Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs GLM 5V Turbo

GLM 5V Turbo leads Gemma 4 31B on the Artificial Analysis Intelligence Index, 23.5 to 14.7, and Gemma 4 31B costs 10.0x less per output token ($0.40 vs $4.00 per million). Updated October 22, 2026; 46 benchmarks have a result for both.

Replace Gemma 4 31B Replace GLM 5V Turbo
Gemma 4 31BGoogle
Coding
39.0
Overall
42.1
Output $/M
$0.40
28
GLM 5V TurboZ.ai
Coding
No data
Overall
No data
Output $/M
$4.00
18
vs boards won of 46 shared

Gemma 4 31B or GLM 5V Turbo: which to pick

Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; GLM 5V Turbo has none, so the two cannot be ranked on coding.

Pick GLM 5V Turbo for work measured by LMArena WebDev or LMArena Text: coding, where it leads.

Model AGemma 4 31BGoogle39.0/1002 independent benchmarksNo cost per solved taskModel BGLM 5V TurboZ.aiNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
46
Gemma 4 31B only
25
GLM 5V Turbo only
19
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, GLM 5V Turbo not benchmarked.
Widest category
Agentic work, 33.0 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Gemma 4 31B 65.5% against GLM 5V Turbo 98.5%, 33.0 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against GLM 5V Turbo $4.00 per million output tokens, 10.0x apart.
Context window
Gemma 4 31B takes 262K tokens, GLM 5V Turbo 203K.

