LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs Qwen3.5-35B-A3B

Updated October 21, 2026. 41 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 Qwen3.5-35B-A3B
Gemma 4 31BGoogle
Coding
38.3
Overall
14.7
Output $/M
$0.40
37
Qwen3.5-35B-A3BQwen
Coding
7.7
Overall
19.3
Output $/M
$1.00
4
vs boards won of 41 shared

Decision reading

Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 7.7 for Qwen3.5-35B-A3B.

Pick Qwen3.5-35B-A3B when what matters is AA Intelligence Index or τ²-Bench Telecom, where it leads.

Model AGemma 4 31BGoogle38.3/1002 independent benchmarksNo cost per solved taskModel BQwen3.5-35B-A3BQwen7.7/1001 independent benchmarkNo cost per solved task
Shared results
41
Gemma 4 31B only
27
Qwen3.5-35B-A3B only
4
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, Qwen3.5-35B-A3B 7.7 from 1 benchmark.
Widest category
Agentic work, 23.7 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Gemma 4 31B 65.5% against Qwen3.5-35B-A3B 89.2%, 23.7 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against Qwen3.5-35B-A3B $1.00 per million output tokens, 2.5x 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 31BBarsQwen3.5-35B-A3BTies
Coding70
Intelligence11
Agentic work01
Reasoning51
Math30
Knowledge40
General171
All shared boards374
CodingLike-for-likeFour of these boards feed the Vibe Coding Index70
Coding benchmarks for Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev13671254Gemma 4 31B
AA Coding Index43.4Not measuredOnly Gemma 4 31B measured
SciCode45.5%Not measuredOnly Gemma 4 31B measured
Terminal-Bench Hard (Artificial Analysis run)36.4%26.5%Gemma 4 31B
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5221.8Gemma 4 31B
LMArena Text: coding14591410Gemma 4 31B
LMArena Text: software and IT14631415Gemma 4 31B
LMArena WebDev: React13591238Gemma 4 31B
LMArena WebDev: HTML13801301Gemma 4 31B
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
AA Intelligence Index14.719.3Qwen3.5-35B-A3B
Epoch Capabilities Index143.0142.5Gemma 4 31B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
AA Agentic Index4.2Not measuredOnly Gemma 4 31B measured
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
τ²-Bench Telecom65.5%89.2%Qwen3.5-35B-A3B
Vending-Bench 2Not measured$463Only Qwen3.5-35B-A3B measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
Reasoning benchmarks for Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
GPQA Diamond (Artificial Analysis run)85.7%84.5%Gemma 4 31B
Humanity's Last Exam (Artificial Analysis run)23.6%21.0%Gemma 4 31B
GPQA Diamond (Epoch AI run)75.8%83.5%Qwen3.5-35B-A3B
LMArena Text: hard prompts14481400Gemma 4 31B
LMArena Text: expert14641408Gemma 4 31B
LMArena Text: hard prompts in English14561411Gemma 4 31B
LMArena Vision: diagrams1283Not measuredOnly Gemma 4 31B measured
LMArena Vision: homework1310Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
OTIS Mock AIME73.3%70.0%Gemma 4 31B
LMArena Text: math14631404Gemma 4 31B
LMArena Text: mathematical work14651410Gemma 4 31B
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B measured
MortgageTax (Vals AI)61.4%Not measuredOnly Gemma 4 31B measured
SimpleQA Verified10.4%Not measuredOnly Gemma 4 31B measured
LMArena Text: science14571413Gemma 4 31B
LMArena Text: medicine and healthcare14511421Gemma 4 31B
LMArena Text: legal and government14381399Gemma 4 31B
LMArena Text: business and finance14301394Gemma 4 31B
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Web design benchmarks for Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
LiveBench design58.4%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 8 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index171
General benchmarks for Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%Not measuredOnly Gemma 4 31B measured
IFBench75.6%72.5%Gemma 4 31B
Long context reasoning (AA-LCR)69.7%72.0%Qwen3.5-35B-A3B
DTBench82.7%80.0%Gemma 4 31B
LMCA39.3%29.5%Gemma 4 31B
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
LMArena Text14431395Gemma 4 31B
LMArena Text: instruction following14331379Gemma 4 31B
LMArena Text: creative writing14171347Gemma 4 31B
LMArena Vision1276Not measuredOnly Gemma 4 31B measured
LMArena Text: English14511407Gemma 4 31B
LMArena Text: non-English14301378Gemma 4 31B
LMArena Text: Chinese14751457Gemma 4 31B
LMArena Text: GermanNot measured1367Only Qwen3.5-35B-A3B measured
LMArena Text: JapaneseNot measured1326Only Qwen3.5-35B-A3B measured
LMArena Text: KoreanNot measured1355Only Qwen3.5-35B-A3B measured
LMArena Text: French14361412Gemma 4 31B
LMArena Text: Spanish14421390Gemma 4 31B
LMArena Text: Russian14601376Gemma 4 31B
LMArena Text: Polish14331385Gemma 4 31B
LMArena Text: multi-turn14521390Gemma 4 31B
LMArena Text: longer queries14461389Gemma 4 31B
LMArena Text: writing and language14321365Gemma 4 31B
LMArena Text: entertainment and media14051347Gemma 4 31B
LMArena Vision: English1271Not measuredOnly Gemma 4 31B measured
LMArena Vision: Chinese1326Not measuredOnly Gemma 4 31B measured
LMArena Vision: reading text1282Not measuredOnly Gemma 4 31B measured
LMArena Vision: humor1280Not measuredOnly Gemma 4 31B measured
LMArena Vision: captioning1218Not measuredOnly Gemma 4 31B measured
LMArena Vision: recognizing things1226Not measuredOnly Gemma 4 31B measured
LMArena Vision: creative writing1285Not measuredOnly Gemma 4 31B measured
LMArena Document1425Not measuredOnly Gemma 4 31B 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 Gemma 4 31B and Qwen3.5-35B-A3B
BenchmarkGemma 4 31BQwen3.5-35B-A3BLeader
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
Qwen3.5-35B-A3B$0.0006Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.011Fits in one request
Qwen3.5-35B-A3B$0.010Fits in one request

Qwen3.5-35B-A3B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.044Fits in one request
Qwen3.5-35B-A3B$0.038Fits in one request

Qwen3.5-35B-A3B 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 Qwen3.5-35B-A3B
SpecificationGoogle Gemma 4 31BQwen3.5-35B-A3B
MakerGoogleQwen
WeightsOpen weightsOpen weights
ReleasedApril 2, 2026February 25, 2026
Context window262K262K
Input $/Mtok$0.20$0.14
Output $/Mtok$0.40$1.00
Coding index38.37.7
Independent measurements behind it21
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than Qwen3.5-35B-A3B for coding?

Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 7.7 for Qwen3.5-35B-A3B. Pick Qwen3.5-35B-A3B when what matters is AA Intelligence Index or τ²-Bench Telecom, where it leads.

Which is cheaper, Gemma 4 31B or Qwen3.5-35B-A3B?

Gemma 4 31B costs $0.20 per million input tokens and $0.40 per million output tokens; Qwen3.5-35B-A3B costs $0.14 and $1.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 4 31B or Qwen3.5-35B-A3B?

Neither: both take 262K tokens.

How many benchmarks is the Gemma 4 31B vs Qwen3.5-35B-A3B comparison based on?

41 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and Qwen3.5-35B-A3B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next