Enter opens the highlighted result. Esc closes.

Gemma 3 4B vs GPT-5.1-Codex-Mini

GPT-5.1-Codex-Mini leads Gemma 3 4B on the Artificial Analysis Intelligence Index, 20.4 to 4.8, and Gemma 3 4B costs 26.7x less per output token ($0.075 vs $2.00 per million). Updated October 21, 2026; 11 benchmarks have a result for both.

Replace Gemma 3 4B Replace GPT-5.1-Codex-Mini
Gemma 3 4BGoogle
Coding
No data
Overall
4.8
Output $/M
$0.075
0
GPT-5.1-Codex-MiniOpenAI
Coding
No data
Overall
20.4
Output $/M
$2.00
11
vs boards won of 11 shared

Gemma 3 4B or GPT-5.1-Codex-Mini: which to pick

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

Pick Gemma 3 4B for output tokens 26.7x cheaper ($0.075 vs $2.00 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AGemma 3 4BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-5.1-Codex-MiniOpenAINot benchmarked1 independent benchmarkNo cost per solved task
Shared results
11
Gemma 3 4B only
28
GPT-5.1-Codex-Mini only
11
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-5.1-Codex-Mini not benchmarked.
Widest category
Math, 79.0 points apart on average over 2 shared benchmarks.
Widest single gap
AA Math Index: Gemma 3 4B 12.7 against GPT-5.1-Codex-Mini 91.7, 79.0 points apart on a 0 to 100 scale.
Output price
Gemma 3 4B $0.075 against GPT-5.1-Codex-Mini $2.00 per million output tokens, 26.7x apart.
Context window
Gemma 3 4B takes 131K tokens, GPT-5.1-Codex-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-5.1-Codex-MiniTies
Coding02
Intelligence01
Agentic work01
Reasoning02
Math02
Knowledge01
General02
All shared boards011
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Gemma 3 4B and GPT-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-MiniLeader
LMArena WebDevNot measured1244Only GPT-5.1-Codex-Mini measured
AA Coding Index2.7Not measuredOnly Gemma 3 4B measured
LiveCodeBench (Artificial Analysis run)11.2%83.6%GPT-5.1-Codex-Mini
Terminal-Bench Hard (Artificial Analysis run)0.8%33.3%GPT-5.1-Codex-Mini
Terminal-BenchNot measured61.6%Only GPT-5.1-Codex-Mini measured
LMArena Text: coding1230Not measuredOnly Gemma 3 4B measured
LMArena Text: software and IT1269Not measuredOnly Gemma 3 4B measured
LMArena WebDev: HTMLNot measured1253Only GPT-5.1-Codex-Mini measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 3 4B and GPT-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-MiniLeader
AA Intelligence Index4.820.4GPT-5.1-Codex-Mini
Epoch Capabilities Index115.9Not measuredOnly Gemma 3 4B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 3 4B and GPT-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-MiniLeader
τ²-Bench Telecom5.0%62.9%GPT-5.1-Codex-Mini
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
Reasoning benchmarks for Gemma 3 4B and GPT-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-MiniLeader
GPQA Diamond (Artificial Analysis run)29.1%81.3%GPT-5.1-Codex-Mini
Humanity's Last Exam (Artificial Analysis run)5.3%18.5%GPT-5.1-Codex-Mini
GPQA Diamond (Epoch AI run)23.2%Not measuredOnly Gemma 3 4B measured
LMArena Text: hard prompts1253Not measuredOnly Gemma 3 4B measured
LMArena Text: expert1223Not measuredOnly Gemma 3 4B measured
LMArena Text: hard prompts in English1253Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Gemma 3 4B and GPT-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-MiniLeader
AA Math Index12.791.7GPT-5.1-Codex-Mini
AIME 2025 (Artificial Analysis run)12.7%91.7%GPT-5.1-Codex-Mini
OTIS Mock AIME7.5%Not measuredOnly Gemma 3 4B measured
LMArena Text: math1239Not measuredOnly Gemma 3 4B measured
LMArena Text: mathematical work1256Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
Knowledge benchmarks for Gemma 3 4B and GPT-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-MiniLeader
MMLU Pro (Artificial Analysis run)41.7%82.0%GPT-5.1-Codex-Mini
LMArena Text: science1306Not measuredOnly Gemma 3 4B measured
LMArena Text: medicine and healthcare1342Not measuredOnly Gemma 3 4B measured
LMArena Text: legal and government1327Not measuredOnly Gemma 3 4B measured
LMArena Text: business and finance1311Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 12 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-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-MiniLeader
Design Arena: websitesNot measured1111Only GPT-5.1-Codex-Mini measured
Design Arena: UI componentsNot measured1081Only GPT-5.1-Codex-Mini measured
Design Arena: game devNot measured1092Only GPT-5.1-Codex-Mini measured
Design Arena: data vizNot measured1097Only GPT-5.1-Codex-Mini measured
Design Arena: 3DNot measured988Only GPT-5.1-Codex-Mini measured
Design Arena: all code categoriesNot measured1094Only GPT-5.1-Codex-Mini measured
Design Arena: SVGNot measured978Only GPT-5.1-Codex-Mini measured
Design Arena: ASCII artNot measured1105Only GPT-5.1-Codex-Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
General benchmarks for Gemma 3 4B and GPT-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-MiniLeader
IFBench28.3%67.9%GPT-5.1-Codex-Mini
Long context reasoning (AA-LCR)6.7%66.7%GPT-5.1-Codex-Mini
DTBench50.9%Not measuredOnly Gemma 3 4B measured
LMCA2.8%Not measuredOnly Gemma 3 4B measured
LMArena Text1291Not measuredOnly Gemma 3 4B measured
LMArena Text: instruction following1239Not measuredOnly Gemma 3 4B measured
LMArena Text: creative writing1270Not measuredOnly Gemma 3 4B measured
LMArena Text: English1300Not measuredOnly Gemma 3 4B measured
LMArena Text: non-English1273Not measuredOnly Gemma 3 4B measured
LMArena Text: German1281Not measuredOnly Gemma 3 4B measured
LMArena Text: Russian1294Not measuredOnly Gemma 3 4B measured
LMArena Text: multi-turn1255Not measuredOnly Gemma 3 4B measured
LMArena Text: longer queries1273Not measuredOnly Gemma 3 4B measured
LMArena Text: writing and language1288Not measuredOnly Gemma 3 4B measured
LMArena Text: entertainment and media1233Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 31 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-5.1-Codex-Mini
BenchmarkGemma 3 4BGPT-5.1-Codex-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-5.1-Codex-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-5.1-Codex-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-5.1-Codex-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-5.1-Codex-Mini
SpecificationGoogle Gemma 3 4BOpenAI GPT-5.1-Codex-Mini
MakerGoogleOpenAI
WeightsOpen weightsNo public weights listed
ReleasedMarch 13, 2025November 13, 2025
Context window131K400K
Input $/Mtok$0.045$0.25
Output $/Mtok$0.075$2.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 4B better than GPT-5.1-Codex-Mini for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 4B for output tokens 26.7x cheaper ($0.075 vs $2.00 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, Gemma 3 4B or GPT-5.1-Codex-Mini?

Gemma 3 4B costs $0.045 per million input tokens and $0.075 per million output tokens; GPT-5.1-Codex-Mini costs $0.25 and $2.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 3 4B or GPT-5.1-Codex-Mini?

GPT-5.1-Codex-Mini, with 400K tokens against 131K.

How many benchmarks is the Gemma 3 4B vs GPT-5.1-Codex-Mini comparison based on?

11 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-5.1-Codex-Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next