Enter opens the highlighted result. Esc closes.

Gemini 3.5 Flash vs GPT-6 Luna

GPT-6 Luna leads Gemini 3.5 Flash on coding, 57.3 to 39.8 on the Vibe Coding Index, and GPT-6 Luna costs 18.0x less per output token ($0.50 vs $9.00 per million). Updated October 22, 2026; 84 benchmarks have a result for both.

Replace Gemini 3.5 Flash Replace GPT-6 Luna
Gemini 3.5 FlashGoogle
Coding
39.8
Overall
63.8
Output $/M
$9.00
60
GPT-6 LunaOpenAI
Coding
57.3
Overall
59.7
Output $/M
$0.50
24
vs boards won of 84 shared

Gemini 3.5 Flash or GPT-6 Luna: which to pick

Pick GPT-6 Luna for coding: it scores 57.3 on the Vibe Coding Index against 39.8 for Gemini 3.5 Flash.

Pick Gemini 3.5 Flash for work measured by Terminal-Bench 2.1 (Vals AI) or LMArena Text: coding, where it leads.

Model AGemini 3.5 FlashGoogle39.8/1004 independent benchmarks$1.21 per solved taskModel BGPT-6 LunaOpenAI57.3/1005 independent benchmarksNo cost per solved task
Shared results
84
Gemini 3.5 Flash only
28
GPT-6 Luna only
19
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
Gemini 3.5 Flash 39.8 from 4 benchmarks, GPT-6 Luna 57.3 from 5 benchmarks.
Widest category
Math, 18.2 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Gemini 3.5 Flash 31.0% against GPT-6 Luna 64.0%, 33.0 points apart on a 0 to 100 scale.
Output price
Gemini 3.5 Flash $9.00 against GPT-6 Luna $0.50 per million output tokens, 18.0x apart.
Context window
Gemini 3.5 Flash takes 1.05M 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
CategoryGemini 3.5 FlashBarsGPT-6 LunaTies
Coding310
Intelligence02
Agentic work72
Reasoning110
Math24
Knowledge61
Web design53
General262
All shared boards6024
CodingLike-for-likeSix of these boards feed the Vibe Coding Index310
Coding benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-6 LunaLeader
LiveBench codingNot measured84.5%Only GPT-6 Luna measured
LMArena WebDev14991578GPT-6 Luna
LiveCodeBench (Vals AI)87.6%Not measuredOnly Gemini 3.5 Flash measured
SWE-bench Verified (Vals AI)78.8%Not measuredOnly Gemini 3.5 Flash measured
Terminal-Bench 4 (Vals AI)6.1%13.6%GPT-6 Luna
Vibe Code Bench (Vals AI)48.7%81.7%GPT-6 Luna
Code migration (Vals AI)26.8%42.5%GPT-6 Luna
ProgramBench (Vals AI)0.0%0.5%GPT-6 Luna
IOI (Vals AI)Not measured55.6%Only GPT-6 Luna measured
Terminal-Bench 2.1 (Vals AI)74.2%73.0%Gemini 3.5 Flash
SWE-bench Multimodal (Vals AI)Not measured37.5%Only GPT-6 Luna measured
SkillsBench (Vals AI)52.7%Not measuredOnly Gemini 3.5 Flash measured
CyberBench (Vals AI)Not measured76.3%Only GPT-6 Luna measured
SciCode53.9%54.6%GPT-6 Luna
Terminal-Bench Hard (Artificial Analysis run)46.2%Not measuredOnly Gemini 3.5 Flash measured
FrontierCodeNot measured42.4%Only GPT-6 Luna measured
WeirdML62.6%Not measuredOnly Gemini 3.5 Flash measured
ALE-Bench911.01576.9GPT-6 Luna
LMArena Text: coding14931437Gemini 3.5 Flash
LMArena Text: software and IT14941423Gemini 3.5 Flash
LMArena WebDev: React14951573GPT-6 Luna
LMArena WebDev: HTML15221595GPT-6 Luna
LMArena WebDev: from an image15041571GPT-6 Luna
SciCode12.3%Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-6 LunaLeader
AA Intelligence Index33.638.1GPT-6 Luna
Epoch Capabilities Index154.9156.8GPT-6 Luna
Agentic workLike-for-likePublic boards, shown as published, kept out of the index72
Agentic work benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-6 LunaLeader
Design Arena: agents building web apps12021191Gemini 3.5 Flash
Design Arena: agents building full-stack apps11971158Gemini 3.5 Flash
Design Arena: agents building mobile apps11741134Gemini 3.5 Flash
Design Arena: agents building Android apps1185Not measuredOnly Gemini 3.5 Flash measured
Design Arena: agents building Godot games1098Not measuredOnly Gemini 3.5 Flash measured
Design Arena: agents building games1180Not measuredOnly Gemini 3.5 Flash measured
Design Arena: HTML slides1093Not measuredOnly Gemini 3.5 Flash measured
Design Arena: PowerPoint slides1154Not measuredOnly Gemini 3.5 Flash measured
LiveBench researchNot measured43.5%Only GPT-6 Luna measured
LiveBench browserNot measured72.0%Only GPT-6 Luna measured
LiveBench long agenticNot measured48.1%Only GPT-6 Luna measured
SREBench (Vals AI)Not measured2.7%Only GPT-6 Luna measured
Finance Agent (Vals AI)57.9%49.9%Gemini 3.5 Flash
Tax Agent Bench (Vals AI)21.6%19.9%Gemini 3.5 Flash
Legal Research Bench (Vals AI)30.8%30.3%Gemini 3.5 Flash
Harvey's Legal Agent Benchmark (Vals AI)Not measured4.2%Only GPT-6 Luna measured
Excel Modeling Benchmark (Vals AI)63.5%68.5%GPT-6 Luna
BioMysteryBench (Vals AI)Not measured61.5%Only GPT-6 Luna measured
Terminal-Bench-Science (Vals AI)5.7%4.3%Gemini 3.5 Flash
Vals Science IndexNot measured28.4%Only GPT-6 Luna measured
τ²-Bench Telecom95.6%Not measuredOnly Gemini 3.5 Flash measured
APEX-Agents27.5%44.3%GPT-6 Luna
SpireClimbNot measured0.0%Only GPT-6 Luna measured
Vending-Bench 2$5,396Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
