Enter opens the highlighted result. Esc closes.

Gemma 3 4B vs GPT-5 Mini

Updated October 21, 2026. 38 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemma 3 4B Replace GPT-5 Mini
Gemma 3 4BGoogle
Coding
No data
Overall
4.8
Output $/M
$0.075
0
GPT-5 MiniOpenAI
Coding
34.2
Overall
20.6
Output $/M
$2.00
38
vs boards won of 38 shared

Decision reading

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; Gemma 3 4B has none, so the two cannot be ranked on coding.

Gemma 3 4B has the edge where output tokens cost 26.7x less.

Model AGemma 3 4BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved task
Shared results
38
Gemma 3 4B only
1
GPT-5 Mini only
60
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 3 4B not benchmarked, GPT-5 Mini 34.2 from 2 benchmarks.
Widest category
Agentic work, 66.1 points apart on average over 1 shared benchmark.
Widest single gap
OTIS Mock AIME: Gemma 3 4B 7.5% against GPT-5 Mini 86.7%, 79.2 points apart on a 0 to 100 scale.
Output price
Gemma 3 4B $0.075 against GPT-5 Mini $2.00 per million output tokens, 26.7x apart.
Context window
Gemma 3 4B takes 131K tokens, GPT-5 Mini 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 MiniTies
Coding04
Intelligence02
Agentic work01
Reasoning06
Math05
Knowledge05
General015
All shared boards038
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Gemma 3 4B and GPT-5 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
SWE-bench VerifiedNot measured59.8%Only GPT-5 Mini measured
SWE-bench MultilingualNot measured39.7%Only GPT-5 Mini measured
AA Coding Index2.7Not measuredOnly Gemma 3 4B measured
LiveCodeBench (Vals AI)Not measured86.6%Only GPT-5 Mini measured
SWE-bench Verified (Vals AI)Not measured60.8%Only GPT-5 Mini measured
Vibe Code Bench (Vals AI)Not measured14.2%Only GPT-5 Mini measured
LiveCodeBench (Artificial Analysis run)11.2%83.8%GPT-5 Mini
SciCodeNot measured39.0%Only GPT-5 Mini measured
Terminal-Bench Hard (Artificial Analysis run)0.8%33.3%GPT-5 Mini
Terminal-BenchNot measured34.8%Only GPT-5 Mini measured
WeirdMLNot measured52.7%Only GPT-5 Mini measured
LMArena Text: coding12301406GPT-5 Mini
LMArena Text: software and IT12691394GPT-5 Mini
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 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
AA Intelligence Index4.820.6GPT-5 Mini
Epoch Capabilities Index115.9145.3GPT-5 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 3 4B and GPT-5 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
τ²-Bench Telecom5.0%71.1%GPT-5 Mini
Vending-Bench 2Not measured-$31Only GPT-5 Mini measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for Gemma 3 4B and GPT-5 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
GPQA DiamondNot measured80.3%Only GPT-5 Mini measured
MMMU Pro (Vals AI)Not measured78.9%Only GPT-5 Mini measured
GPQA Diamond (Artificial Analysis run)29.1%82.8%GPT-5 Mini
Humanity's Last Exam (Artificial Analysis run)5.3%21.5%GPT-5 Mini
GPQA Diamond (Epoch AI run)23.2%75.0%GPT-5 Mini
ARC-AGINot measured54.3%Only GPT-5 Mini measured
ARC-AGI-2Not measured4.4%Only GPT-5 Mini measured
Chess puzzlesNot measured24.0%Only GPT-5 Mini measured
Mystery game puzzlesNot measured10.0%Only GPT-5 Mini measured
VPCTNot measured40.2%Only GPT-5 Mini measured
LMArena Text: hard prompts12531380GPT-5 Mini
LMArena Text: expert12231379GPT-5 Mini
LMArena Text: hard prompts in English12531383GPT-5 Mini
LMArena Vision: diagramsNot measured1202Only GPT-5 Mini measured
LMArena Vision: homeworkNot measured1210Only GPT-5 Mini measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index05
Math benchmarks for Gemma 3 4B and GPT-5 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
AIMENot measured91.5%Only GPT-5 Mini measured
MATH 500 (Vals AI)Not measured94.8%Only GPT-5 Mini measured
MGSM (Vals AI)Not measured92.6%Only GPT-5 Mini measured
AA Math Index12.790.7GPT-5 Mini
AIME 2025 (Artificial Analysis run)12.7%90.7%GPT-5 Mini
OTIS Mock AIME7.5%86.7%GPT-5 Mini
FrontierMath, tiers 1 to 3Not measured46.7%Only GPT-5 Mini measured
FrontierMath, tier 4Not measured12.2%Only GPT-5 Mini measured
ProofBenchNot measured9.0%Only GPT-5 Mini measured
MATH level 5Not measured97.8%Only GPT-5 Mini measured
LMArena Text: math12391378GPT-5 Mini
LMArena Text: mathematical work12561380GPT-5 Mini
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Gemma 3 4B and GPT-5 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
MMLU ProNot measured82.2%Only GPT-5 Mini measured
LegalBench (Vals AI)Not measured81.8%Only GPT-5 Mini measured
CaseLaw (Vals AI)Not measured68.5%Only GPT-5 Mini measured
CorpFin (Vals AI)Not measured60.2%Only GPT-5 Mini measured
TaxEval (Vals AI)Not measured75.2%Only GPT-5 Mini measured
