Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs GPT-4 Turbo

Gemma 4 31B leads GPT-4 Turbo on the Artificial Analysis Intelligence Index, 14.7 to 7.0, and Gemma 4 31B costs 75.0x less per output token ($0.40 vs $30.00 per million). Updated October 22, 2026; 34 benchmarks have a result for both.

Replace Gemma 4 31B Replace GPT-4 Turbo
Gemma 4 31BGoogle
Coding
39.0
Overall
42.1
Output $/M
$0.40
34
GPT-4 TurboOpenAI
Coding
No data
Overall
No data
Output $/M
$30.00
0
vs boards won of 34 shared

Gemma 4 31B or GPT-4 Turbo: which to pick

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

Compare them on price, context and the boards below.

Model AGemma 4 31BGoogle39.0/1002 independent benchmarksNo cost per solved taskModel BGPT-4 TurboOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
34
Gemma 4 31B only
37
GPT-4 Turbo only
8
Like-for-like categories
6 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, GPT-4 Turbo not benchmarked.
Widest category
Knowledge, 33.0 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Vision: Chinese: Gemma 4 31B 1326 against GPT-4 Turbo 1045, 46.8 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against GPT-4 Turbo $30.00 per million output tokens, 75.0x apart.
Context window
Gemma 4 31B takes 262K tokens, GPT-4 Turbo 128K.

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 31BBarsGPT-4 TurboTies
Coding30
Intelligence20
Reasoning40
Math20
Knowledge40
General190
All shared boards340
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Gemma 4 31B and GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 TurboLeader
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev1367Not measuredOnly Gemma 4 31B measured
AA Coding Index43.421.5Gemma 4 31B
LiveCodeBench (Artificial Analysis run)Not measured29.1%Only GPT-4 Turbo measured
SciCode45.5%Not measuredOnly Gemma 4 31B measured
Terminal-Bench Hard (Artificial Analysis run)36.4%Not measuredOnly Gemma 4 31B measured
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5Not measuredOnly Gemma 4 31B measured
LMArena Text: coding14591268Gemma 4 31B
LMArena Text: software and IT14631267Gemma 4 31B
LMArena WebDev: React1359Not measuredOnly Gemma 4 31B measured
LMArena WebDev: HTML1380Not measuredOnly Gemma 4 31B 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 index20
Intelligence benchmarks for Gemma 4 31B and GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 TurboLeader
AA Intelligence Index14.77.0Gemma 4 31B
Epoch Capabilities Index143.0127.3Gemma 4 31B
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Agentic work benchmarks for Gemma 4 31B and GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 TurboLeader
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%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for Gemma 4 31B and GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 TurboLeader
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
GPQA Diamond (Artificial Analysis run)85.7%Not measuredOnly Gemma 4 31B measured
Humanity's Last Exam (Artificial Analysis run)23.6%3.1%Gemma 4 31B
GPQA Diamond (Epoch AI run)75.8%Not measuredOnly Gemma 4 31B measured
LMArena Text: hard prompts14481251Gemma 4 31B
LMArena Text: expert14641223Gemma 4 31B
LMArena Text: hard prompts in English14561266Gemma 4 31B
LMArena Vision: diagrams1283Not measuredOnly Gemma 4 31B measured
LMArena Vision: homework1310Not measuredOnly Gemma 4 31B measured
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 GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 TurboLeader
OTIS Mock AIME73.3%Not measuredOnly Gemma 4 31B measured
LMArena Text: math14631272Gemma 4 31B
LMArena Text: mathematical work14651268Gemma 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 GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 TurboLeader
LegalBench (Vals AI)Not measured80.5%Only GPT-4 Turbo measured
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B measured
MortgageTax (Vals AI)61.4%Not measuredOnly Gemma 4 31B measured
MedQA (Vals AI)Not measured82.0%Only GPT-4 Turbo measured
MMLU Pro (Artificial Analysis run)Not measured69.4%Only GPT-4 Turbo measured
SimpleQA Verified10.4%Not measuredOnly Gemma 4 31B measured
MMLUNot measured81.3%Only GPT-4 Turbo measured
LMArena Text: science14571256Gemma 4 31B
LMArena Text: medicine and healthcare14511239Gemma 4 31B
LMArena Text: legal and government14381265Gemma 4 31B
LMArena Text: business and finance14301222Gemma 4 31B
FACTS Benchmark Suite45.3%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 6 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 GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 TurboLeader
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 index190
General benchmarks for Gemma 4 31B and GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 TurboLeader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%Not measuredOnly Gemma 4 31B measured
IFBench75.6%Not measuredOnly Gemma 4 31B measured
Long context reasoning (AA-LCR)69.7%Not measuredOnly Gemma 4 31B measured
DTBench82.7%61.6%Gemma 4 31B
LMCA39.3%9.8%Gemma 4 31B
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
LMArena Text14431272Gemma 4 31B
LMArena Text: instruction following14331249Gemma 4 31B
LMArena Text: creative writing14171268Gemma 4 31B
LMArena Vision12761090Gemma 4 31B
LMArena Text: English14511291Gemma 4 31B
LMArena Text: non-English14301245Gemma 4 31B
LMArena Text: Chinese14751242Gemma 4 31B
LMArena Text: GermanNot measured1259Only GPT-4 Turbo measured
LMArena Text: JapaneseNot measured1194Only GPT-4 Turbo measured
LMArena Text: KoreanNot measured1187Only GPT-4 Turbo measured
LMArena Text: French14361276Gemma 4 31B
LMArena Text: Spanish14421260Gemma 4 31B
LMArena Text: Russian14601259Gemma 4 31B
LMArena Text: Polish14331302Gemma 4 31B
LMArena Text: multi-turn14521267Gemma 4 31B
LMArena Text: longer queries14461254Gemma 4 31B
LMArena Text: writing and language14321279Gemma 4 31B
LMArena Text: entertainment and media14051258Gemma 4 31B
LMArena Vision: English12711097Gemma 4 31B
LMArena Vision: Chinese13261045Gemma 4 31B
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 GPT-4 Turbo
BenchmarkGemma 4 31BGPT-4 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
GPT-4 Turbo$0.025Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.0082Fits in one request
GPT-4 Turbo$0.590Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.032Fits in one request
GPT-4 Turbo$2.30Exceeds 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 GPT-4 Turbo
SpecificationGoogle Gemma 4 31BOpenAI GPT-4 Turbo
MakerGoogleOpenAI
WeightsOpen weightsNo public weights listed
ReleasedApril 2, 2026April 9, 2024
Context window262K128K
Input $/Mtok$0.14$10.00
Output $/Mtok$0.40$30.00
Coding index39.0Not benchmarked
Independent measurements behind it20
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than GPT-4 Turbo for coding?

Only Gemma 4 31B has a coding score, 39.0 on the Vibe Coding Index; GPT-4 Turbo has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, Gemma 4 31B or GPT-4 Turbo?

Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens; GPT-4 Turbo costs $10.00 and $30.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 4 31B or GPT-4 Turbo?

Gemma 4 31B, with 262K tokens against 128K.

How many benchmarks is the Gemma 4 31B vs GPT-4 Turbo comparison based on?

34 benchmarks have a result for both models as of October 22, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and GPT-4 Turbo's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next