Reasoning benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-6 LunaLeader
GPQA Diamond92.7%Not measuredOnly Gemini 3.5 Flash measured
LiveBench reasoningNot measured81.8%Only GPT-6 Luna measured
MysteryMechanism (Vals AI)Not measured19.4%Only GPT-6 Luna measured
MMMU Pro (Vals AI)88.3%Not measuredOnly Gemini 3.5 Flash measured
GPQA Diamond (Artificial Analysis run)92.2%Not measuredOnly Gemini 3.5 Flash measured
Humanity's Last Exam (Artificial Analysis run)42.7%38.5%Gemini 3.5 Flash
GPQA Diamond (Epoch AI run)92.8%90.5%Gemini 3.5 Flash
ARC-AGI92.5%86.7%Gemini 3.5 Flash
ARC-AGI-272.1%59.3%Gemini 3.5 Flash
SimpleBench76.7%Not measuredOnly Gemini 3.5 Flash measured
Chess puzzles45.0%36.0%Gemini 3.5 Flash
Mystery game puzzles32.0%7.0%Gemini 3.5 Flash
EBR-bench4.8%Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: hard prompts14881410Gemini 3.5 Flash
LMArena Text: expert14951442Gemini 3.5 Flash
LMArena Text: hard prompts in English14831410Gemini 3.5 Flash
LMArena Vision: diagrams13231245Gemini 3.5 Flash
LMArena Vision: homework13301261Gemini 3.5 Flash
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-6 LunaLeader
OTIS Mock AIME95.6%98.9%GPT-6 Luna
FrontierMath, tiers 1 to 362.8%78.9%GPT-6 Luna
FrontierMath, tier 426.8%56.1%GPT-6 Luna
ProofBench31.0%64.0%GPT-6 Luna
LMArena Text: math15041409Gemini 3.5 Flash
LMArena Text: mathematical work14951427Gemini 3.5 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index61
Knowledge benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-6 LunaLeader
MMLU Pro89.5%Not measuredOnly Gemini 3.5 Flash measured
LegalBench (Vals AI)83.6%Not measuredOnly Gemini 3.5 Flash measured
CorpFin (Vals AI)64.7%Not measuredOnly Gemini 3.5 Flash measured
TaxEval (Vals AI)74.4%Not measuredOnly Gemini 3.5 Flash measured
MortgageTax (Vals AI)68.1%Not measuredOnly Gemini 3.5 Flash measured
MedCode (Vals AI)55.8%44.7%Gemini 3.5 Flash
SimpleQA Verified66.2%41.4%Gemini 3.5 Flash
LMArena Text: science14951386Gemini 3.5 Flash
LMArena Text: medicine and healthcare14831352Gemini 3.5 Flash
LMArena Text: legal and government14881400Gemini 3.5 Flash
LMArena Text: business and finance14671388Gemini 3.5 Flash
FACTS Benchmark Suite63.1%63.3%GPT-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 index53
Web design benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-6 LunaLeader
Design Arena: websites12671271GPT-6 Luna
Design Arena: UI components12691295GPT-6 Luna
Design Arena: game dev12631257Gemini 3.5 Flash
Design Arena: data viz12361216Gemini 3.5 Flash
Design Arena: 3D12431218Gemini 3.5 Flash
Design Arena: all code categories12661270GPT-6 Luna
Design Arena: SVG12531252Gemini 3.5 Flash
Design Arena: ASCII art12541153Gemini 3.5 Flash
LiveBench designNot measured82.5%Only GPT-6 Luna measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index262
General benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-6 LunaLeader
Vals IndexNot measured52.3%Only GPT-6 Luna measured
LiveBench data analysisNot measured73.4%Only GPT-6 Luna measured
Public Benefits Bench (Vals AI)59.5%57.6%Gemini 3.5 Flash
SAGE (Vals AI)49.9%48.1%Gemini 3.5 Flash
MedScribe (Vals AI)76.6%83.7%GPT-6 Luna
Vals Multimodal Index62.9%Not measuredOnly Gemini 3.5 Flash measured
IFBench76.3%Not measuredOnly Gemini 3.5 Flash measured
Long context reasoning (AA-LCR)74.3%83.3%GPT-6 Luna
DTBench94.7%90.1%Gemini 3.5 Flash
LMCA47.1%44.5%Gemini 3.5 Flash
Surface Evolver Bench58.1%Not measuredOnly Gemini 3.5 Flash measured
Furniture assemblyNot measured44.2%Only GPT-6 Luna measured
LMArena Text14821389Gemini 3.5 Flash
LMArena Text: instruction following14671408Gemini 3.5 Flash
LMArena Text: creative writing14701363Gemini 3.5 Flash
LMArena Vision13081216Gemini 3.5 Flash
LMArena Text: English14811393Gemini 3.5 Flash
LMArena Text: non-English14751381Gemini 3.5 Flash
LMArena Text: Chinese15271427Gemini 3.5 Flash
LMArena Text: German14941376Gemini 3.5 Flash
LMArena Text: Japanese14861369Gemini 3.5 Flash
LMArena Text: Korean14481359Gemini 3.5 Flash
LMArena Text: French14901408Gemini 3.5 Flash
LMArena Text: Spanish14801391Gemini 3.5 Flash
LMArena Text: Russian14931392Gemini 3.5 Flash
LMArena Text: Polish15161383Gemini 3.5 Flash
LMArena Text: multi-turn14811392Gemini 3.5 Flash
LMArena Text: longer queries14831408Gemini 3.5 Flash
LMArena Text: writing and language14781384Gemini 3.5 Flash
LMArena Text: entertainment and media14591364Gemini 3.5 Flash
LMArena Vision: English13051204Gemini 3.5 Flash
LMArena Vision: Chinese13771266Gemini 3.5 Flash
LMArena Vision: reading text13171225Gemini 3.5 Flash
LMArena Vision: humor1321Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision: creative writing13011205Gemini 3.5 Flash
LMArena Document1463Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.5 Flash and GPT-6 Luna
BenchmarkGemini 3.5 FlashGPT-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

