Enter opens the highlighted result. Esc closes.

Gemini 3.7 Flash vs Kimi K3

Kimi K3 leads Gemini 3.7 Flash on coding, 62.3 to 58.0 on the Vibe Coding Index, and Gemini 3.7 Flash costs 4.0x less per output token ($3.75 vs $15.00 per million). Updated October 22, 2026; 100 benchmarks have a result for both.

Replace Gemini 3.7 Flash Replace Kimi K3
Gemini 3.7 FlashGoogle
Coding
58.0
Overall
65.7
Output $/M
$3.75
47
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
52
vs boards won of 100 shared, 1 tied

Gemini 3.7 Flash or Kimi K3: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 58.0 for Gemini 3.7 Flash.

Pick Gemini 3.7 Flash for output tokens 4.0x cheaper ($3.75 vs $15.00 per million) and work measured by LiveBench coding or LiveCodeBench (Vals AI), where it leads.

Model AGemini 3.7 FlashGoogle58.0/1006 independent benchmarks$1.78 per solved taskModel BKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved task
Shared results
100
Gemini 3.7 Flash only
14
Kimi K3 only
17
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 3.7 Flash 58.0 from 6 benchmarks, Kimi K3 62.3 from 6 benchmarks.
Widest category
Agentic work, 9.5 points apart on average over 16 shared benchmarks.
Widest single gap
LiveBench browser: Gemini 3.7 Flash 56.0% against Kimi K3 16.0%, 40.0 points apart on a 0 to 100 scale.
Output price
Gemini 3.7 Flash $3.75 against Kimi K3 $15.00 per million output tokens, 4.0x 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
CategoryGemini 3.7 FlashBarsKimi K3Ties
Coding615
Intelligence11
Agentic work610
Reasoning103
Math141 tie
Knowledge82
Web design08
General159
All shared boards47521 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index615
Coding benchmarks for Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
LiveBench coding80.5%59.3%Gemini 3.7 Flash
LMArena WebDev15911655Kimi K3
AA Coding Index71.576.2Kimi K3
LiveCodeBench (Vals AI)88.7%87.2%Gemini 3.7 Flash
SWE-bench Verified (Vals AI)80.8%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)12.1%17.2%Kimi K3
Vibe Code Bench (Vals AI)70.4%85.0%Kimi K3
Code migration (Vals AI)34.8%16.1%Gemini 3.7 Flash
ProgramBench (Vals AI)0.0%2.0%Kimi K3
IOI (Vals AI)67.8%48.9%Gemini 3.7 Flash
Terminal-Bench 2.1 (Vals AI)77.5%80.9%Kimi K3
SWE-bench Multimodal (Vals AI)Not measured44.2%Only Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured18.2%Only Kimi K3 measured
SkillsBench (Vals AI)65.9%Not measuredOnly Gemini 3.7 Flash measured
CyberBench (Vals AI)43.8%75.2%Kimi K3
SciCode59.8%59.5%Gemini 3.7 Flash
FrontierCode43.6%44.2%Kimi K3
FrontierSWE20.3%25.9%Kimi K3
WeirdMLNot measured82.6%Only Kimi K3 measured
ALE-Bench904.31524.5Kimi K3
LMArena Text: coding14991508Kimi K3
LMArena Text: software and IT14981499Kimi K3
LMArena WebDev: React15871670Kimi K3
LMArena WebDev: HTML15931644Kimi K3
LMArena WebDev: from an image15991579Gemini 3.7 Flash
SciCode13.8%Not measuredOnly Gemini 3.7 Flash measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
AA Intelligence Index39.643.6Kimi K3
Epoch Capabilities Index158.0157.9Gemini 3.7 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index610
Agentic work benchmarks for Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
AA Agentic IndexNot measured50.0Only Kimi K3 measured
Design Arena: agents building web apps12231295Kimi K3
Design Arena: agents building full-stack apps12081315Kimi K3
Design Arena: agents building mobile apps12291269Kimi K3
Design Arena: agents building Android apps12431253Kimi K3
Design Arena: agents building Godot games12641223Gemini 3.7 Flash
Design Arena: agents building games12351252Kimi K3
Design Arena: HTML slidesNot measured1206Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1247Only Kimi K3 measured
Design Arena: spreadsheets10581070Kimi K3
LiveBench research76.5%79.0%Kimi K3
LiveBench browser56.0%16.0%Gemini 3.7 Flash
LiveBench long agentic28.3%42.8%Kimi K3
SREBench (Vals AI)4.6%Not measuredOnly Gemini 3.7 Flash measured
Finance Agent (Vals AI)59.0%53.1%Gemini 3.7 Flash
Tax Agent Bench (Vals AI)22.8%33.4%Kimi K3
Legal Research Bench (Vals AI)34.6%46.1%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)71.3%66.7%Gemini 3.7 Flash
BioMysteryBench (Vals AI)Not measured72.6%Only Kimi K3 measured
Terminal-Bench-Science (Vals AI)7.1%1.4%Gemini 3.7 Flash
Time Horizon Index (Vals AI)Not measured10.5%Only Kimi K3 measured
APEX-Agents67.8%47.8%Gemini 3.7 Flash
Remote Labor Index5.0%Not measuredOnly Gemini 3.7 Flash measured
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2Not measured$5,165Only Kimi K3 measured
