LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.5 Flash vs Kimi K2.7 Code

Updated October 21, 2026. 48 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.5 Flash Replace Kimi K2.7 Code
Gemini 3.5 FlashGoogle
Coding
42.8
Overall
33.6
Output $/M
$9.00
41
Kimi K2.7 CodeMoonshot AI
Coding
39.1
Overall
25.8
Output $/M
$3.35
5
vs boards won of 48 shared, 2 tied

Decision reading

Pick Gemini 3.5 Flash for coding: it scores 42.8 on the Vibe Coding Index against 39.1 for Kimi K2.7 Code.

Pick Kimi K2.7 Code when output tokens cost 2.7x less, or when a solved task costs $0.35 against $1.21.

Model AGemini 3.5 FlashGoogle42.8/1001 independent benchmark$1.21 per solved taskModel BKimi K2.7 CodeMoonshot AI39.1/1001 independent benchmark$0.35 per solved task
Shared results
48
Gemini 3.5 Flash only
62
Kimi K2.7 Code only
3
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 42.8 from 1 benchmark, Kimi K2.7 Code 39.1 from 1 benchmark.
Widest category
Knowledge, 29.7 points apart on average over 1 shared benchmark.
Widest single gap
Chess puzzles: Gemini 3.5 Flash 45.0% against Kimi K2.7 Code 14.0%, 31.0 points apart on a 0 to 100 scale.
Output price
Gemini 3.5 Flash $9.00 against Kimi K2.7 Code $3.35 per million output tokens, 2.7x apart.
Context window
Gemini 3.5 Flash takes 1.05M tokens, Kimi K2.7 Code 262K.

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 FlashBarsKimi K2.7 CodeTies
Coding1311 tie
Intelligence20
Agentic work83
Reasoning50
Math201 tie
Knowledge10
Web design80
General21
All shared boards4152 ties
CodingLike-for-likeFour of these boards feed the Vibe Coding Index131
Coding benchmarks for Gemini 3.5 Flash and Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
LMArena WebDev14991474Gemini 3.5 Flash
AA Coding IndexNot measured60.8Only Kimi K2.7 Code measured
LiveCodeBench (Vals AI)87.6%82.0%Gemini 3.5 Flash
SWE-bench Verified (Vals AI)78.8%78.2%Gemini 3.5 Flash
Terminal-Bench 4 (Vals AI)6.1%Not measuredOnly Gemini 3.5 Flash measured
Vibe Code Bench (Vals AI)48.7%47.2%Gemini 3.5 Flash
Code migration (Vals AI)26.8%25.4%Gemini 3.5 Flash
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)74.2%67.0%Gemini 3.5 Flash
SkillsBench (Vals AI)52.7%50.0%Gemini 3.5 Flash
SciCode53.9%47.8%Gemini 3.5 Flash
Terminal-Bench Hard (Artificial Analysis run)46.2%44.7%Gemini 3.5 Flash
FrontierCodeNot measured30.1%Only Kimi K2.7 Code measured
WeirdML62.6%54.1%Gemini 3.5 Flash
ALE-Bench911.0886.2Gemini 3.5 Flash
LMArena Text: coding1493Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: software and IT1494Not measuredOnly Gemini 3.5 Flash measured
LMArena WebDev: React14951475Gemini 3.5 Flash
LMArena WebDev: HTML15221451Gemini 3.5 Flash
LMArena WebDev: from an image15041513Kimi K2.7 Code
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 3.5 Flash and Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
AA Intelligence Index33.625.8Gemini 3.5 Flash
Epoch Capabilities Index154.9150.1Gemini 3.5 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index83
Agentic work benchmarks for Gemini 3.5 Flash and Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
AA Agentic IndexNot measured21.0Only Kimi K2.7 Code measured
Design Arena: agents building web apps12021176Gemini 3.5 Flash
Design Arena: agents building full-stack apps11971175Gemini 3.5 Flash
Design Arena: agents building mobile apps11751143Gemini 3.5 Flash
Design Arena: agents building Android apps11901143Gemini 3.5 Flash
Design Arena: agents building Godot games10981147Kimi K2.7 Code
Design Arena: agents building games11801130Gemini 3.5 Flash
Design Arena: HTML slides11421201Kimi K2.7 Code
Design Arena: PowerPoint slides11781154Gemini 3.5 Flash
Finance Agent (Vals AI)57.9%Not measuredOnly Gemini 3.5 Flash measured
Tax Agent Bench (Vals AI)21.6%Not measuredOnly Gemini 3.5 Flash measured
Legal Research Bench (Vals AI)30.8%Not measuredOnly Gemini 3.5 Flash measured
Excel Modeling Benchmark (Vals AI)63.5%Not measuredOnly Gemini 3.5 Flash measured
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly Gemini 3.5 Flash measured
τ²-Bench Telecom95.6%90.1%Gemini 3.5 Flash
APEX-Agents27.5%37.6%Kimi K2.7 Code
Vending-Bench 2$5,396$5,083Gemini 3.5 Flash
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for Gemini 3.5 Flash and Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
GPQA Diamond92.7%Not measuredOnly Gemini 3.5 Flash measured
MMMU Pro (Vals AI)88.3%Not measuredOnly Gemini 3.5 Flash measured
GPQA Diamond (Artificial Analysis run)92.2%89.6%Gemini 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)42.7%35.0%Gemini 3.5 Flash
GPQA Diamond (Epoch AI run)92.8%87.9%Gemini 3.5 Flash
ARC-AGI92.5%Not measuredOnly Gemini 3.5 Flash measured
ARC-AGI-272.1%Not measuredOnly Gemini 3.5 Flash measured
SimpleBench76.7%57.9%Gemini 3.5 Flash
Chess puzzles45.0%14.0%Gemini 3.5 Flash
Mystery game puzzles32.0%Not measuredOnly Gemini 3.5 Flash measured
EBR-bench4.8%Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: hard prompts1488Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: expert1495Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: hard prompts in English1483Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision: diagrams1323Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision: homework1330Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Gemini 3.5 Flash and Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
OTIS Mock AIME95.6%95.6%Tie
FrontierMath, tiers 1 to 362.8%54.0%Gemini 3.5 Flash
FrontierMath, tier 426.8%12.2%Gemini 3.5 Flash
ProofBench31.0%Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: math1504Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: mathematical work1495Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for Gemini 3.5 Flash and Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
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%Not measuredOnly Gemini 3.5 Flash measured
SimpleQA Verified66.2%36.5%Gemini 3.5 Flash
LMArena Text: science1495Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: medicine and healthcare1483Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: legal and government1488Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: business and finance1467Not measuredOnly Gemini 3.5 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 index80
Web design benchmarks for Gemini 3.5 Flash and Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
Design Arena: websites12681264Gemini 3.5 Flash
Design Arena: UI components12721259Gemini 3.5 Flash
Design Arena: game dev12631220Gemini 3.5 Flash
Design Arena: data viz12361226Gemini 3.5 Flash
Design Arena: 3D12441241Gemini 3.5 Flash
Design Arena: all code categories12661253Gemini 3.5 Flash
Design Arena: SVG12541176Gemini 3.5 Flash
Design Arena: ASCII art12531196Gemini 3.5 Flash
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index21
General benchmarks for Gemini 3.5 Flash and Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
Public Benefits Bench (Vals AI)59.5%Not measuredOnly Gemini 3.5 Flash measured
SAGE (Vals AI)49.9%Not measuredOnly Gemini 3.5 Flash measured
MedScribe (Vals AI)76.6%Not measuredOnly Gemini 3.5 Flash measured
Vals Multimodal Index62.9%Not measuredOnly Gemini 3.5 Flash measured
IFBench76.3%63.1%Gemini 3.5 Flash
Long context reasoning (AA-LCR)74.3%79.3%Kimi K2.7 Code
DTBench94.7%Not measuredOnly Gemini 3.5 Flash measured
LMCA47.1%Not measuredOnly Gemini 3.5 Flash measured
Surface Evolver Bench58.1%48.8%Gemini 3.5 Flash
LMArena Text1482Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: instruction following1467Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: creative writing1470Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision1308Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: English1481Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: non-English1475Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: Chinese1527Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: German1494Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: Japanese1486Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: Korean1448Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: French1490Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: Spanish1480Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: Russian1493Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: Polish1516Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: multi-turn1481Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: longer queries1483Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: writing and language1478Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: entertainment and media1459Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision: English1305Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision: Chinese1377Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision: reading text1317Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision: humor1321Not measuredOnly Gemini 3.5 Flash measured
LMArena Vision: creative writing1301Not measuredOnly Gemini 3.5 Flash measured
LMArena Document1463Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 13 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 Kimi K2.7 Code
BenchmarkGemini 3.5 FlashKimi K2.7 CodeLeader
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
Kimi K2.7 Code$0.0023Fits in one request

