Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs MiMo-V2.5

MiMo-V2.5 leads Gemma 4 31B on coding, 50.0 to 39.0 on the Vibe Coding Index, at about the same output price ($0.336 vs $0.40 per million). Updated October 22, 2026; 50 benchmarks have a result for both.

Replace Gemma 4 31B Replace MiMo-V2.5
Gemma 4 31BGoogle
Coding
39.0
Overall
42.1
Output $/M
$0.40
34
MiMo-V2.5Xiaomi
Coding
50.0
Overall
50.7
Output $/M
$0.336
16
vs boards won of 50 shared

Gemma 4 31B or MiMo-V2.5: which to pick

Pick MiMo-V2.5 for coding: it scores 50.0 on the Vibe Coding Index against 39.0 for Gemma 4 31B.

Pick Gemma 4 31B for work measured by SciCode or ALE-Bench, where it leads.

Model AGemma 4 31BGoogle39.0/1002 independent benchmarksNo cost per solved taskModel BMiMo-V2.5Xiaomi50.0/1003 independent benchmarks$0.01 per solved task
Shared results
50
Gemma 4 31B only
21
MiMo-V2.5 only
30
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 4 31B 39.0 from 2 benchmarks, MiMo-V2.5 50.0 from 3 benchmarks.
Widest category
Agentic work, 18.4 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Gemma 4 31B 65.5% against MiMo-V2.5 90.6%, 25.1 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against MiMo-V2.5 $0.336 per million output tokens, 1.2x apart.
Context window
Gemma 4 31B takes 262K 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 4 31BBarsMiMo-V2.5Ties
Coding36
Intelligence01
Agentic work02
Reasoning43
Math20
Knowledge41
General213
All shared boards3416
CodingLike-for-likeSix of these boards feed the Vibe Coding Index36
Coding benchmarks for Gemma 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-V2.5Leader
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev13671438MiMo-V2.5
AA Coding Index43.456.8MiMo-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
SciCode45.5%43.9%Gemma 4 31B
Terminal-Bench Hard (Artificial Analysis run)36.4%41.7%MiMo-V2.5
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5514.0Gemma 4 31B
LMArena Text: coding14591469MiMo-V2.5
LMArena Text: software and IT14631463Gemma 4 31B
LMArena WebDev: React13591425MiMo-V2.5
LMArena WebDev: HTML13801429MiMo-V2.5
SciCode8.9%Not measuredOnly Gemma 4 31B 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 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-V2.5Leader
AA Intelligence Index14.721.8MiMo-V2.5
Epoch Capabilities Index143.0Not measuredOnly Gemma 4 31B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Gemma 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-V2.5Leader
AA Agentic Index4.215.8MiMo-V2.5
LiveBench research44.4%Not measuredOnly Gemma 4 31B measured
LiveBench browser4.0%Not measuredOnly Gemma 4 31B measured
LiveBench long agentic13.3%Not measuredOnly Gemma 4 31B measured
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 Telecom65.5%90.6%MiMo-V2.5
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index43
Reasoning benchmarks for Gemma 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-V2.5Leader
GPQA DiamondNot measured81.6%Only MiMo-V2.5 measured
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
MMMU Pro (Vals AI)Not measured80.0%Only MiMo-V2.5 measured
GPQA Diamond (Artificial Analysis run)85.7%84.9%Gemma 4 31B
Humanity's Last Exam (Artificial Analysis run)23.6%27.2%MiMo-V2.5
GPQA Diamond (Epoch AI run)75.8%Not measuredOnly Gemma 4 31B measured
LMArena Text: hard prompts14481450MiMo-V2.5
LMArena Text: expert14641459Gemma 4 31B
LMArena Text: hard prompts in English14561461MiMo-V2.5
LMArena Vision: diagrams12831269Gemma 4 31B
LMArena Vision: homework13101262Gemma 4 31B
Kagi LLM Benchmark63.5%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Gemma 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-V2.5Leader
OTIS Mock AIME73.3%Not measuredOnly Gemma 4 31B measured
ProofBenchNot measured16.0%Only MiMo-V2.5 measured
LMArena Text: math14631436Gemma 4 31B
LMArena Text: mathematical work14651451Gemma 4 31B
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
Knowledge benchmarks for Gemma 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-V2.5Leader
MMLU ProNot measured82.9%Only MiMo-V2.5 measured
LegalBench (Vals AI)Not measured78.9%Only MiMo-V2.5 measured
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B 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)61.4%59.3%Gemma 4 31B
MedCode (Vals AI)Not measured31.9%Only MiMo-V2.5 measured
SimpleQA Verified10.4%Not measuredOnly Gemma 4 31B measured
LMArena Text: science14571440Gemma 4 31B
LMArena Text: medicine and healthcare14511432Gemma 4 31B
LMArena Text: legal and government14381425Gemma 4 31B
LMArena Text: business and finance14301432MiMo-V2.5
FACTS Benchmark Suite45.3%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Gemma 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-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
LiveBench design58.4%Not measuredOnly Gemma 4 31B measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index213
General benchmarks for Gemma 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-V2.5Leader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%43.3%Gemma 4 31B
MedScribe (Vals AI)Not measured72.2%Only MiMo-V2.5 measured
Vals Multimodal IndexNot measured52.8%Only MiMo-V2.5 measured
IFBench75.6%67.1%Gemma 4 31B
Long context reasoning (AA-LCR)69.7%73.0%MiMo-V2.5
DTBench82.7%Not measuredOnly Gemma 4 31B measured
LMCA39.3%Not measuredOnly Gemma 4 31B measured
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
LMArena Text14431428Gemma 4 31B
LMArena Text: instruction following14331435MiMo-V2.5
LMArena Text: creative writing14171393Gemma 4 31B
LMArena Vision12761247Gemma 4 31B
LMArena Text: English14511447Gemma 4 31B
LMArena Text: non-English14301405Gemma 4 31B
LMArena Text: Chinese14751469Gemma 4 31B
LMArena Text: GermanNot measured1421Only MiMo-V2.5 measured
LMArena Text: JapaneseNot measured1306Only MiMo-V2.5 measured
LMArena Text: KoreanNot measured1361Only MiMo-V2.5 measured
LMArena Text: French14361448MiMo-V2.5
LMArena Text: Spanish14421414Gemma 4 31B
LMArena Text: Russian14601396Gemma 4 31B
LMArena Text: Polish14331413Gemma 4 31B
LMArena Text: multi-turn14521445Gemma 4 31B
LMArena Text: longer queries14461445Gemma 4 31B
LMArena Text: writing and language14321409Gemma 4 31B
LMArena Text: entertainment and media14051399Gemma 4 31B
LMArena Vision: English12711259Gemma 4 31B
LMArena Vision: Chinese13261326Gemma 4 31B
LMArena Vision: reading text12821256Gemma 4 31B
LMArena Vision: humor12801226Gemma 4 31B
LMArena Vision: captioning1218Not measuredOnly Gemma 4 31B measured
LMArena Vision: recognizing things12261189Gemma 4 31B
LMArena Vision: creative writing12851230Gemma 4 31B
LMArena Document1425Not measuredOnly Gemma 4 31B measured
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 4 31B and MiMo-V2.5
BenchmarkGemma 4 31BMiMo-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 4 31B$0.0003Fits in one request
MiMo-V2.5$0.0003Fits in one request

