 Luna measured
LiveBench design82.1%82.5%GPT-6 Luna
GeneralLike-for-likePublic boards, shown as published, kept out of the index251
General benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-6 LunaLeader
Vals Index63.9%52.3%GPT-6.1 Sol
LiveBench data analysis82.7%73.4%GPT-6.1 Sol
Public Benefits Bench (Vals AI)59.3%57.6%GPT-6.1 Sol
SAGE (Vals AI)46.5%48.1%GPT-6 Luna
MedScribe (Vals AI)86.5%83.7%GPT-6.1 Sol
Long context reasoning (AA-LCR)84.0%83.3%GPT-6.1 Sol
DTBench96.5%90.1%GPT-6.1 Sol
LMCA62.8%44.5%GPT-6.1 Sol
Furniture assembly80.0%44.2%GPT-6.1 Sol
LMArena Text14431389GPT-6.1 Sol
LMArena Text: instruction following14661408GPT-6.1 Sol
LMArena Text: creative writing14251363GPT-6.1 Sol
LMArena Vision12881216GPT-6.1 Sol
LMArena Text: English14501393GPT-6.1 Sol
LMArena Text: non-English14331381GPT-6.1 Sol
LMArena Text: Chinese14871427GPT-6.1 Sol
LMArena Text: GermanNot measured1376Only GPT-6 Luna measured
LMArena Text: JapaneseNot measured1369Only GPT-6 Luna measured
LMArena Text: KoreanNot measured1359Only GPT-6 Luna measured
LMArena Text: French14601408GPT-6.1 Sol
LMArena Text: Spanish14391391GPT-6.1 Sol
LMArena Text: Russian14571392GPT-6.1 Sol
LMArena Text: PolishNot measured1383Only GPT-6 Luna measured
LMArena Text: multi-turn14421392GPT-6.1 Sol
LMArena Text: longer queries14581408GPT-6.1 Sol
LMArena Text: writing and language14441384GPT-6.1 Sol
LMArena Text: entertainment and media14261364GPT-6.1 Sol
LMArena Vision: English12741204GPT-6.1 Sol
LMArena Vision: ChineseNot measured1266Only GPT-6 Luna measured
LMArena Vision: reading text12891225GPT-6.1 Sol
LMArena Vision: creative writing13011205GPT-6.1 Sol
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-6.1 Sol and GPT-6 Luna
BenchmarkGPT-6.1 SolGPT-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

GPT-6.1 Sol$0.0070Fits in one request
GPT-6 Luna$0.0003Fits in one request

GPT-6 Luna costs less

Repository review

50K input + 3K output tokens

GPT-6.1 Sol$0.130Fits in one request
GPT-6 Luna$0.0065Fits in one request

GPT-6 Luna costs less

Agent loop

200K input + 10K output tokens

GPT-6.1 Sol$0.500Fits 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 GPT-6.1 Sol and GPT-6 Luna
SpecificationOpenAI GPT-6.1 SolOpenAI GPT-6 Luna
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 29, 2026September 22, 2026
Context window1.05M1.05M
Input $/Mtok$2.00$0.10
Output $/Mtok$10.00$0.50
Coding index82.457.3
Independent measurements behind it55
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-6.1 Sol better than GPT-6 Luna for coding?

Pick GPT-6.1 Sol for coding: it scores 82.4 on the Vibe Coding Index against 57.3 for GPT-6 Luna. Pick GPT-6 Luna for output tokens 20.0x cheaper ($0.50 vs $10.00 per million) and work measured by CyberBench (Vals AI) or LiveBench design, where it leads.

Which is cheaper, GPT-6.1 Sol or GPT-6 Luna?

GPT-6.1 Sol costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-6.1 Sol or GPT-6 Luna?

Neither: both take 1.05M tokens.

How many benchmarks is the GPT-6.1 Sol vs GPT-6 Luna comparison based on?

94 benchmarks have a result for both models as of October 22, 2026. GPT-6.1 Sol's coding index rests on 5 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/gpt-6-1-sol-vs-gpt-6-luna" title="GPT-6.1 Sol 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/gpt-6-1-sol-vs-gpt-6-luna">LLMBenchmark.ai, GPT-6.1 Sol vs GPT-6 Luna</a></p>