Gemini 3.5 Flash$0.0060Fits in one request
GPT-6 Luna$0.0003Fits in one request

GPT-6 Luna costs less

Repository review

50K input + 3K output tokens

Gemini 3.5 Flash$0.102Fits in one request
GPT-6 Luna$0.0065Fits in one request

GPT-6 Luna costs less

Agent loop

200K input + 10K output tokens

Gemini 3.5 Flash$0.390Fits 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 Gemini 3.5 Flash and GPT-6 Luna
SpecificationGoogle Gemini 3.5 FlashOpenAI GPT-6 Luna
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 19, 2026September 22, 2026
Context window1.05M1.05M
Input $/Mtok$1.50$0.10
Output $/Mtok$9.00$0.50
Coding index39.857.3
Independent measurements behind it45
Cost per solved task$1.21Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.5 Flash better than GPT-6 Luna for coding?

Pick GPT-6 Luna for coding: it scores 57.3 on the Vibe Coding Index against 39.8 for Gemini 3.5 Flash. Pick Gemini 3.5 Flash for work measured by Terminal-Bench 2.1 (Vals AI) or LMArena Text: coding, where it leads.

Which is cheaper, Gemini 3.5 Flash or GPT-6 Luna?

Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for Gemini 3.5 Flash only.

Which has the bigger context window, Gemini 3.5 Flash or GPT-6 Luna?

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

How many benchmarks is the Gemini 3.5 Flash vs GPT-6 Luna comparison based on?

84 benchmarks have a result for both models as of October 22, 2026. Gemini 3.5 Flash's coding index rests on 4 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/gemini-3-5-flash-vs-gpt-6-luna" title="Gemini 3.5 Flash 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/gemini-3-5-flash-vs-gpt-6-luna">LLMBenchmark.ai, Gemini 3.5 Flash vs GPT-6 Luna</a></p>