Enter opens the highlighted result. Esc closes.

Gemma 3 27B vs Kimi K2.5

Kimi K2.5 leads Gemma 3 27B on the Artificial Analysis Intelligence Index, 23.5 to 4.9, and Gemma 3 27B costs 9.5x less per output token ($0.30 vs $2.85 per million). Updated October 21, 2026; 49 benchmarks have a result for both.

Replace Gemma 3 27B Replace Kimi K2.5
Gemma 3 27BGoogle
Coding
No data
Overall
31.4
Output $/M
$0.30
0
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
49
vs boards won of 49 shared

Gemma 3 27B or Kimi K2.5: which to pick

Only Kimi K2.5 has a coding score, 38.6 on the Vibe Coding Index; Gemma 3 27B has none, so the two cannot be ranked on coding.

Pick Gemma 3 27B for output tokens 9.5x cheaper ($0.30 vs $2.85 per million).

Model AGemma 3 27BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
49
Gemma 3 27B only
17
Kimi K2.5 only
50
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
Gemma 3 27B not benchmarked, Kimi K2.5 38.6 from 3 benchmarks.
Widest category
Agentic work, 85.4 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Gemma 3 27B 10.5% against Kimi K2.5 95.9%, 85.4 points apart on a 0 to 100 scale.
Output price
Gemma 3 27B $0.30 against Kimi K2.5 $2.85 per million output tokens, 9.5x apart.
Context window
Gemma 3 27B takes 131K tokens, Kimi K2.5 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
CategoryGemma 3 27BBarsKimi K2.5Ties
Coding04
Intelligence02
Agentic work01
Reasoning08
Math02
Knowledge04
General028
All shared boards049
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
Aider polyglot4.9%Not measuredOnly Gemma 3 27B measured
SWE-bench VerifiedNot measured70.8%Only Kimi K2.5 measured
SWE-bench MultilingualNot measured67.3%Only Kimi K2.5 measured
LMArena WebDevNot measured1437Only Kimi K2.5 measured
AA Coding Index10.146.8Kimi K2.5
LiveCodeBench (Vals AI)Not measured83.9%Only Kimi K2.5 measured
SWE-bench Verified (Vals AI)Not measured70.0%Only Kimi K2.5 measured
Vibe Code Bench (Vals AI)Not measured17.5%Only Kimi K2.5 measured
Code migration (Vals AI)Not measured7.0%Only Kimi K2.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured42.0%Only Kimi K2.5 measured
LiveCodeBench (Artificial Analysis run)13.7%Not measuredOnly Gemma 3 27B measured
SciCode23.3%Not measuredOnly Gemma 3 27B measured
Terminal-Bench Hard (Artificial Analysis run)3.8%34.8%Kimi K2.5
Terminal-BenchNot measured43.2%Only Kimi K2.5 measured
WeirdMLNot measured45.6%Only Kimi K2.5 measured
ALE-BenchNot measured821.6Only Kimi K2.5 measured
LMArena Text: coding13221483Kimi K2.5
LMArena Text: software and IT13541471Kimi K2.5
LMArena WebDev: ReactNot measured1429Only Kimi K2.5 measured
LMArena WebDev: HTMLNot measured1426Only Kimi K2.5 measured
LMArena WebDev: from an imageNot measured1439Only Kimi K2.5 measured
SciCode0.0%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
AA Intelligence Index4.923.5Kimi K2.5
Epoch Capabilities Index130.0148.1Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
AA Agentic Index0.1Not measuredOnly Gemma 3 27B measured
Design Arena: agents building web appsNot measured1136Only Kimi K2.5 measured
Design Arena: agents building full-stack appsNot measured1114Only Kimi K2.5 measured
Design Arena: agents building mobile appsNot measured1147Only Kimi K2.5 measured
Design Arena: agents building Android appsNot measured1118Only Kimi K2.5 measured
Design Arena: agents building Godot gamesNot measured1219Only Kimi K2.5 measured
Finance Agent (Vals AI)Not measured35.8%Only Kimi K2.5 measured
Legal Research Bench (Vals AI)Not measured15.9%Only Kimi K2.5 measured
Excel Modeling Benchmark (Vals AI)Not measured28.5%Only Kimi K2.5 measured
τ²-Bench Telecom10.5%95.9%Kimi K2.5
OSWorldNot measured63.3%Only Kimi K2.5 measured
Vending-Bench 2Not measured$1,198Only Kimi K2.5 measured
Berkeley Function Calling Leaderboard (BFCL)29.5%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
GPQA DiamondNot measured84.1%Only Kimi K2.5 measured
MMMU Pro (Vals AI)Not measured84.3%Only Kimi K2.5 measured
GPQA Diamond (Artificial Analysis run)42.8%87.9%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)4.4%30.7%Kimi K2.5
GPQA Diamond (Epoch AI run)47.7%Not measuredOnly Gemma 3 27B measured
