Enter opens the highlighted result. Esc closes.

Gemma 3 4B vs GPT-5.4 Nano

GPT-5.4 Nano leads Gemma 3 4B on the Artificial Analysis Intelligence Index, 20.7 to 4.8, and Gemma 3 4B costs 16.7x less per output token ($0.075 vs $1.25 per million). Updated October 22, 2026; 36 benchmarks have a result for both.

Replace Gemma 3 4B Replace GPT-5.4 Nano
Gemma 3 4BGoogle
Coding
No data
Overall
22.6
Output $/M
$0.075
0
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
36
vs boards won of 36 shared

Gemma 3 4B or GPT-5.4 Nano: which to pick

Only GPT-5.4 Nano has a coding score, 44.8 on the Vibe Coding Index; Gemma 3 4B has none, so the two cannot be ranked on coding.

Pick Gemma 3 4B for output tokens 16.7x cheaper ($0.075 vs $1.25 per million).

Model AGemma 3 4BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved task
Shared results
36
Gemma 3 4B only
6
GPT-5.4 Nano only
49
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 3 4B not benchmarked, GPT-5.4 Nano 44.8 from 2 benchmarks.
Widest category
Agentic work, 71.1 points apart on average over 1 shared benchmark.
Widest single gap
OTIS Mock AIME: Gemma 3 4B 7.5% against GPT-5.4 Nano 87.8%, 80.3 points apart on a 0 to 100 scale.
Output price
Gemma 3 4B $0.075 against GPT-5.4 Nano $1.25 per million output tokens, 16.7x apart.
Context window
Gemma 3 4B takes 131K tokens, GPT-5.4 Nano 400K.

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 4BBarsGPT-5.4 NanoTies
Coding04
Intelligence02
Agentic work01
Reasoning07
Math03
Knowledge04
General015
All shared boards036
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Gemma 3 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
AA Coding Index2.756.1GPT-5.4 Nano
LiveCodeBench (Vals AI)Not measured84.0%Only GPT-5.4 Nano measured
SWE-bench Verified (Vals AI)Not measured69.8%Only GPT-5.4 Nano measured
Vibe Code Bench (Vals AI)Not measured26.1%Only GPT-5.4 Nano measured
Code migration (Vals AI)Not measured14.5%Only GPT-5.4 Nano measured
Terminal-Bench 2.1 (Vals AI)Not measured41.6%Only GPT-5.4 Nano measured
LiveCodeBench (Artificial Analysis run)11.2%Not measuredOnly Gemma 3 4B measured
SciCodeNot measured47.2%Only GPT-5.4 Nano measured
Terminal-Bench Hard (Artificial Analysis run)0.8%42.4%GPT-5.4 Nano
WeirdMLNot measured49.2%Only GPT-5.4 Nano measured
ALE-BenchNot measured1004.5Only GPT-5.4 Nano measured
LMArena Text: coding12301404GPT-5.4 Nano
LMArena Text: software and IT12691402GPT-5.4 Nano
SciCode0.0%Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 3 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
AA Intelligence Index4.820.7GPT-5.4 Nano
Epoch Capabilities Index115.9146.0GPT-5.4 Nano
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 3 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
AA Agentic IndexNot measured16.0Only GPT-5.4 Nano measured
Finance Agent (Vals AI)Not measured38.2%Only GPT-5.4 Nano measured
Tax Agent Bench (Vals AI)Not measured5.0%Only GPT-5.4 Nano measured
Legal Research Bench (Vals AI)Not measured6.3%Only GPT-5.4 Nano measured
Excel Modeling Benchmark (Vals AI)Not measured44.8%Only GPT-5.4 Nano measured
τ²-Bench Telecom5.0%76.0%GPT-5.4 Nano
Berkeley Function Calling Leaderboard (BFCL)19.6%Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for Gemma 3 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
GPQA DiamondNot measured77.5%Only GPT-5.4 Nano measured
MMMU Pro (Vals AI)Not measured73.6%Only GPT-5.4 Nano measured
GPQA Diamond (Artificial Analysis run)29.1%81.7%GPT-5.4 Nano
Humanity's Last Exam (Artificial Analysis run)5.3%28.3%GPT-5.4 Nano
GPQA Diamond (Epoch AI run)23.2%78.5%GPT-5.4 Nano
ARC-AGINot measured51.5%Only GPT-5.4 Nano measured
ARC-AGI-2Not measured5.7%Only GPT-5.4 Nano measured
Chess puzzlesNot measured45.0%Only GPT-5.4 Nano measured
Mystery game puzzlesNot measured9.0%Only GPT-5.4 Nano measured
LMArena Text: hard prompts12531381GPT-5.4 Nano
LMArena Text: expert12231396GPT-5.4 Nano
LMArena Text: hard prompts in English12531387GPT-5.4 Nano
LMArena Vision: diagramsNot measured1210Only GPT-5.4 Nano measured
LMArena Vision: homeworkNot measured1225Only GPT-5.4 Nano measured
Kagi LLM Benchmark25.2%39.7%GPT-5.4 Nano
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Gemma 3 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
AIMENot measured88.8%Only GPT-5.4 Nano measured
AA Math Index12.7Not measuredOnly Gemma 3 4B measured
AIME 2025 (Artificial Analysis run)12.7%Not measuredOnly Gemma 3 4B measured
OTIS Mock AIME7.5%87.8%GPT-5.4 Nano
FrontierMath, tiers 1 to 3Not measured44.9%Only GPT-5.4 Nano measured
FrontierMath, tier 4Not measured12.2%Only GPT-5.4 Nano measured
ProofBenchNot measured5.0%Only GPT-5.4 Nano measured
LMArena Text: math12391405GPT-5.4 Nano
LMArena Text: mathematical work12561409GPT-5.4 Nano
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Gemma 3 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
MMLU ProNot measured77.2%Only GPT-5.4 Nano measured
LegalBench (Vals AI)Not measured77.9%Only GPT-5.4 Nano measured
CaseLaw (Vals AI)Not measured51.9%Only GPT-5.4 Nano measured
CorpFin (Vals AI)Not measured61.2%Only GPT-5.4 Nano measured
TaxEval (Vals AI)Not measured67.4%Only GPT-5.4 Nano measured
MortgageTax (Vals AI)Not measured59.1%Only GPT-5.4 Nano measured
MedCode (Vals AI)Not measured41.0%Only GPT-5.4 Nano measured
MMLU Pro (Artificial Analysis run)41.7%Not measuredOnly Gemma 3 4B measured
SimpleQA VerifiedNot measured11.7%Only GPT-5.4 Nano measured
LMArena Text: science13061374GPT-5.4 Nano
LMArena Text: medicine and healthcare13421369GPT-5.4 Nano
LMArena Text: legal and government13271368GPT-5.4 Nano
LMArena Text: business and finance13111366GPT-5.4 Nano
Neither model has a result on the other 5 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Gemma 3 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index015
General benchmarks for Gemma 3 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
SAGE (Vals AI)Not measured38.1%Only GPT-5.4 Nano measured
MedScribe (Vals AI)Not measured77.1%Only GPT-5.4 Nano measured
Vals Multimodal IndexNot measured47.6%Only GPT-5.4 Nano measured
IFBench28.3%75.9%GPT-5.4 Nano
Long context reasoning (AA-LCR)6.7%76.7%GPT-5.4 Nano
DTBench50.9%80.3%GPT-5.4 Nano
LMCA2.8%36.9%GPT-5.4 Nano
LMArena Text12911372GPT-5.4 Nano
LMArena Text: instruction following12391362GPT-5.4 Nano
LMArena Text: creative writing12701315GPT-5.4 Nano
LMArena VisionNot measured1196Only GPT-5.4 Nano measured
LMArena Text: English13001381GPT-5.4 Nano
LMArena Text: non-English12731359GPT-5.4 Nano
LMArena Text: ChineseNot measured1391Only GPT-5.4 Nano measured
LMArena Text: German12811368GPT-5.4 Nano
LMArena Text: JapaneseNot measured1343Only GPT-5.4 Nano measured
LMArena Text: KoreanNot measured1321Only GPT-5.4 Nano measured
LMArena Text: FrenchNot measured1395Only GPT-5.4 Nano measured
LMArena Text: SpanishNot measured1371Only GPT-5.4 Nano measured
LMArena Text: Russian12941363GPT-5.4 Nano
LMArena Text: PolishNot measured1366Only GPT-5.4 Nano measured
LMArena Text: multi-turn12551382GPT-5.4 Nano
LMArena Text: longer queries12731365GPT-5.4 Nano
LMArena Text: writing and language12881338GPT-5.4 Nano
LMArena Text: entertainment and media12331325GPT-5.4 Nano
LMArena Vision: EnglishNot measured1202Only GPT-5.4 Nano measured
LMArena Vision: ChineseNot measured1232Only GPT-5.4 Nano measured
LMArena Vision: reading textNot measured1204Only GPT-5.4 Nano measured
LMArena Vision: humorNot measured1161Only GPT-5.4 Nano measured
LMArena Vision: recognizing thingsNot measured1141Only GPT-5.4 Nano measured
LMArena Vision: creative writingNot measured1159Only GPT-5.4 Nano 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 4B and GPT-5.4 Nano
BenchmarkGemma 3 4BGPT-5.4 NanoLeader
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 4B$0.0001Fits in one request
GPT-5.4 Nano$0.0008Fits in one request

