Enter opens the highlighted result. Esc closes.

Gemma 3 27B vs MiMo-V2.5

MiMo-V2.5 leads Gemma 3 27B on the Artificial Analysis Intelligence Index, 21.8 to 4.9, at about the same output price ($0.336 vs $0.30 per million). Updated October 22, 2026; 47 benchmarks have a result for both.

Replace Gemma 3 27B Replace MiMo-V2.5
Gemma 3 27BGoogle
Coding
No data
Overall
31.4
Output $/M
$0.30
1
MiMo-V2.5Xiaomi
Coding
50.0
Overall
50.7
Output $/M
$0.336
46
vs boards won of 47 shared

Gemma 3 27B or MiMo-V2.5: which to pick

Only MiMo-V2.5 has a coding score, 50.0 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 1.1x cheaper ($0.30 vs $0.336 per million) and work measured by LMArena Vision: recognizing things, where it leads.

Model AGemma 3 27BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMiMo-V2.5Xiaomi50.0/1003 independent benchmarks$0.01 per solved task
Shared results
47
Gemma 3 27B only
19
MiMo-V2.5 only
33
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, MiMo-V2.5 50.0 from 3 benchmarks.
Widest category
Agentic work, 47.9 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Gemma 3 27B 10.5% against MiMo-V2.5 90.6%, 80.1 points apart on a 0 to 100 scale.
Output price
Gemma 3 27B $0.30 against MiMo-V2.5 $0.336 per million output tokens, 1.1x apart.
Context window
Gemma 3 27B takes 131K tokens, MiMo-V2.5 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
CategoryGemma 3 27BBarsMiMo-V2.5Ties
Coding05
Intelligence01
Agentic work02
Reasoning07
Math02
Knowledge04
General125
All shared boards146
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
Coding benchmarks for Gemma 3 27B and MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
Aider polyglot4.9%Not measuredOnly Gemma 3 27B measured
LMArena WebDevNot measured1438Only MiMo-V2.5 measured
AA Coding Index10.156.8MiMo-V2.5
LiveCodeBench (Vals AI)Not measured81.5%Only MiMo-V2.5 measured
SWE-bench Verified (Vals AI)Not measured71.0%Only MiMo-V2.5 measured
Vibe Code Bench (Vals AI)Not measured42.2%Only MiMo-V2.5 measured
Code migration (Vals AI)Not measured14.2%Only MiMo-V2.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured60.7%Only MiMo-V2.5 measured
LiveCodeBench (Artificial Analysis run)13.7%Not measuredOnly Gemma 3 27B measured
SciCode23.3%43.9%MiMo-V2.5
Terminal-Bench Hard (Artificial Analysis run)3.8%41.7%MiMo-V2.5
ALE-BenchNot measured514.0Only MiMo-V2.5 measured
LMArena Text: coding13221469MiMo-V2.5
LMArena Text: software and IT13541463MiMo-V2.5
LMArena WebDev: ReactNot measured1425Only MiMo-V2.5 measured
LMArena WebDev: HTMLNot measured1429Only MiMo-V2.5 measured
SciCode0.0%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 3 27B and MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
AA Intelligence Index4.921.8MiMo-V2.5
Epoch Capabilities Index130.0Not measuredOnly Gemma 3 27B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Gemma 3 27B and MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
AA Agentic Index0.115.8MiMo-V2.5
Finance Agent (Vals AI)Not measured36.7%Only MiMo-V2.5 measured
Tax Agent Bench (Vals AI)Not measured7.8%Only MiMo-V2.5 measured
Legal Research Bench (Vals AI)Not measured9.1%Only MiMo-V2.5 measured
Excel Modeling Benchmark (Vals AI)Not measured55.1%Only MiMo-V2.5 measured
τ²-Bench Telecom10.5%90.6%MiMo-V2.5
Berkeley Function Calling Leaderboard (BFCL)29.5%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for Gemma 3 27B and MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
GPQA DiamondNot measured81.6%Only MiMo-V2.5 measured
MMMU Pro (Vals AI)Not measured80.0%Only MiMo-V2.5 measured
GPQA Diamond (Artificial Analysis run)42.8%84.9%MiMo-V2.5
Humanity's Last Exam (Artificial Analysis run)4.4%27.2%MiMo-V2.5
GPQA Diamond (Epoch AI run)47.7%Not measuredOnly Gemma 3 27B measured
LMArena Text: hard prompts13401450MiMo-V2.5
LMArena Text: expert13041459MiMo-V2.5
LMArena Text: hard prompts in English13531461MiMo-V2.5
LMArena Vision: diagrams11561269MiMo-V2.5
LMArena Vision: homework11601262MiMo-V2.5
Kagi LLM Benchmark35.1%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Gemma 3 27B and MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
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
ProofBenchNot measured16.0%Only MiMo-V2.5 measured
MATH level 574.0%Not measuredOnly Gemma 3 27B measured
LMArena Text: math13121436MiMo-V2.5
LMArena Text: mathematical work13271451MiMo-V2.5
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 MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
MMLU ProNot measured82.9%Only MiMo-V2.5 measured
LegalBench (Vals AI)Not measured78.9%Only MiMo-V2.5 measured
CorpFin (Vals AI)Not measured59.9%Only MiMo-V2.5 measured
TaxEval (Vals AI)Not measured71.8%Only MiMo-V2.5 measured
MortgageTax (Vals AI)Not measured59.3%Only MiMo-V2.5 measured
MedCode (Vals AI)Not measured31.9%Only MiMo-V2.5 measured
MMLU Pro (Artificial Analysis run)66.9%Not measuredOnly Gemma 3 27B measured
GeoBench52.0%Not measuredOnly Gemma 3 27B measured
LMArena Text: science13831440MiMo-V2.5
LMArena Text: medicine and healthcare13911432MiMo-V2.5
LMArena Text: legal and government13751425MiMo-V2.5
LMArena Text: business and finance13601432MiMo-V2.5
FACTS Benchmark Suite29.1%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 5 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 MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
Design Arena: websitesNot measured1265Only MiMo-V2.5 measured
Design Arena: UI componentsNot measured1255Only MiMo-V2.5 measured
Design Arena: game devNot measured1249Only MiMo-V2.5 measured
Design Arena: data vizNot measured1250Only MiMo-V2.5 measured
Design Arena: 3DNot measured1215Only MiMo-V2.5 measured
Design Arena: all code categoriesNot measured1260Only MiMo-V2.5 measured
Design Arena: SVGNot measured1179Only MiMo-V2.5 measured
Design Arena: ASCII artNot measured1140Only MiMo-V2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index125
General benchmarks for Gemma 3 27B and MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
SAGE (Vals AI)Not measured43.3%Only MiMo-V2.5 measured
MedScribe (Vals AI)Not measured72.2%Only MiMo-V2.5 measured
Vals Multimodal IndexNot measured52.8%Only MiMo-V2.5 measured
IFBench31.8%67.1%MiMo-V2.5
Long context reasoning (AA-LCR)7.3%73.0%MiMo-V2.5
DTBench52.5%Not measuredOnly Gemma 3 27B measured
LMCA12.3%Not measuredOnly Gemma 3 27B measured
Fiction.LiveBench33.3%Not measuredOnly Gemma 3 27B measured
Creative writing (Lech Mazur)79.9%Not measuredOnly Gemma 3 27B measured
LMArena Text13581428MiMo-V2.5
LMArena Text: instruction following13211435MiMo-V2.5
LMArena Text: creative writing13451393MiMo-V2.5
LMArena Vision11651247MiMo-V2.5
LMArena Text: English13771447MiMo-V2.5
LMArena Text: non-English13341405MiMo-V2.5
LMArena Text: Chinese13461469MiMo-V2.5
LMArena Text: German13621421MiMo-V2.5
LMArena Text: Japanese12871306MiMo-V2.5
LMArena Text: Korean13081361MiMo-V2.5
LMArena Text: French13681448MiMo-V2.5
LMArena Text: Spanish13491414MiMo-V2.5
LMArena Text: Russian13491396MiMo-V2.5
LMArena Text: Polish13451413MiMo-V2.5
LMArena Text: multi-turn13451445MiMo-V2.5
LMArena Text: longer queries13331445MiMo-V2.5
LMArena Text: writing and language13471409MiMo-V2.5
LMArena Text: entertainment and media13201399MiMo-V2.5
LMArena Vision: English11881259MiMo-V2.5
LMArena Vision: Chinese11641326MiMo-V2.5
LMArena Vision: reading text11561256MiMo-V2.5
LMArena Vision: humor11661226MiMo-V2.5
LMArena Vision: captioning1151Not measuredOnly Gemma 3 27B measured
LMArena Vision: recognizing things11961189Gemma 3 27B
LMArena Vision: creative writing11771230MiMo-V2.5
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 Gemma 3 27B and MiMo-V2.5
BenchmarkGemma 3 27BMiMo-V2.5Leader
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
MiMo-V2.5$0.0003Fits in one request

