Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Qwen3 32B

gpt-oss-20b leads Qwen3 32B on the Artificial Analysis Intelligence Index, 10.0 to 7.3, and gpt-oss-20b costs 2.7x less per output token ($0.15 vs $0.40 per million). Updated October 21, 2026; 42 benchmarks have a result for both.

Replace gpt-oss-20b Replace Qwen3 32B
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
14
Qwen3 32BQwen
Coding
No data
Overall
40.8
Output $/M
$0.40
28
vs boards won of 42 shared

gpt-oss-20b or Qwen3 32B: which to pick

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

Pick gpt-oss-20b for output tokens 2.7x cheaper ($0.15 vs $0.40 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3 32BQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
42
gpt-oss-20b only
20
Qwen3 32B only
3
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
gpt-oss-20b not benchmarked, Qwen3 32B not benchmarked.
Widest category
Agentic work, 35.1 points apart on average over 2 shared benchmarks.
Widest single gap
BrowseComp-Plus: gpt-oss-20b 50.6% against Qwen3 32B 10.7%, 39.9 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Qwen3 32B $0.40 per million output tokens, 2.7x 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
Categorygpt-oss-20bBarsQwen3 32BTies
Coding32
Intelligence11
Agentic work20
Reasoning34
Math23
Knowledge05
General313
All shared boards1428
CodingLike-for-likeSix of these boards feed the Vibe Coding Index32
Coding benchmarks for gpt-oss-20b and Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
Aider polyglotNot measured40.0%Only Qwen3 32B measured
LiveCodeBench (Vals AI)80.4%Not measuredOnly gpt-oss-20b measured
LiveCodeBench (Artificial Analysis run)77.7%54.6%gpt-oss-20b
SciCode38.9%36.0%gpt-oss-20b
Terminal-Bench Hard (Artificial Analysis run)10.6%3.0%gpt-oss-20b
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
WeirdML40.9%Not measuredOnly gpt-oss-20b measured
ALE-Bench566.0Not measuredOnly gpt-oss-20b measured
LMArena Text: coding13071357Qwen3 32B
LMArena Text: software and IT13111366Qwen3 32B
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for gpt-oss-20b and Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
AA Intelligence Index10.07.3gpt-oss-20b
Epoch Capabilities Index137.7138.4Qwen3 32B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for gpt-oss-20b and Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
τ²-Bench Telecom60.2%29.8%gpt-oss-20b
Berkeley Function Calling Leaderboard (BFCL)Not measured48.7%Only Qwen3 32B measured
BrowseComp-Plus50.6%10.7%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 index34
Reasoning benchmarks for gpt-oss-20b and Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
GPQA Diamond68.9%Not measuredOnly gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)68.8%66.8%gpt-oss-20b
Humanity's Last Exam (Artificial Analysis run)11.0%7.4%gpt-oss-20b
GPQA Diamond (Epoch AI run)60.8%65.7%Qwen3 32B
LMArena Text: hard prompts12741334Qwen3 32B
LMArena Text: expert12581362Qwen3 32B
LMArena Text: hard prompts in English12921350Qwen3 32B
Kagi LLM Benchmark53.2%48.7%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 index23
Math benchmarks for gpt-oss-20b and Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
AIME86.0%Not measuredOnly gpt-oss-20b measured
MATH 500 (Vals AI)94.2%Not measuredOnly gpt-oss-20b measured
MGSM (Vals AI)89.0%Not measuredOnly gpt-oss-20b measured
AA Math Index89.373.0gpt-oss-20b
AIME 2025 (Artificial Analysis run)89.3%73.0%gpt-oss-20b
OTIS Mock AIME65.3%66.9%Qwen3 32B
LMArena Text: math13171399Qwen3 32B
LMArena Text: mathematical work13051420Qwen3 32B
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for gpt-oss-20b and Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
MMLU Pro71.6%Not measuredOnly gpt-oss-20b measured
LegalBench (Vals AI)70.8%Not measuredOnly gpt-oss-20b measured
CaseLaw (Vals AI)43.8%Not measuredOnly gpt-oss-20b measured
CorpFin (Vals AI)53.1%Not measuredOnly gpt-oss-20b measured
TaxEval (Vals AI)63.7%Not measuredOnly gpt-oss-20b measured
MedQA (Vals AI)82.9%Not measuredOnly gpt-oss-20b measured
MMLU Pro (Artificial Analysis run)74.8%79.8%Qwen3 32B
LMArena Text: science12961372Qwen3 32B
LMArena Text: medicine and healthcare13101368Qwen3 32B
LMArena Text: legal and government12801324Qwen3 32B
LMArena Text: business and finance12841318Qwen3 32B
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 gpt-oss-20b and Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
Design Arena: websites852Not 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 index313
General benchmarks for gpt-oss-20b and Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
IFBench65.1%36.3%gpt-oss-20b
Long context reasoning (AA-LCR)34.7%0.0%gpt-oss-20b
DTBench68.0%67.5%gpt-oss-20b
LMCA14.5%17.3%Qwen3 32B
Fiction.LiveBenchNot measured74.2%Only Qwen3 32B measured
LMArena Text12881340Qwen3 32B
LMArena Text: instruction following12361305Qwen3 32B
LMArena Text: creative writing12011297Qwen3 32B
LMArena Text: English13031359Qwen3 32B
LMArena Text: non-English12691317Qwen3 32B
LMArena Text: Chinese13151357Qwen3 32B
LMArena Text: German12551341Qwen3 32B
LMArena Text: Japanese1244Not measuredOnly gpt-oss-20b measured
LMArena Text: Korean1236Not measuredOnly gpt-oss-20b measured
LMArena Text: Spanish1267Not measuredOnly gpt-oss-20b measured
LMArena Text: Russian12781311Qwen3 32B
LMArena Text: Polish1252Not measuredOnly gpt-oss-20b measured
LMArena Text: multi-turn12681331Qwen3 32B
LMArena Text: longer queries12501327Qwen3 32B
LMArena Text: writing and language12381298Qwen3 32B
LMArena Text: entertainment and media12161279Qwen3 32B
Neither model has a result on the other 25 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 Qwen3 32B
Benchmarkgpt-oss-20bQwen3 32BLeader
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
Qwen3 32B$0.0003Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Qwen3 32B$0.0082Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Qwen3 32B$0.032Exceeds 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 Qwen3 32B
SpecificationOpenAI gpt-oss-20bQwen3 32B
MakerOpenAIQwen
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025April 28, 2025
Context window131K131K
Input $/Mtok$0.03$0.14
Output $/Mtok$0.15$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-20b better than Qwen3 32B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 2.7x cheaper ($0.15 vs $0.40 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, gpt-oss-20b or Qwen3 32B?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Qwen3 32B costs $0.14 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or Qwen3 32B?

Neither: both take 131K tokens.

How many benchmarks is the gpt-oss-20b vs Qwen3 32B comparison based on?

42 benchmarks have a result for both models as of October 21, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Qwen3 32B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next