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index103
Reasoning benchmarks for Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
GPQA Diamond93.9%92.9%Gemini 3.7 Flash
LiveBench reasoning87.8%90.7%Kimi K3
MMMU Pro (Vals AI)89.0%88.2%Gemini 3.7 Flash
GPQA Diamond (Artificial Analysis run)94.5%93.5%Gemini 3.7 Flash
Humanity's Last Exam (Artificial Analysis run)47.9%46.9%Gemini 3.7 Flash
GPQA Diamond (Epoch AI run)94.8%93.1%Gemini 3.7 Flash
ARC-AGI95.5%94.5%Gemini 3.7 Flash
ARC-AGI-284.6%60.4%Gemini 3.7 Flash
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzles66.0%37.0%Gemini 3.7 Flash
Mystery game puzzles37.0%26.0%Gemini 3.7 Flash
LMArena Text: hard prompts14951495Gemini 3.7 Flash
LMArena Text: expert15121520Kimi K3
LMArena Text: hard prompts in English14871496Kimi K3
LMArena Vision: diagrams1329Not measuredOnly Gemini 3.7 Flash measured
LMArena Vision: homework1320Not measuredOnly Gemini 3.7 Flash measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index14
Math benchmarks for Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
OTIS Mock AIME97.2%97.2%Tie
FrontierMath, tiers 1 to 371.6%72.2%Kimi K3
FrontierMath, tier 436.6%39.0%Kimi K3
ProofBench58.0%87.0%Kimi K3
LMArena Text: math15111494Gemini 3.7 Flash
LMArena Text: mathematical work15021505Kimi K3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
Knowledge benchmarks for Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
MMLU Pro90.1%88.0%Gemini 3.7 Flash
LegalBench (Vals AI)87.3%86.2%Gemini 3.7 Flash
CorpFin (Vals AI)Not measured71.6%Only Kimi K3 measured
TaxEval (Vals AI)74.7%75.7%Kimi K3
MortgageTax (Vals AI)66.7%66.3%Gemini 3.7 Flash
MedCode (Vals AI)53.4%49.4%Gemini 3.7 Flash
SimpleQA Verified69.2%50.6%Gemini 3.7 Flash
LMArena Text: science15111508Gemini 3.7 Flash
LMArena Text: medicine and healthcare14941489Gemini 3.7 Flash
LMArena Text: legal and government14961503Kimi K3
LMArena Text: business and finance14791470Gemini 3.7 Flash
FACTS Benchmark Suite71.2%Not measuredOnly Gemini 3.7 Flash measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
Design Arena: websites13031334Kimi K3
Design Arena: UI components12961341Kimi K3
Design Arena: game dev13171358Kimi K3
Design Arena: data viz13151351Kimi K3
Design Arena: 3D13071387Kimi K3
Design Arena: all code categories13081360Kimi K3
Design Arena: SVG12831302Kimi K3
Design Arena: ASCII art1276Not measuredOnly Gemini 3.7 Flash measured
LiveBench design73.2%77.2%Kimi K3
GeneralLike-for-likePublic boards, shown as published, kept out of the index159
General benchmarks for Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
Vals IndexNot measured53.0%Only Kimi K3 measured
LiveBench data analysis68.0%78.7%Kimi K3
Public Benefits Bench (Vals AI)Not measured68.2%Only Kimi K3 measured
SAGE (Vals AI)49.2%52.8%Kimi K3
MedScribe (Vals AI)83.9%88.0%Kimi K3
Vals Multimodal IndexNot measured73.4%Only Kimi K3 measured
Long context reasoning (AA-LCR)83.0%88.7%Kimi K3
DTBench96.8%91.2%Gemini 3.7 Flash
LMCA50.4%52.7%Kimi K3
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assembly26.7%34.2%Kimi K3
LMArena Text14891476Gemini 3.7 Flash
LMArena Text: instruction following14841485Kimi K3
LMArena Text: creative writing14881457Gemini 3.7 Flash
LMArena Vision1314Not measuredOnly Gemini 3.7 Flash measured
LMArena Text: English14831481Gemini 3.7 Flash
LMArena Text: non-English14871466Gemini 3.7 Flash
LMArena Text: Chinese15521529Gemini 3.7 Flash
LMArena Text: German15061490Gemini 3.7 Flash
LMArena Text: Japanese15111494Gemini 3.7 Flash
LMArena Text: Korean14811460Gemini 3.7 Flash
LMArena Text: French15001492Gemini 3.7 Flash
LMArena Text: Spanish14951472Gemini 3.7 Flash
LMArena Text: Russian15151485Gemini 3.7 Flash
LMArena Text: Polish15031458Gemini 3.7 Flash
LMArena Text: multi-turn14851489Kimi K3
LMArena Text: longer queries14921494Kimi K3
LMArena Text: writing and language14911471Gemini 3.7 Flash
LMArena Text: entertainment and media14771453Gemini 3.7 Flash
LMArena Vision: English1309Not measuredOnly Gemini 3.7 Flash measured
LMArena Vision: Chinese1394Not measuredOnly Gemini 3.7 Flash measured
LMArena Vision: reading text1322Not measuredOnly Gemini 3.7 Flash measured
LMArena Vision: humor1299Not measuredOnly Gemini 3.7 Flash measured
LMArena Vision: creative writing1312Not measuredOnly Gemini 3.7 Flash 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 Gemini 3.7 Flash and Kimi K3
BenchmarkGemini 3.7 FlashKimi K3Leader
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 3.7 Flash$0.0026Fits in one request
Kimi K3$0.011Fits in one request