Gemma 3 27B costs less

Repository review

50K input + 3K output tokens

Gemma 3 27B$0.0049Fits in one request
MiMo-V2.5$0.0094Fits in one request

Gemma 3 27B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 27B$0.019Exceeds the context window
MiMo-V2.5$0.037Fits 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 MiMo-V2.5
SpecificationGoogle Gemma 3 27BXiaomi MiMo-V2.5
MakerGoogleXiaomi
WeightsOpen weightsOpen weights
ReleasedMarch 12, 2025April 22, 2026
Context window131K1.05M
Input $/Mtok$0.08$0.168
Output $/Mtok$0.30$0.336
Coding indexNot benchmarked50.0
Independent measurements behind it03
Cost per solved taskNot computable$0.01
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 27B better than MiMo-V2.5 for coding?

Only MiMo-V2.5 has a coding score, 50.0 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 1.1x cheaper ($0.30 vs $0.336 per million) and work measured by LMArena Vision: recognizing things, where it leads.

Which is cheaper, Gemma 3 27B or MiMo-V2.5?

Gemma 3 27B costs $0.08 per million input tokens and $0.30 per million output tokens; MiMo-V2.5 costs $0.168 and $0.336. Cost per solved task is known for MiMo-V2.5 only.

Which has the bigger context window, Gemma 3 27B or MiMo-V2.5?

MiMo-V2.5, with 1.05M tokens against 131K.

How many benchmarks is the Gemma 3 27B vs MiMo-V2.5 comparison based on?

47 benchmarks have a result for both models as of October 22, 2026. Gemma 3 27B's coding index rests on 0 independent benchmarks and MiMo-V2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next