ARC-AGINot measured65.3%Only Kimi K2.5 measured
ARC-AGI-2Not measured11.8%Only Kimi K2.5 measured
SimpleBenchNot measured46.8%Only Kimi K2.5 measured
LMArena Text: hard prompts13401453Kimi K2.5
LMArena Text: expert13041466Kimi K2.5
LMArena Text: hard prompts in English13531460Kimi K2.5
LMArena Vision: diagrams11561282Kimi K2.5
LMArena Vision: homework11601297Kimi K2.5
Kagi LLM Benchmark35.1%78.5%Kimi K2.5
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
AIMENot measured95.6%Only Kimi K2.5 measured
AA Math Index20.7Not measuredOnly Gemma 3 27B measured
AIME 2025 (Artificial Analysis run)20.7%Not measuredOnly Gemma 3 27B measured
OTIS Mock AIME22.5%Not measuredOnly Gemma 3 27B measured
MATH level 574.0%Not measuredOnly Gemma 3 27B measured
LMArena Text: math13121470Kimi K2.5
LMArena Text: mathematical work13271473Kimi K2.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
MMLU ProNot measured85.9%Only Kimi K2.5 measured
CaseLaw (Vals AI)Not measured58.7%Only Kimi K2.5 measured
CorpFin (Vals AI)Not measured68.3%Only Kimi K2.5 measured
TaxEval (Vals AI)Not measured74.2%Only Kimi K2.5 measured
MortgageTax (Vals AI)Not measured66.5%Only Kimi K2.5 measured
MedQA (Vals AI)Not measured94.4%Only Kimi K2.5 measured
MedCode (Vals AI)Not measured39.3%Only Kimi K2.5 measured
MMLU Pro (Artificial Analysis run)66.9%Not measuredOnly Gemma 3 27B measured
SimpleQA VerifiedNot measured34.3%Only Kimi K2.5 measured
GeoBench52.0%Not measuredOnly Gemma 3 27B measured
LMArena Text: science13831459Kimi K2.5
LMArena Text: medicine and healthcare13911448Kimi K2.5
LMArena Text: legal and government13751441Kimi K2.5
LMArena Text: business and finance13601427Kimi K2.5
FACTS Benchmark Suite29.1%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 3 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
Design Arena: websitesNot measured1248Only Kimi K2.5 measured
Design Arena: UI componentsNot measured1236Only Kimi K2.5 measured
Design Arena: game devNot measured1207Only Kimi K2.5 measured
Design Arena: data vizNot measured1219Only Kimi K2.5 measured
Design Arena: 3DNot measured1205Only Kimi K2.5 measured
Design Arena: all code categoriesNot measured1236Only Kimi K2.5 measured
Design Arena: SVGNot measured1149Only Kimi K2.5 measured
Design Arena: ASCII artNot measured1166Only Kimi K2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index028
General benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
SAGE (Vals AI)Not measured49.9%Only Kimi K2.5 measured
MedScribe (Vals AI)Not measured76.4%Only Kimi K2.5 measured
IFBench31.8%70.2%Kimi K2.5
Long context reasoning (AA-LCR)7.3%78.0%Kimi K2.5
DTBench52.5%Not measuredOnly Gemma 3 27B measured
LMCA12.3%Not measuredOnly Gemma 3 27B measured
Fiction.LiveBench33.3%86.1%Kimi K2.5
Creative writing (Lech Mazur)79.9%Not measuredOnly Gemma 3 27B measured
CL-benchNot measured19.3%Only Kimi K2.5 measured
CL-bench LifeNot measured13.2%Only Kimi K2.5 measured
LMArena Text13581445Kimi K2.5
LMArena Text: instruction following13211431Kimi K2.5
LMArena Text: creative writing13451422Kimi K2.5
LMArena Vision11651269Kimi K2.5
LMArena Text: English13771453Kimi K2.5
LMArena Text: non-English13341433Kimi K2.5
LMArena Text: Chinese13461494Kimi K2.5
LMArena Text: German13621441Kimi K2.5
LMArena Text: Japanese12871423Kimi K2.5
LMArena Text: Korean13081412Kimi K2.5
LMArena Text: French13681454Kimi K2.5
LMArena Text: Spanish13491450Kimi K2.5
LMArena Text: Russian13491435Kimi K2.5
LMArena Text: Polish13451445Kimi K2.5
LMArena Text: multi-turn13451444Kimi K2.5
LMArena Text: longer queries13331445Kimi K2.5
LMArena Text: writing and language13471425Kimi K2.5
LMArena Text: entertainment and media13201417Kimi K2.5
LMArena Vision: English11881274Kimi K2.5
LMArena Vision: Chinese11641328Kimi K2.5
LMArena Vision: reading text11561276Kimi K2.5
LMArena Vision: humor11661284Kimi K2.5
LMArena Vision: captioning11511257Kimi K2.5
LMArena Vision: recognizing things11961285Kimi K2.5
LMArena Vision: creative writing11771269Kimi K2.5
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 3 27B and Kimi K2.5
BenchmarkGemma 3 27BKimi K2.5Leader
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

