Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs Mistral Medium 3.5

Updated October 21, 2026. 54 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemma 4 31B Replace Mistral Medium 3.5
Gemma 4 31BGoogle
Coding
38.3
Overall
14.7
Output $/M
$0.40
49
Mistral Medium 3.5Mistral AI
Coding
9.2
Overall
14.2
Output $/M
$7.50
5
vs boards won of 54 shared

Decision reading

Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 9.2 for Mistral Medium 3.5.

Pick Mistral Medium 3.5 when what matters is AA Coding Index or LMArena Text: coding, where it leads.

Model AGemma 4 31BGoogle38.3/1002 independent benchmarksNo cost per solved taskModel BMistral Medium 3.5Mistral AI9.2/1001 independent benchmark$6.02 per solved task
Shared results
54
Gemma 4 31B only
14
Mistral Medium 3.5 only
26
Like-for-like categories
7 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
Gemma 4 31B 38.3 from 2 benchmarks, Mistral Medium 3.5 9.2 from 1 benchmark.
Widest category
Agentic work, 15.7 points apart on average over 2 shared benchmarks.
Widest single gap
MortgageTax (Vals AI): Gemma 4 31B 61.4% against Mistral Medium 3.5 28.9%, 32.5 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against Mistral Medium 3.5 $7.50 per million output tokens, 18.8x apart.
Context window
Both take 262K 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
CategoryGemma 4 31BBarsMistral Medium 3.5Ties
Coding72
Intelligence20
Agentic work02
Reasoning70
Math20
Knowledge60
General251
All shared boards495
CodingLike-for-likeFour of these boards feed the Vibe Coding Index72
Coding benchmarks for Gemma 4 31B and Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev13671264Gemma 4 31B
AA Coding Index43.446.9Mistral Medium 3.5
SWE-bench Verified (Vals AI)Not measured66.4%Only Mistral Medium 3.5 measured
Vibe Code Bench (Vals AI)Not measured2.9%Only Mistral Medium 3.5 measured
Code migration (Vals AI)Not measured5.1%Only Mistral Medium 3.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured39.0%Only Mistral Medium 3.5 measured
SciCode45.5%40.2%Gemma 4 31B
Terminal-Bench Hard (Artificial Analysis run)36.4%33.3%Gemma 4 31B
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5764.0Gemma 4 31B
LMArena Text: coding14591460Mistral Medium 3.5
LMArena Text: software and IT14631458Gemma 4 31B
LMArena WebDev: React13591254Gemma 4 31B
LMArena WebDev: HTML13801308Gemma 4 31B
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemma 4 31B and Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
AA Intelligence Index14.714.2Gemma 4 31B
Epoch Capabilities Index143.0141.4Gemma 4 31B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Gemma 4 31B and Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
AA Agentic Index4.27.0Mistral Medium 3.5
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 measured32.1%Only Mistral Medium 3.5 measured
Tax Agent Bench (Vals AI)Not measured4.5%Only Mistral Medium 3.5 measured
Legal Research Bench (Vals AI)Not measured9.1%Only Mistral Medium 3.5 measured
Excel Modeling Benchmark (Vals AI)Not measured11.2%Only Mistral Medium 3.5 measured
τ²-Bench Telecom65.5%94.2%Mistral Medium 3.5
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
Reasoning benchmarks for Gemma 4 31B and Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
GPQA DiamondNot measured34.9%Only Mistral Medium 3.5 measured
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
GPQA Diamond (Artificial Analysis run)85.7%74.8%Gemma 4 31B
Humanity's Last Exam (Artificial Analysis run)23.6%13.8%Gemma 4 31B
GPQA Diamond (Epoch AI run)75.8%Not measuredOnly Gemma 4 31B measured
LMArena Text: hard prompts14481436Gemma 4 31B
LMArena Text: expert14641432Gemma 4 31B
LMArena Text: hard prompts in English14561445Gemma 4 31B
LMArena Vision: diagrams12831254Gemma 4 31B
LMArena Vision: homework13101230Gemma 4 31B
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Gemma 4 31B and Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
OTIS Mock AIME73.3%Not measuredOnly Gemma 4 31B measured
ProofBenchNot measured9.0%Only Mistral Medium 3.5 measured
LMArena Text: math14631431Gemma 4 31B
LMArena Text: mathematical work14651440Gemma 4 31B
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Gemma 4 31B and Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
MMLU ProNot measured75.3%Only Mistral Medium 3.5 measured
CaseLaw (Vals AI)52.6%44.2%Gemma 4 31B
CorpFin (Vals AI)Not measured58.8%Only Mistral Medium 3.5 measured
TaxEval (Vals AI)Not measured68.0%Only Mistral Medium 3.5 measured
MortgageTax (Vals AI)61.4%28.9%Gemma 4 31B
