LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs GLM 4.7

Updated October 21, 2026. 42 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 GLM 4.7
Gemma 4 31BGoogle
Coding
38.3
Overall
14.7
Output $/M
$0.40
22
GLM 4.7Z.ai
Coding
33.6
Overall
22.2
Output $/M
$1.98
20
vs boards won of 42 shared

Decision reading

Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 33.6 for GLM 4.7.

Pick GLM 4.7 when what matters is LMArena WebDev or AA Coding Index, where it leads.

Model AGemma 4 31BGoogle38.3/1002 independent benchmarksNo cost per solved taskModel BGLM 4.7Z.ai33.6/1001 independent benchmark$0.29 per solved task
Shared results
42
Gemma 4 31B only
26
GLM 4.7 only
38
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, GLM 4.7 33.6 from 1 benchmark.
Widest category
Agentic work, 30.4 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Gemma 4 31B 65.5% against GLM 4.7 95.9%, 30.4 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against GLM 4.7 $1.98 per million output tokens, 4.9x apart.
Context window
Gemma 4 31B takes 262K tokens, GLM 4.7 205K.

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 31BBarsGLM 4.7Ties
Coding44
Intelligence02
Agentic work01
Reasoning33
Math21
Knowledge15
General124
All shared boards2220
CodingLike-for-likeFour of these boards feed the Vibe Coding Index44
Coding benchmarks for Gemma 4 31B and GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev13671435GLM 4.7
AA Coding Index43.445.3GLM 4.7
LiveCodeBench (Vals AI)Not measured82.2%Only GLM 4.7 measured
SWE-bench Verified (Vals AI)Not measured69.4%Only GLM 4.7 measured
LiveCodeBench (Artificial Analysis run)Not measured89.4%Only GLM 4.7 measured
SciCode45.5%Not measuredOnly Gemma 4 31B measured
Terminal-Bench Hard (Artificial Analysis run)36.4%31.8%Gemma 4 31B
Terminal-BenchNot measured33.4%Only GLM 4.7 measured
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5399.5Gemma 4 31B
LMArena Text: coding14591454Gemma 4 31B
LMArena Text: software and IT14631453Gemma 4 31B
LMArena WebDev: React13591420GLM 4.7
LMArena WebDev: HTML13801447GLM 4.7
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 4 31B and GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
AA Intelligence Index14.722.2GLM 4.7
Epoch Capabilities Index143.0143.6GLM 4.7
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 4 31B and GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
AA Agentic Index4.2Not measuredOnly Gemma 4 31B measured
Design Arena: agents building full-stack appsNot measured1050Only GLM 4.7 measured
Design Arena: agents building mobile appsNot measured1105Only GLM 4.7 measured
Design Arena: agents building Android appsNot measured1118Only GLM 4.7 measured
Design Arena: agents building Godot gamesNot measured1058Only GLM 4.7 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%95.9%GLM 4.7
Vending-Bench 2Not measured$2,377Only GLM 4.7 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
Reasoning benchmarks for Gemma 4 31B and GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
GPQA DiamondNot measured80.0%Only GLM 4.7 measured
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
GPQA Diamond (Artificial Analysis run)85.7%85.9%GLM 4.7
Humanity's Last Exam (Artificial Analysis run)23.6%27.4%GLM 4.7
GPQA Diamond (Epoch AI run)75.8%83.3%GLM 4.7
SimpleBenchNot measured47.7%Only GLM 4.7 measured
Chess puzzlesNot measured21.0%Only GLM 4.7 measured
LMArena Text: hard prompts14481443Gemma 4 31B
LMArena Text: expert14641424Gemma 4 31B
LMArena Text: hard prompts in English14561452Gemma 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 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index21
Math benchmarks for Gemma 4 31B and GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
AIMENot measured93.3%Only GLM 4.7 measured
MGSM (Vals AI)Not measured88.2%Only GLM 4.7 measured
AA Math IndexNot measured95.0Only GLM 4.7 measured
AIME 2025 (Artificial Analysis run)Not measured95.0%Only GLM 4.7 measured
OTIS Mock AIME73.3%83.3%GLM 4.7
ProofBenchNot measured6.0%Only GLM 4.7 measured
LMArena Text: math14631424Gemma 4 31B
LMArena Text: mathematical work14651411Gemma 4 31B
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index15
Knowledge benchmarks for Gemma 4 31B and GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
MMLU ProNot measured82.7%Only GLM 4.7 measured
