Enter opens the highlighted result. Esc closes.

Gemma 3 27B vs GPT-4 Turbo

GPT-4 Turbo leads Gemma 3 27B on the Artificial Analysis Intelligence Index, 7.0 to 4.9, and Gemma 3 27B costs 100.0x less per output token ($0.30 vs $30.00 per million). Updated October 22, 2026; 39 benchmarks have a result for both.

Replace Gemma 3 27B Replace GPT-4 Turbo
Gemma 3 27BGoogle
Coding
No data
Overall
31.4
Output $/M
$0.30
34
GPT-4 TurboOpenAI
Coding
No data
Overall
No data
Output $/M
$30.00
5
vs boards won of 39 shared

Gemma 3 27B or GPT-4 Turbo: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Gemma 3 27B for output tokens 100.0x cheaper ($0.30 vs $30.00 per million) and a larger context window (131K against 128K tokens).

Model AGemma 3 27BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-4 TurboOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
39
Gemma 3 27B only
27
GPT-4 Turbo only
3
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 3 27B not benchmarked, GPT-4 Turbo not benchmarked.
Widest category
Knowledge, 18.1 points apart on average over 5 shared benchmarks.
Widest single gap
LMArena Text: medicine and healthcare: Gemma 3 27B 1391 against GPT-4 Turbo 1239, 25.3 points apart on a 0 to 100 scale.
Output price
Gemma 3 27B $0.30 against GPT-4 Turbo $30.00 per million output tokens, 100.0x apart.
Context window
Gemma 3 27B takes 131K 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 3 27BBarsGPT-4 TurboTies
Coding22
Intelligence11
Reasoning40
Math20
Knowledge41
General211
All shared boards345
CodingLike-for-likeSix of these boards feed the Vibe Coding Index22
Coding benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-4 TurboLeader
Aider polyglot4.9%Not measuredOnly Gemma 3 27B measured
AA Coding Index10.121.5GPT-4 Turbo
LiveCodeBench (Artificial Analysis run)13.7%29.1%GPT-4 Turbo
SciCode23.3%Not measuredOnly Gemma 3 27B measured
Terminal-Bench Hard (Artificial Analysis run)3.8%Not measuredOnly Gemma 3 27B measured
LMArena Text: coding13221268Gemma 3 27B
LMArena Text: software and IT13541267Gemma 3 27B
SciCode0.0%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-4 TurboLeader
AA Intelligence Index4.97.0GPT-4 Turbo
Epoch Capabilities Index130.0127.3Gemma 3 27B
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-4 TurboLeader
AA Agentic Index0.1Not measuredOnly Gemma 3 27B measured
τ²-Bench Telecom10.5%Not measuredOnly Gemma 3 27B measured
Berkeley Function Calling Leaderboard (BFCL)29.5%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-4 TurboLeader
GPQA Diamond (Artificial Analysis run)42.8%Not measuredOnly Gemma 3 27B measured
Humanity's Last Exam (Artificial Analysis run)4.4%3.1%Gemma 3 27B
GPQA Diamond (Epoch AI run)47.7%Not measuredOnly Gemma 3 27B measured
LMArena Text: hard prompts13401251Gemma 3 27B
LMArena Text: expert13041223Gemma 3 27B
LMArena Text: hard prompts in English13531266Gemma 3 27B
LMArena Vision: diagrams1156Not measuredOnly Gemma 3 27B measured
LMArena Vision: homework1160Not measuredOnly Gemma 3 27B measured
Kagi LLM Benchmark35.1%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-4 TurboLeader
AA Math Index20.7Not measuredOnly Gemma 3 27B measured
AIME 2025 (Artificial Analysis run)20.7%Not measuredOnly Gemma 3 27B measured
OTIS Mock AIME22.5%Not measuredOnly Gemma 3 27B measured
MATH level 574.0%Not measuredOnly Gemma 3 27B measured
LMArena Text: math13121272Gemma 3 27B
LMArena Text: mathematical work13271268Gemma 3 27B
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
Knowledge benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-4 TurboLeader
LegalBench (Vals AI)Not measured80.5%Only GPT-4 Turbo measured
MedQA (Vals AI)Not measured82.0%Only GPT-4 Turbo measured
MMLU Pro (Artificial Analysis run)66.9%69.4%GPT-4 Turbo
MMLUNot measured81.3%Only GPT-4 Turbo measured
GeoBench52.0%Not measuredOnly Gemma 3 27B measured
LMArena Text: science13831256Gemma 3 27B
LMArena Text: medicine and healthcare13911239Gemma 3 27B
LMArena Text: legal and government13751265Gemma 3 27B
LMArena Text: business and finance13601222Gemma 3 27B
FACTS Benchmark Suite29.1%Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 8 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-4 TurboLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index211
General benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-4 TurboLeader
IFBench31.8%Not measuredOnly Gemma 3 27B measured
Long context reasoning (AA-LCR)7.3%Not measuredOnly Gemma 3 27B measured
DTBench52.5%61.6%GPT-4 Turbo
LMCA12.3%9.8%Gemma 3 27B
Fiction.LiveBench33.3%Not measuredOnly Gemma 3 27B measured
Creative writing (Lech Mazur)79.9%Not measuredOnly Gemma 3 27B measured
LMArena Text13581272Gemma 3 27B
LMArena Text: instruction following13211249Gemma 3 27B
LMArena Text: creative writing13451268Gemma 3 27B
LMArena Vision11651090Gemma 3 27B
LMArena Text: English13771291Gemma 3 27B
LMArena Text: non-English13341245Gemma 3 27B
LMArena Text: Chinese13461242Gemma 3 27B
LMArena Text: German13621259Gemma 3 27B
LMArena Text: Japanese12871194Gemma 3 27B
LMArena Text: Korean13081187Gemma 3 27B
LMArena Text: French13681276Gemma 3 27B
LMArena Text: Spanish13491260Gemma 3 27B
LMArena Text: Russian13491259Gemma 3 27B
LMArena Text: Polish13451302Gemma 3 27B
LMArena Text: multi-turn13451267Gemma 3 27B
LMArena Text: longer queries13331254Gemma 3 27B
LMArena Text: writing and language13471279Gemma 3 27B
LMArena Text: entertainment and media13201258Gemma 3 27B
LMArena Vision: English11881097Gemma 3 27B
LMArena Vision: Chinese11641045Gemma 3 27B
LMArena Vision: reading text1156Not measuredOnly Gemma 3 27B measured
LMArena Vision: humor1166Not measuredOnly Gemma 3 27B measured
LMArena Vision: captioning1151Not measuredOnly Gemma 3 27B measured
LMArena Vision: recognizing things1196Not measuredOnly Gemma 3 27B measured
LMArena Vision: creative writing1177Not measuredOnly Gemma 3 27B measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 3 27B and GPT-4 Turbo
BenchmarkGemma 3 27BGPT-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 3 27B$0.0002Fits in one request
GPT-4 Turbo$0.025Fits in one request

