Enter opens the highlighted result. Esc closes.

Gemma 3 4B vs gpt-oss-20b

gpt-oss-20b leads Gemma 3 4B on the Artificial Analysis Intelligence Index, 10.0 to 4.8, and Gemma 3 4B costs 2.0x less per output token ($0.075 vs $0.15 per million). Updated October 21, 2026; 39 benchmarks have a result for both.

Replace Gemma 3 4B Replace gpt-oss-20b
Gemma 3 4BGoogle
Coding
No data
Overall
22.6
Output $/M
$0.075
13
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
26
vs boards won of 39 shared

Gemma 3 4B or gpt-oss-20b: 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 2.0x cheaper ($0.075 vs $0.15 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-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
39
Gemma 3 4B only
3
gpt-oss-20b only
23
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-oss-20b not benchmarked.
Widest category
Agentic work, 55.3 points apart on average over 1 shared benchmark.
Widest single gap
AIME 2025 (Artificial Analysis run): Gemma 3 4B 12.7% against gpt-oss-20b 89.3%, 76.7 points apart on a 0 to 100 scale.
Output price
Gemma 3 4B $0.075 against gpt-oss-20b $0.15 per million output tokens, 2.0x apart.
Context window
Both take 131K tokens.

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-oss-20bTies
Coding04
Intelligence02
Agentic work01
Reasoning07
Math05
Knowledge41
General96
All shared boards1326
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Gemma 3 4B and gpt-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
AA Coding Index2.7Not measuredOnly Gemma 3 4B measured
LiveCodeBench (Vals AI)Not measured80.4%Only gpt-oss-20b measured
LiveCodeBench (Artificial Analysis run)11.2%77.7%gpt-oss-20b
SciCodeNot measured38.9%Only gpt-oss-20b measured
Terminal-Bench Hard (Artificial Analysis run)0.8%10.6%gpt-oss-20b
Terminal-BenchNot measured3.4%Only gpt-oss-20b measured
WeirdMLNot measured40.9%Only gpt-oss-20b measured
ALE-BenchNot measured566.0Only gpt-oss-20b measured
LMArena Text: coding12301307gpt-oss-20b
LMArena Text: software and IT12691311gpt-oss-20b
SciCode0.0%Not measuredOnly Gemma 3 4B measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 3 4B and gpt-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
AA Intelligence Index4.810.0gpt-oss-20b
Epoch Capabilities Index115.9137.7gpt-oss-20b
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemma 3 4B and gpt-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
τ²-Bench Telecom5.0%60.2%gpt-oss-20b
Berkeley Function Calling Leaderboard (BFCL)19.6%Not measuredOnly Gemma 3 4B measured
BrowseComp-PlusNot measured50.6%Only gpt-oss-20b measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for Gemma 3 4B and gpt-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
GPQA DiamondNot measured68.9%Only gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)29.1%68.8%gpt-oss-20b
Humanity's Last Exam (Artificial Analysis run)5.3%11.0%gpt-oss-20b
GPQA Diamond (Epoch AI run)23.2%60.8%gpt-oss-20b
LMArena Text: hard prompts12531274gpt-oss-20b
LMArena Text: expert12231258gpt-oss-20b
LMArena Text: hard prompts in English12531292gpt-oss-20b
Kagi LLM Benchmark25.2%53.2%gpt-oss-20b
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index05
Math benchmarks for Gemma 3 4B and gpt-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
AIMENot measured86.0%Only gpt-oss-20b measured
MATH 500 (Vals AI)Not measured94.2%Only gpt-oss-20b measured
MGSM (Vals AI)Not measured89.0%Only gpt-oss-20b measured
AA Math Index12.789.3gpt-oss-20b
AIME 2025 (Artificial Analysis run)12.7%89.3%gpt-oss-20b
OTIS Mock AIME7.5%65.3%gpt-oss-20b
LMArena Text: math12391317gpt-oss-20b
LMArena Text: mathematical work12561305gpt-oss-20b
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
Knowledge benchmarks for Gemma 3 4B and gpt-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
MMLU ProNot measured71.6%Only gpt-oss-20b measured
LegalBench (Vals AI)Not measured70.8%Only gpt-oss-20b measured
CaseLaw (Vals AI)Not measured43.8%Only gpt-oss-20b measured
CorpFin (Vals AI)Not measured53.1%Only gpt-oss-20b measured
TaxEval (Vals AI)Not measured63.7%Only gpt-oss-20b measured
MedQA (Vals AI)Not measured82.9%Only gpt-oss-20b measured
MMLU Pro (Artificial Analysis run)41.7%74.8%gpt-oss-20b
LMArena Text: science13061296Gemma 3 4B
LMArena Text: medicine and healthcare13421310Gemma 3 4B
LMArena Text: legal and government13271280Gemma 3 4B
LMArena Text: business and finance13111284Gemma 3 4B
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Web design benchmarks for Gemma 3 4B and gpt-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
Design Arena: websitesNot measured852Only gpt-oss-20b measured
Design Arena: data vizNot measured933Only gpt-oss-20b measured
Neither model has a result on the other 7 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index96
General benchmarks for Gemma 3 4B and gpt-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
IFBench28.3%65.1%gpt-oss-20b
Long context reasoning (AA-LCR)6.7%34.7%gpt-oss-20b
DTBench50.9%68.0%gpt-oss-20b
LMCA2.8%14.5%gpt-oss-20b
LMArena Text12911288Gemma 3 4B
LMArena Text: instruction following12391236Gemma 3 4B
LMArena Text: creative writing12701201Gemma 3 4B
LMArena Text: English13001303gpt-oss-20b
LMArena Text: non-English12731269Gemma 3 4B
LMArena Text: ChineseNot measured1315Only gpt-oss-20b measured
LMArena Text: German12811255Gemma 3 4B
LMArena Text: JapaneseNot measured1244Only gpt-oss-20b measured
LMArena Text: KoreanNot measured1236Only gpt-oss-20b measured
LMArena Text: SpanishNot measured1267Only gpt-oss-20b measured
LMArena Text: Russian12941278Gemma 3 4B
LMArena Text: PolishNot measured1252Only gpt-oss-20b measured
LMArena Text: multi-turn12551268gpt-oss-20b
LMArena Text: longer queries12731250Gemma 3 4B
LMArena Text: writing and language12881238Gemma 3 4B
LMArena Text: entertainment and media12331216Gemma 3 4B
Neither model has a result on the other 26 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-oss-20b
BenchmarkGemma 3 4Bgpt-oss-20bLeader
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-oss-20b$0.0001Fits in one request

Gemma 3 4B costs less

Repository review

50K input + 3K output tokens

Gemma 3 4B$0.0025Fits in one request
gpt-oss-20b$0.0019Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

Gemma 3 4B$0.0097Exceeds the context window
gpt-oss-20b$0.0075Exceeds the context window

gpt-oss-20b 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-oss-20b
SpecificationGoogle Gemma 3 4BOpenAI gpt-oss-20b
MakerGoogleOpenAI
WeightsOpen weightsOpen weights
ReleasedMarch 13, 2025August 5, 2025
Context window131K131K
Input $/Mtok$0.045$0.03
Output $/Mtok$0.075$0.15
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 4B better than gpt-oss-20b for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 4B for output tokens 2.0x cheaper ($0.075 vs $0.15 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-oss-20b?

Gemma 3 4B costs $0.045 per million input tokens and $0.075 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 3 4B or gpt-oss-20b?

Neither: both take 131K tokens.

How many benchmarks is the Gemma 3 4B vs gpt-oss-20b comparison based on?

39 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-oss-20b's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next