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 5V TurboTies
Coding33
Intelligence01
Agentic work01
Reasoning61
Math20
Knowledge31
General1411
All shared boards2818
CodingLike-for-likeSix of these boards feed the Vibe Coding Index33
Coding benchmarks for Gemma 4 31B and GLM 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev13671402GLM 5V Turbo
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%32.6%Gemma 4 31B
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5Not measuredOnly Gemma 4 31B measured
LMArena Text: coding14591466GLM 5V Turbo
LMArena Text: software and IT14631460Gemma 4 31B
LMArena WebDev: React13591386GLM 5V Turbo
LMArena WebDev: HTML13801356Gemma 4 31B
LMArena WebDev: from an imageNot measured1425Only GLM 5V Turbo measured
SciCode8.9%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 4 31B and GLM 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
AA Intelligence Index14.723.5GLM 5V Turbo
Epoch Capabilities Index143.0Not measuredOnly Gemma 4 31B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 4 31B and GLM 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
AA Agentic Index4.2Not measuredOnly Gemma 4 31B measured
Design Arena: agents building web appsNot measured1124Only GLM 5V Turbo measured
Design Arena: agents building full-stack appsNot measured1149Only GLM 5V Turbo measured
Design Arena: agents building mobile appsNot measured1134Only GLM 5V Turbo measured
Design Arena: agents building Android appsNot measured1267Only GLM 5V Turbo measured
Design Arena: agents building Godot gamesNot measured957Only GLM 5V Turbo measured
Design Arena: agents building gamesNot measured1102Only GLM 5V Turbo measured
Design Arena: HTML slidesNot measured1070Only GLM 5V Turbo measured
Design Arena: PowerPoint slidesNot measured1127Only GLM 5V Turbo 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%98.5%GLM 5V Turbo
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index61
Reasoning benchmarks for Gemma 4 31B and GLM 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
GPQA Diamond (Artificial Analysis run)85.7%80.9%Gemma 4 31B
Humanity's Last Exam (Artificial Analysis run)23.6%17.1%Gemma 4 31B
GPQA Diamond (Epoch AI run)75.8%Not measuredOnly Gemma 4 31B measured
LMArena Text: hard prompts14481443Gemma 4 31B
LMArena Text: expert14641453Gemma 4 31B
LMArena Text: hard prompts in English14561456Gemma 4 31B
LMArena Vision: diagrams12831286GLM 5V Turbo
LMArena Vision: homework13101273Gemma 4 31B
Kagi LLM Benchmark63.5%Not 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 index20
Math benchmarks for Gemma 4 31B and GLM 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
OTIS Mock AIME73.3%Not measuredOnly Gemma 4 31B measured
LMArena Text: math14631442Gemma 4 31B
LMArena Text: mathematical work14651447Gemma 4 31B
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
Knowledge benchmarks for Gemma 4 31B and GLM 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
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: science14571448Gemma 4 31B
LMArena Text: medicine and healthcare14511433Gemma 4 31B
LMArena Text: legal and government14381436Gemma 4 31B
LMArena Text: business and finance14301435GLM 5V Turbo
FACTS Benchmark Suite45.3%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 10 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 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
Design Arena: websitesNot measured1230Only GLM 5V Turbo measured
Design Arena: UI componentsNot measured1210Only GLM 5V Turbo measured
Design Arena: game devNot measured1218Only GLM 5V Turbo measured
Design Arena: data vizNot measured1202Only GLM 5V Turbo measured
Design Arena: 3DNot measured1208Only GLM 5V Turbo measured
Design Arena: all code categoriesNot measured1228Only GLM 5V Turbo measured
Design Arena: SVGNot measured1151Only GLM 5V Turbo measured
Design Arena: ASCII artNot measured1117Only GLM 5V Turbo measured
LiveBench design58.4%Not measuredOnly Gemma 4 31B measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index1411
General benchmarks for Gemma 4 31B and GLM 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%Not measuredOnly Gemma 4 31B measured
IFBench75.6%61.1%Gemma 4 31B
Long context reasoning (AA-LCR)69.7%70.3%GLM 5V Turbo
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 Text14431437Gemma 4 31B
LMArena Text: instruction following14331423Gemma 4 31B
LMArena Text: creative writing14171417GLM 5V Turbo
LMArena Vision12761264Gemma 4 31B
LMArena Text: English14511454GLM 5V Turbo
LMArena Text: non-English14301420Gemma 4 31B
LMArena Text: Chinese14751491GLM 5V Turbo
LMArena Text: GermanNot measured1422Only GLM 5V Turbo measured
LMArena Text: KoreanNot measured1397Only GLM 5V Turbo measured
LMArena Text: French14361443GLM 5V Turbo
LMArena Text: Spanish14421452GLM 5V Turbo
LMArena Text: Russian14601432Gemma 4 31B
LMArena Text: Polish14331432Gemma 4 31B
LMArena Text: multi-turn14521431Gemma 4 31B
LMArena Text: longer queries14461438Gemma 4 31B
LMArena Text: writing and language14321420Gemma 4 31B
LMArena Text: entertainment and media14051407GLM 5V Turbo
LMArena Vision: English12711274GLM 5V Turbo
LMArena Vision: Chinese13261329GLM 5V Turbo
LMArena Vision: reading text12821270Gemma 4 31B
LMArena Vision: humor12801268Gemma 4 31B
LMArena Vision: captioning12181264GLM 5V Turbo
LMArena Vision: recognizing things12261241GLM 5V Turbo
LMArena Vision: creative writing12851252Gemma 4 31B
LMArena Document14251416Gemma 4 31B
Neither model has a result on the other 14 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 5V Turbo
BenchmarkGemma 4 31BGLM 5V TurboLeader
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
GLM 5V Turbo$0.0032Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.0082Fits in one request
GLM 5V Turbo$0.072Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.032Fits in one request
GLM 5V Turbo$0.280Exceeds 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 5V Turbo
SpecificationGoogle Gemma 4 31BZ.ai GLM 5V Turbo
MakerGoogleZ.ai
WeightsOpen weightsNo public weights listed
ReleasedApril 2, 2026April 1, 2026
Context window262K203K
Input $/Mtok$0.14$1.20
Output $/Mtok$0.40$4.00
Coding index39.0Not benchmarked
Independent measurements behind it21
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than GLM 5V Turbo for coding?

Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; GLM 5V Turbo has none, so the two cannot be ranked on coding. Pick GLM 5V Turbo for work measured by LMArena WebDev or LMArena Text: coding, where it leads.

Which is cheaper, Gemma 4 31B or GLM 5V Turbo?

Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens; GLM 5V Turbo costs $1.20 and $4.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 4 31B or GLM 5V Turbo?

Gemma 4 31B, with 262K tokens against 203K.

How many benchmarks is the Gemma 4 31B vs GLM 5V Turbo comparison based on?

46 benchmarks have a result for both models as of October 22, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and GLM 5V Turbo's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next