Gemma 3 27B$0.0002Fits in one request
Kimi K2.5$0.0020Fits in one request

Gemma 3 27B costs less

Repository review

50K input + 3K output tokens

Gemma 3 27B$0.0049Fits in one request
Kimi K2.5$0.035Fits in one request

Gemma 3 27B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 27B$0.019Exceeds the context window
Kimi K2.5$0.135Fits in one request

Gemma 3 27B 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 Gemma 3 27B and Kimi K2.5
SpecificationGoogle Gemma 3 27BMoonshotAI Kimi K2.5
MakerGoogleMoonshot AI
WeightsOpen weightsOpen weights
ReleasedMarch 12, 2025January 27, 2026
Context window131K262K
Input $/Mtok$0.08$0.532
Output $/Mtok$0.30$2.85
Coding indexNot benchmarked38.6
Independent measurements behind it03
Cost per solved taskNot computable$0.24
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 27B better than Kimi K2.5 for coding?

Only Kimi K2.5 has a coding score, 38.6 on the Vibe Coding Index; Gemma 3 27B has none, so the two cannot be ranked on coding. Pick Gemma 3 27B for output tokens 9.5x cheaper ($0.30 vs $2.85 per million).

Which is cheaper, Gemma 3 27B or Kimi K2.5?

Gemma 3 27B costs $0.08 per million input tokens and $0.30 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Cost per solved task is known for Kimi K2.5 only.

Which has the bigger context window, Gemma 3 27B or Kimi K2.5?

Kimi K2.5, with 262K tokens against 131K.

How many benchmarks is the Gemma 3 27B vs Kimi K2.5 comparison based on?

49 benchmarks have a result for both models as of October 21, 2026. Gemma 3 27B's coding index rests on 0 independent benchmarks and Kimi K2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next