Gemma 3 27B costs less

Repository review

50K input + 3K output tokens

Gemma 3 27B$0.0049Fits in one request
GPT-4 Turbo$0.590Fits in one request

Gemma 3 27B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 27B$0.019Exceeds the context window
GPT-4 Turbo$2.30Exceeds the context window

Gemma 3 27B 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 3 27B and GPT-4 Turbo
SpecificationGoogle Gemma 3 27BOpenAI GPT-4 Turbo
MakerGoogleOpenAI
WeightsOpen weightsNo public weights listed
ReleasedMarch 12, 2025April 9, 2024
Context window131K128K
Input $/Mtok$0.08$10.00
Output $/Mtok$0.30$30.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 27B better than GPT-4 Turbo for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 27B for output tokens 100.0x cheaper ($0.30 vs $30.00 per million) and a larger context window (131K against 128K tokens).

Which is cheaper, Gemma 3 27B or GPT-4 Turbo?

Gemma 3 27B costs $0.08 per million input tokens and $0.30 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 3 27B or GPT-4 Turbo?

Gemma 3 27B, with 131K tokens against 128K.

How many benchmarks is the Gemma 3 27B vs GPT-4 Turbo comparison based on?

39 benchmarks have a result for both models as of October 22, 2026. Gemma 3 27B's coding index rests on 0 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