Gemma 3 4B costs less

Repository review

50K input + 3K output tokens

Gemma 3 4B$0.0025Fits in one request
GPT-5.4 Nano$0.014Fits in one request

Gemma 3 4B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 4B$0.0097Exceeds the context window
GPT-5.4 Nano$0.052Fits in one request

Gemma 3 4B 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 4B and GPT-5.4 Nano
SpecificationGoogle Gemma 3 4BOpenAI GPT-5.4 Nano
MakerGoogleOpenAI
WeightsOpen weightsNo public weights listed
ReleasedMarch 13, 2025March 17, 2026
Context window131K400K
Input $/Mtok$0.045$0.20
Output $/Mtok$0.075$1.25
Coding indexNot benchmarked44.8
Independent measurements behind it02
Cost per solved taskNot computable$0.14
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 4B better than GPT-5.4 Nano for coding?

Only GPT-5.4 Nano has a coding score, 44.8 on the Vibe Coding Index; Gemma 3 4B has none, so the two cannot be ranked on coding. Pick Gemma 3 4B for output tokens 16.7x cheaper ($0.075 vs $1.25 per million).

Which is cheaper, Gemma 3 4B or GPT-5.4 Nano?

Gemma 3 4B costs $0.045 per million input tokens and $0.075 per million output tokens; GPT-5.4 Nano costs $0.20 and $1.25. Cost per solved task is known for GPT-5.4 Nano only.

Which has the bigger context window, Gemma 3 4B or GPT-5.4 Nano?

GPT-5.4 Nano, with 400K tokens against 131K.

How many benchmarks is the Gemma 3 4B vs GPT-5.4 Nano comparison based on?

36 benchmarks have a result for both models as of October 22, 2026. Gemma 3 4B's coding index rests on 0 independent benchmarks and GPT-5.4 Nano's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next