Kimi K2.7 Code costs less

Repository review

50K input + 3K output tokens

Gemini 3.5 Flash$0.102Fits in one request
Kimi K2.7 Code$0.044Fits in one request

Kimi K2.7 Code costs less

Agent loop

200K input + 10K output tokens

Gemini 3.5 Flash$0.390Fits in one request
Kimi K2.7 Code$0.168Fits in one request

Kimi K2.7 Code 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 Kimi K2.7 Code
SpecificationGoogle Gemini 3.5 FlashMoonshotAI Kimi K2.7 Code
MakerGoogleMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedMay 19, 2026June 12, 2026
Context window1.05M262K
Input $/Mtok$1.50$0.6712
Output $/Mtok$9.00$3.35
Coding index42.839.1
Independent measurements behind it11
Cost per solved task$1.21$0.35
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.5 Flash better than Kimi K2.7 Code for coding?

Pick Gemini 3.5 Flash for coding: it scores 42.8 on the Vibe Coding Index against 39.1 for Kimi K2.7 Code. Pick Kimi K2.7 Code when output tokens cost 2.7x less, or when a solved task costs $0.35 against $1.21.

Which is cheaper, Gemini 3.5 Flash or Kimi K2.7 Code?

Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; Kimi K2.7 Code costs $0.6712 and $3.35. Per solved SWE-bench Verified task, Gemini 3.5 Flash costs $1.21 and Kimi K2.7 Code $0.35.

Which has the bigger context window, Gemini 3.5 Flash or Kimi K2.7 Code?

Gemini 3.5 Flash, with 1.05M tokens against 262K.

How many benchmarks is the Gemini 3.5 Flash vs Kimi K2.7 Code comparison based on?

48 benchmarks have a result for both models as of October 21, 2026. Gemini 3.5 Flash's coding index rests on 1 independent benchmark and Kimi K2.7 Code's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next