MedCode (Vals AI)Not measured33.8%Only Mistral Medium 3.5 measured
SimpleQA Verified10.4%Not measuredOnly Gemma 4 31B measured
LMArena Text: science14571428Gemma 4 31B
LMArena Text: medicine and healthcare14511409Gemma 4 31B
LMArena Text: legal and government14381437Gemma 4 31B
LMArena Text: business and finance14301426Gemma 4 31B
Neither model has a result on the other 6 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 Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
Design Arena: websitesNot measured1142Only Mistral Medium 3.5 measured
Design Arena: UI componentsNot measured1079Only Mistral Medium 3.5 measured
Design Arena: game devNot measured1079Only Mistral Medium 3.5 measured
Design Arena: data vizNot measured1120Only Mistral Medium 3.5 measured
Design Arena: 3DNot measured1061Only Mistral Medium 3.5 measured
Design Arena: all code categoriesNot measured1122Only Mistral Medium 3.5 measured
Design Arena: SVGNot measured949Only Mistral Medium 3.5 measured
Design Arena: ASCII artNot measured1062Only Mistral Medium 3.5 measured
LiveBench design58.4%Not measuredOnly Gemma 4 31B measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index251
General benchmarks for Gemma 4 31B and Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%37.6%Gemma 4 31B
MedScribe (Vals AI)Not measured67.7%Only Mistral Medium 3.5 measured
Vals Multimodal IndexNot measured34.8%Only Mistral Medium 3.5 measured
IFBench75.6%68.8%Gemma 4 31B
Long context reasoning (AA-LCR)69.7%69.3%Gemma 4 31B
DTBench82.7%75.5%Gemma 4 31B
LMCA39.3%26.1%Gemma 4 31B
Surface Evolver Bench30.6%26.9%Gemma 4 31B
LMArena Text14431421Gemma 4 31B
LMArena Text: instruction following14331415Gemma 4 31B
LMArena Text: creative writing14171374Gemma 4 31B
LMArena Vision12761222Gemma 4 31B
LMArena Text: English14511433Gemma 4 31B
LMArena Text: non-English14301404Gemma 4 31B
LMArena Text: Chinese14751444Gemma 4 31B
LMArena Text: GermanNot measured1453Only Mistral Medium 3.5 measured
LMArena Text: KoreanNot measured1384Only Mistral Medium 3.5 measured
LMArena Text: French14361448Mistral Medium 3.5
LMArena Text: Spanish14421411Gemma 4 31B
LMArena Text: Russian14601395Gemma 4 31B
LMArena Text: Polish14331430Gemma 4 31B
LMArena Text: multi-turn14521423Gemma 4 31B
LMArena Text: longer queries14461415Gemma 4 31B
LMArena Text: writing and language14321384Gemma 4 31B
LMArena Text: entertainment and media14051382Gemma 4 31B
LMArena Vision: English12711240Gemma 4 31B
LMArena Vision: Chinese13261244Gemma 4 31B
LMArena Vision: reading text12821233Gemma 4 31B
LMArena Vision: humor12801216Gemma 4 31B
LMArena Vision: captioning1218Not measuredOnly Gemma 4 31B measured
LMArena Vision: recognizing things1226Not measuredOnly Gemma 4 31B measured
LMArena Vision: creative writing12851198Gemma 4 31B
LMArena Document1425Not measuredOnly Gemma 4 31B 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 Gemma 4 31B and Mistral Medium 3.5
BenchmarkGemma 4 31BMistral Medium 3.5Leader
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$0.0004Fits in one request
Mistral Medium 3.5$0.0053Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.011Fits in one request
Mistral Medium 3.5$0.098Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.044Fits in one request
Mistral Medium 3.5$0.375Fits 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 Mistral Medium 3.5
SpecificationGoogle Gemma 4 31BMistral Medium 3.5
MakerGoogleMistral AI
WeightsOpen weightsNo public weights listed
ReleasedApril 2, 2026April 30, 2026
Context window262K262K
Input $/Mtok$0.20$1.50
Output $/Mtok$0.40$7.50
Coding index38.39.2
Independent measurements behind it21
Cost per solved taskNot computable$6.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than Mistral Medium 3.5 for coding?

Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 9.2 for Mistral Medium 3.5. Pick Mistral Medium 3.5 when what matters is AA Coding Index or LMArena Text: coding, where it leads.

Which is cheaper, Gemma 4 31B or Mistral Medium 3.5?

Gemma 4 31B costs $0.20 per million input tokens and $0.40 per million output tokens; Mistral Medium 3.5 costs $1.50 and $7.50. Cost per solved task is known for Mistral Medium 3.5 only.

Which has the bigger context window, Gemma 4 31B or Mistral Medium 3.5?

Neither: both take 262K tokens.

How many benchmarks is the Gemma 4 31B vs Mistral Medium 3.5 comparison based on?

54 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and Mistral Medium 3.5's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next