MiMo-V2.5 costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.0082Fits in one request
MiMo-V2.5$0.0094Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.032Fits in one request
MiMo-V2.5$0.037Fits in one request

Gemma 4 31B 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 4 31B and MiMo-V2.5
SpecificationGoogle Gemma 4 31BXiaomi MiMo-V2.5
MakerGoogleXiaomi
WeightsOpen weightsOpen weights
ReleasedApril 2, 2026April 22, 2026
Context window262K1.05M
Input $/Mtok$0.14$0.168
Output $/Mtok$0.40$0.336
Coding index39.050.0
Independent measurements behind it23
Cost per solved taskNot computable$0.01
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than MiMo-V2.5 for coding?

Pick MiMo-V2.5 for coding: it scores 50.0 on the Vibe Coding Index against 39.0 for Gemma 4 31B. Pick Gemma 4 31B for work measured by SciCode or ALE-Bench, where it leads.

Which is cheaper, Gemma 4 31B or MiMo-V2.5?

Gemma 4 31B costs $0.14 per million input tokens and $0.40 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 4 31B or MiMo-V2.5?

MiMo-V2.5, with 1.05M tokens against 262K.

How many benchmarks is the Gemma 4 31B vs MiMo-V2.5 comparison based on?

50 benchmarks have a result for both models as of October 22, 2026. Gemma 4 31B's coding index rests on 2 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

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/gemma-4-31b-it-vs-xiaomi-mimo-v2-5" title="Gemma 4 31B vs MiMo-V2.5, 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/gemma-4-31b-it-vs-xiaomi-mimo-v2-5">LLMBenchmark.ai, Gemma 4 31B vs MiMo-V2.5</a></p>