LegalBench (Vals AI)Not measured83.4%Only GLM 4.7 measured
CaseLaw (Vals AI)52.6%54.9%GLM 4.7
CorpFin (Vals AI)Not measured46.4%Only GLM 4.7 measured
TaxEval (Vals AI)Not measured68.8%Only GLM 4.7 measured
MortgageTax (Vals AI)61.4%Not measuredOnly Gemma 4 31B measured
MedQA (Vals AI)Not measured93.7%Only GLM 4.7 measured
MedCode (Vals AI)Not measured32.8%Only GLM 4.7 measured
MMLU Pro (Artificial Analysis run)Not measured85.6%Only GLM 4.7 measured
SimpleQA Verified10.4%32.2%GLM 4.7
LMArena Text: science14571457GLM 4.7
LMArena Text: medicine and healthcare14511469GLM 4.7
LMArena Text: legal and government14381444GLM 4.7
LMArena Text: business and finance14301429Gemma 4 31B
Neither model has a result on the other 3 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 GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
Design Arena: websitesNot measured1226Only GLM 4.7 measured
Design Arena: UI componentsNot measured1199Only GLM 4.7 measured
Design Arena: game devNot measured1189Only GLM 4.7 measured
Design Arena: data vizNot measured1195Only GLM 4.7 measured
Design Arena: 3DNot measured1191Only GLM 4.7 measured
Design Arena: all code categoriesNot measured1217Only GLM 4.7 measured
Design Arena: SVGNot measured1142Only GLM 4.7 measured
Design Arena: ASCII artNot measured1165Only GLM 4.7 measured
LiveBench design58.4%Not measuredOnly Gemma 4 31B measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index124
General benchmarks for Gemma 4 31B and GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%Not measuredOnly Gemma 4 31B measured
MedScribe (Vals AI)Not measured68.6%Only GLM 4.7 measured
IFBench75.6%67.9%Gemma 4 31B
Long context reasoning (AA-LCR)69.7%71.0%GLM 4.7
DTBench82.7%Not measuredOnly Gemma 4 31B measured
LMCA39.3%Not measuredOnly Gemma 4 31B measured
CL-benchNot measured15.9%Only GLM 4.7 measured
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
CL-bench LifeNot measured10.9%Only GLM 4.7 measured
LMArena Text14431435Gemma 4 31B
LMArena Text: instruction following14331412Gemma 4 31B
LMArena Text: creative writing14171401Gemma 4 31B
LMArena Vision1276Not measuredOnly Gemma 4 31B measured
LMArena Text: English14511453GLM 4.7
LMArena Text: non-English14301417Gemma 4 31B
LMArena Text: Chinese14751495GLM 4.7
LMArena Text: GermanNot measured1426Only GLM 4.7 measured
LMArena Text: JapaneseNot measured1439Only GLM 4.7 measured
LMArena Text: KoreanNot measured1399Only GLM 4.7 measured
LMArena Text: French14361432Gemma 4 31B
LMArena Text: Spanish14421434Gemma 4 31B
LMArena Text: Russian14601423Gemma 4 31B
LMArena Text: Polish14331435GLM 4.7
LMArena Text: multi-turn14521446Gemma 4 31B
LMArena Text: longer queries14461432Gemma 4 31B
LMArena Text: writing and language14321411Gemma 4 31B
LMArena Text: entertainment and media14051400Gemma 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 10 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 GLM 4.7
BenchmarkGemma 4 31BGLM 4.7Leader
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
GLM 4.7$0.0015Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.011Fits in one request
GLM 4.7$0.033Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.044Fits in one request
GLM 4.7$0.128Exceeds the context window

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 GLM 4.7
SpecificationGoogle Gemma 4 31BZ.ai GLM 4.7
MakerGoogleZ.ai
WeightsOpen weightsOpen weights
ReleasedApril 2, 2026December 22, 2025
Context window262K205K
Input $/Mtok$0.20$0.54
Output $/Mtok$0.40$1.98
Coding index38.333.6
Independent measurements behind it21
Cost per solved taskNot computable$0.29
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than GLM 4.7 for coding?

Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 33.6 for GLM 4.7. Pick GLM 4.7 when what matters is LMArena WebDev or AA Coding Index, where it leads.

Which is cheaper, Gemma 4 31B or GLM 4.7?

Gemma 4 31B costs $0.20 per million input tokens and $0.40 per million output tokens; GLM 4.7 costs $0.54 and $1.98. Cost per solved task is known for GLM 4.7 only.

Which has the bigger context window, Gemma 4 31B or GLM 4.7?

Gemma 4 31B, with 262K tokens against 205K.

How many benchmarks is the Gemma 4 31B vs GLM 4.7 comparison based on?

42 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and GLM 4.7's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next