Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs o3 Mini

Updated October 21, 2026. 53 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace gpt-oss-20b Replace o3 Mini
gpt-oss-20bOpenAI
Coding
No data
Overall
10.0
Output $/M
$0.15
6
o3 MiniOpenAI
Coding
No data
Overall
12.5
Output $/M
$4.40
47
vs boards won of 53 shared

Decision reading

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

gpt-oss-20b has the edge where output tokens cost 29.3x less, and where what matters is SciCode or WeirdML, where it leads.

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel Bo3 MiniOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
53
gpt-oss-20b only
7
o3 Mini only
17
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
gpt-oss-20b not benchmarked, o3 Mini not benchmarked.
Widest category
Agentic work, 28.9 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: gpt-oss-20b 60.2% against o3 Mini 31.3%, 28.9 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against o3 Mini $4.40 per million output tokens, 29.3x apart.
Context window
gpt-oss-20b takes 131K tokens, o3 Mini 200K.

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
Categorygpt-oss-20bBarso3 MiniTies
Coding34
Intelligence02
Agentic work10
Reasoning07
Math15
Knowledge19
General020
All shared boards647
CodingLike-for-likeSix of these boards feed the Vibe Coding Index34
Coding benchmarks for gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 MiniLeader
Aider polyglotNot measured60.4%Only o3 Mini measured
SWE-bench VerifiedNot measured42.4%Only o3 Mini measured
SWE-bench LiteNot measured32.3%Only o3 Mini measured
LiveCodeBench (Vals AI)80.4%71.5%gpt-oss-20b
LiveCodeBench (Artificial Analysis run)77.7%73.4%gpt-oss-20b
SciCode38.9%42.8%o3 Mini
Terminal-Bench Hard (Artificial Analysis run)10.6%6.8%gpt-oss-20b
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
GSO-BenchNot measured1.3%Only o3 Mini measured
WeirdML40.9%43.7%o3 Mini
CybenchNot measured22.5%Only o3 Mini measured
ALE-Bench566.0Not measuredOnly gpt-oss-20b measured
LMArena Text: coding13071378o3 Mini
LMArena Text: software and IT13111364o3 Mini
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 MiniLeader
AA Intelligence Index10.012.5o3 Mini
Epoch Capabilities Index137.7140.2o3 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 MiniLeader
τ²-Bench Telecom60.2%31.3%gpt-oss-20b
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 gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 MiniLeader
GPQA Diamond68.9%75.5%o3 Mini
GPQA Diamond (Artificial Analysis run)68.8%77.3%o3 Mini
Humanity's Last Exam (Artificial Analysis run)11.0%12.0%o3 Mini
GPQA Diamond (Epoch AI run)60.8%77.0%o3 Mini
ARC-AGINot measured34.5%Only o3 Mini measured
ARC-AGI-2Not measured3.0%Only o3 Mini measured
SimpleBenchNot measured22.8%Only o3 Mini measured
Chess puzzlesNot measured15.0%Only o3 Mini measured
Mystery game puzzlesNot measured7.0%Only o3 Mini measured
LMArena Text: hard prompts12741365o3 Mini
LMArena Text: expert12581364o3 Mini
LMArena Text: hard prompts in English12921375o3 Mini
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index15
Math benchmarks for gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 MiniLeader
AIME86.0%86.5%o3 Mini
MATH 500 (Vals AI)94.2%91.8%gpt-oss-20b
MGSM (Vals AI)89.0%91.3%o3 Mini
AA Math Index89.3Not measuredOnly gpt-oss-20b measured
AIME 2025 (Artificial Analysis run)89.3%Not measuredOnly gpt-oss-20b measured
OTIS Mock AIME65.3%76.9%o3 Mini
FrontierMath, tiers 1 to 3Not measured18.6%Only o3 Mini measured
FrontierMath, tier 4Not measured0.0%Only o3 Mini measured
MATH level 5Not measured96.5%Only o3 Mini measured
LMArena Text: math13171396o3 Mini
LMArena Text: mathematical work13051399o3 Mini
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 MiniLeader
MMLU Pro71.6%78.7%o3 Mini
LegalBench (Vals AI)70.8%71.5%o3 Mini
CaseLaw (Vals AI)43.8%Not measuredOnly gpt-oss-20b measured
CorpFin (Vals AI)53.1%45.3%gpt-oss-20b
TaxEval (Vals AI)63.7%69.4%o3 Mini
MedQA (Vals AI)82.9%94.8%o3 Mini
MMLU Pro (Artificial Analysis run)74.8%80.2%o3 Mini
SimpleQA VerifiedNot measured15.3%Only o3 Mini measured
LMArena Text: science12961339o3 Mini
LMArena Text: medicine and healthcare13101330o3 Mini
LMArena Text: legal and government12801328o3 Mini
LMArena Text: business and finance12841313o3 Mini
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Web design benchmarks for gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 MiniLeader
Design Arena: websites853Not measuredOnly gpt-oss-20b measured
Design Arena: data viz933Not measuredOnly 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 index020
General benchmarks for gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 MiniLeader
IFBench65.1%67.1%o3 Mini
Long context reasoning (AA-LCR)34.7%43.0%o3 Mini
DTBench68.0%68.8%o3 Mini
LMCA14.5%19.0%o3 Mini
Fiction.LiveBenchNot measured50.0%Only o3 Mini measured
Creative writing (Lech Mazur)Not measured61.7%Only o3 Mini measured
LMArena Text12881337o3 Mini
LMArena Text: instruction following12361337o3 Mini
LMArena Text: creative writing12011286o3 Mini
LMArena Text: English13031351o3 Mini
LMArena Text: non-English12691319o3 Mini
LMArena Text: Chinese13151379o3 Mini
LMArena Text: German12551303o3 Mini
LMArena Text: Japanese12441286o3 Mini
LMArena Text: Korean12361313o3 Mini
LMArena Text: FrenchNot measured1334Only o3 Mini measured
LMArena Text: Spanish12671321o3 Mini
LMArena Text: Russian12781304o3 Mini
LMArena Text: Polish12521294o3 Mini
LMArena Text: multi-turn12681320o3 Mini
LMArena Text: longer queries12501343o3 Mini
LMArena Text: writing and language12381313o3 Mini
LMArena Text: entertainment and media12161283o3 Mini
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for gpt-oss-20b and o3 Mini
Benchmarkgpt-oss-20bo3 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

gpt-oss-20b$0.0001Fits in one request
o3 Mini$0.0033Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
o3 Mini$0.068Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
o3 Mini$0.264Exceeds 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 gpt-oss-20b and o3 Mini
SpecificationOpenAI gpt-oss-20bOpenAI o3 Mini
MakerOpenAIOpenAI
WeightsOpen weightsNo public weights listed
ReleasedAugust 5, 2025January 31, 2025
Context window131K200K
Input $/Mtok$0.03$1.10
Output $/Mtok$0.15$4.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-20b better than o3 Mini for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. gpt-oss-20b has the edge where output tokens cost 29.3x less, and where what matters is SciCode or WeirdML, where it leads.

Which is cheaper, gpt-oss-20b or o3 Mini?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or o3 Mini?

o3 Mini, with 200K tokens against 131K.

How many benchmarks is the gpt-oss-20b vs o3 Mini comparison based on?

53 benchmarks have a result for both models as of October 21, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and o3 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next