Gemini 3.7 Flash costs less

Repository review

50K input + 3K output tokens

Gemini 3.7 Flash$0.049Fits in one request
Kimi K3$0.195Fits in one request

Gemini 3.7 Flash costs less

Agent loop

200K input + 10K output tokens

Gemini 3.7 Flash$0.188Fits in one request
Kimi K3$0.750Fits in one request

Gemini 3.7 Flash 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 3.7 Flash and Kimi K3
SpecificationGoogle Gemini 3.7 FlashMoonshotAI Kimi K3
MakerGoogleMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedAugust 13, 2026July 16, 2026
Context window1.05M1.05M
Input $/Mtok$0.75$3.00
Output $/Mtok$3.75$15.00
Coding index58.062.3
Independent measurements behind it66
Cost per solved task$1.78$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.7 Flash better than Kimi K3 for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 58.0 for Gemini 3.7 Flash. Pick Gemini 3.7 Flash for output tokens 4.0x cheaper ($3.75 vs $15.00 per million) and work measured by LiveBench coding or LiveCodeBench (Vals AI), where it leads.

Which is cheaper, Gemini 3.7 Flash or Kimi K3?

Gemini 3.7 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Kimi K3 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Gemini 3.7 Flash costs $1.78 and Kimi K3 $0.81.

Which has the bigger context window, Gemini 3.7 Flash or Kimi K3?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.7 Flash vs Kimi K3 comparison based on?

100 benchmarks have a result for both models as of October 22, 2026. Gemini 3.7 Flash's coding index rests on 6 independent benchmarks and Kimi K3'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/gemini-3-7-flash-vs-kimi-k3" title="Gemini 3.7 Flash vs Kimi K3, 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-3-7-flash-vs-kimi-k3">LLMBenchmark.ai, Gemini 3.7 Flash vs Kimi K3</a></p>