MortgageTax (Vals AI)Not measured66.9%Only GPT-5 Mini measured
MedQA (Vals AI)Not measured96.1%Only GPT-5 Mini measured
MedCode (Vals AI)Not measured43.0%Only GPT-5 Mini measured
MMLU Pro (Artificial Analysis run)41.7%83.7%GPT-5 Mini
SimpleQA VerifiedNot measured21.6%Only GPT-5 Mini measured
LMArena Text: science13061371GPT-5 Mini
LMArena Text: medicine and healthcare13421380GPT-5 Mini
LMArena Text: legal and government13271375GPT-5 Mini
LMArena Text: business and finance13111358GPT-5 Mini
Neither model has a result on the other 3 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Gemma 3 4B and GPT-5 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
Design Arena: websitesNot measured1125Only GPT-5 Mini measured
Design Arena: UI componentsNot measured1106Only GPT-5 Mini measured
Design Arena: game devNot measured1129Only GPT-5 Mini measured
Design Arena: data vizNot measured1130Only GPT-5 Mini measured
Design Arena: 3DNot measured1037Only GPT-5 Mini measured
Design Arena: all code categoriesNot measured1115Only GPT-5 Mini measured
Design Arena: SVGNot measured1091Only GPT-5 Mini measured
Design Arena: ASCII artNot measured1124Only GPT-5 Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index015
General benchmarks for Gemma 3 4B and GPT-5 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
SAGE (Vals AI)Not measured43.0%Only GPT-5 Mini measured
MedScribe (Vals AI)Not measured80.6%Only GPT-5 Mini measured
IFBench28.3%75.4%GPT-5 Mini
Long context reasoning (AA-LCR)6.7%72.3%GPT-5 Mini
DTBench50.9%80.5%GPT-5 Mini
LMCA2.8%34.2%GPT-5 Mini
Fiction.LiveBenchNot measured69.4%Only GPT-5 Mini measured
Creative writing (Lech Mazur)Not measured83.1%Only GPT-5 Mini measured
LMArena Text12911373GPT-5 Mini
LMArena Text: instruction following12391357GPT-5 Mini
LMArena Text: creative writing12701325GPT-5 Mini
LMArena VisionNot measured1202Only GPT-5 Mini measured
LMArena Text: English13001379GPT-5 Mini
LMArena Text: non-English12731363GPT-5 Mini
LMArena Text: ChineseNot measured1386Only GPT-5 Mini measured
LMArena Text: German12811366GPT-5 Mini
LMArena Text: JapaneseNot measured1341Only GPT-5 Mini measured
LMArena Text: KoreanNot measured1308Only GPT-5 Mini measured
LMArena Text: FrenchNot measured1386Only GPT-5 Mini measured
LMArena Text: SpanishNot measured1354Only GPT-5 Mini measured
LMArena Text: Russian12941362GPT-5 Mini
LMArena Text: PolishNot measured1378Only GPT-5 Mini measured
LMArena Text: multi-turn12551363GPT-5 Mini
LMArena Text: longer queries12731355GPT-5 Mini
LMArena Text: writing and language12881344GPT-5 Mini
LMArena Text: entertainment and media12331340GPT-5 Mini
LMArena Vision: EnglishNot measured1216Only GPT-5 Mini measured
LMArena Vision: ChineseNot measured1214Only GPT-5 Mini measured
LMArena Vision: reading textNot measured1199Only GPT-5 Mini measured
LMArena Vision: humorNot measured1205Only GPT-5 Mini measured
LMArena Vision: captioningNot measured1217Only GPT-5 Mini measured
LMArena Vision: recognizing thingsNot measured1226Only GPT-5 Mini measured
LMArena Vision: creative writingNot measured1181Only GPT-5 Mini 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 3 4B and GPT-5 Mini
BenchmarkGemma 3 4BGPT-5 MiniLeader
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 Mini$0.0013Fits 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 Mini$0.018Fits 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 Mini$0.070Fits 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 Mini
SpecificationGoogle Gemma 3 4BOpenAI GPT-5 Mini
MakerGoogleOpenAI
WeightsOpen weightsNo public weights listed
ReleasedMarch 13, 2025August 7, 2025
Context window131K400K
Input $/Mtok$0.045$0.25
Output $/Mtok$0.075$2.00
Coding indexNot benchmarked34.2
Independent measurements behind it02
Cost per solved taskNot computable$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 4B better than GPT-5 Mini for coding?

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; Gemma 3 4B has none, so the two cannot be ranked on coding. Gemma 3 4B has the edge where output tokens cost 26.7x less.

Which is cheaper, Gemma 3 4B or GPT-5 Mini?

Gemma 3 4B costs $0.045 per million input tokens and $0.075 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Cost per solved task is known for GPT-5 Mini only.

Which has the bigger context window, Gemma 3 4B or GPT-5 Mini?

GPT-5 Mini, with 400K tokens against 131K.

How many benchmarks is the Gemma 3 4B vs GPT-5 Mini comparison based on?

38 benchmarks have a result for both models as of October 21, 2026. Gemma 3 4B's coding index rests on 0 independent benchmarks and GPT-5 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next