Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Qwen3.5 397B A17B

Qwen3.5 397B A17B leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 21.4 to 10.0, and gpt-oss-20b costs 15.6x less per output token ($0.15 vs $2.34 per million). Updated October 22, 2026; 43 benchmarks have a result for both.

Replace gpt-oss-20b Replace Qwen3.5 397B A17B
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
0
Qwen3.5 397B A17BQwen
Coding
No data
Overall
57.1
Output $/M
$2.34
43
vs boards won of 43 shared

gpt-oss-20b or Qwen3.5 397B A17B: 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 15.6x cheaper ($0.15 vs $2.34 per million) and work measured by SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
43
gpt-oss-20b only
19
Qwen3.5 397B A17B only
22
Like-for-like categories
8 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, Qwen3.5 397B A17B not benchmarked.
Widest category
Web design, 36.3 points apart on average over 2 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): gpt-oss-20b 34.7% against Qwen3.5 397B A17B 77.3%, 42.7 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Qwen3.5 397B A17B $2.34 per million output tokens, 15.6x apart.
Context window
gpt-oss-20b takes 131K tokens, Qwen3.5 397B A17B 262K.

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-20bBarsQwen3.5 397B A17BTies
Coding05
Intelligence02
Agentic work01
Reasoning06
Math03
Knowledge04
Web design02
General020
All shared boards043
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
Coding benchmarks for gpt-oss-20b and Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
LMArena WebDevNot measured1400Only Qwen3.5 397B A17B measured
LiveCodeBench (Vals AI)80.4%Not measuredOnly gpt-oss-20b measured
LiveCodeBench (Artificial Analysis run)77.7%Not measuredOnly gpt-oss-20b measured
SciCode38.9%44.8%Qwen3.5 397B A17B
Terminal-Bench Hard (Artificial Analysis run)10.6%40.9%Qwen3.5 397B A17B
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
WeirdML40.9%Not measuredOnly gpt-oss-20b measured
ALE-Bench566.0621.9Qwen3.5 397B A17B
LMArena Text: coding13071464Qwen3.5 397B A17B
LMArena Text: software and IT13111463Qwen3.5 397B A17B
LMArena WebDev: ReactNot measured1388Only Qwen3.5 397B A17B measured
LMArena WebDev: HTMLNot measured1410Only Qwen3.5 397B A17B measured
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for gpt-oss-20b and Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
AA Intelligence Index10.021.4Qwen3.5 397B A17B
Epoch Capabilities Index137.7146.8Qwen3.5 397B A17B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for gpt-oss-20b and Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
τ²-Bench Telecom60.2%95.6%Qwen3.5 397B A17B
APEX-AgentsNot measured24.9%Only Qwen3.5 397B A17B measured
BrowseComp-Plus50.6%Not measuredOnly 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 index06
Reasoning benchmarks for gpt-oss-20b and Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
GPQA Diamond68.9%Not measuredOnly gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)68.8%89.3%Qwen3.5 397B A17B
Humanity's Last Exam (Artificial Analysis run)11.0%29.0%Qwen3.5 397B A17B
GPQA Diamond (Epoch AI run)60.8%86.4%Qwen3.5 397B A17B
Mystery game puzzlesNot measured18.0%Only Qwen3.5 397B A17B measured
LMArena Text: hard prompts12741448Qwen3.5 397B A17B
LMArena Text: expert12581462Qwen3.5 397B A17B
LMArena Text: hard prompts in English12921450Qwen3.5 397B A17B
LMArena Vision: diagramsNot measured1277Only Qwen3.5 397B A17B measured
LMArena Vision: homeworkNot measured1292Only Qwen3.5 397B A17B measured
Kagi LLM Benchmark53.2%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for gpt-oss-20b and Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
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 Index89.3Not measuredOnly gpt-oss-20b measured
AIME 2025 (Artificial Analysis run)89.3%Not measuredOnly gpt-oss-20b measured
OTIS Mock AIME65.3%88.9%Qwen3.5 397B A17B
FrontierMath, tiers 1 to 3Not measured31.2%Only Qwen3.5 397B A17B measured
LMArena Text: math13171453Qwen3.5 397B A17B
LMArena Text: mathematical work13051454Qwen3.5 397B A17B
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for gpt-oss-20b and Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
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%Not measuredOnly gpt-oss-20b measured
LMArena Text: science12961457Qwen3.5 397B A17B
LMArena Text: medicine and healthcare13101455Qwen3.5 397B A17B
LMArena Text: legal and government12801441Qwen3.5 397B A17B
LMArena Text: business and finance12841435Qwen3.5 397B A17B
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index02
Web design benchmarks for gpt-oss-20b and Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
Design Arena: websites8521190Qwen3.5 397B A17B
Design Arena: UI componentsNot measured1161Only Qwen3.5 397B A17B measured
Design Arena: game devNot measured1140Only Qwen3.5 397B A17B measured
Design Arena: data viz9331175Qwen3.5 397B A17B
Design Arena: 3DNot measured1160Only Qwen3.5 397B A17B measured
Design Arena: all code categoriesNot measured1179Only Qwen3.5 397B A17B measured
Design Arena: SVGNot measured1139Only Qwen3.5 397B A17B measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for gpt-oss-20b and Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
IFBench65.1%78.8%Qwen3.5 397B A17B
Long context reasoning (AA-LCR)34.7%77.3%Qwen3.5 397B A17B
DTBench68.0%87.5%Qwen3.5 397B A17B
LMCA14.5%37.9%Qwen3.5 397B A17B
LMArena Text12881437Qwen3.5 397B A17B
LMArena Text: instruction following12361424Qwen3.5 397B A17B
LMArena Text: creative writing12011402Qwen3.5 397B A17B
LMArena VisionNot measured1262Only Qwen3.5 397B A17B measured
LMArena Text: English13031443Qwen3.5 397B A17B
LMArena Text: non-English12691430Qwen3.5 397B A17B
LMArena Text: Chinese13151498Qwen3.5 397B A17B
LMArena Text: German12551445Qwen3.5 397B A17B
LMArena Text: Japanese12441429Qwen3.5 397B A17B
LMArena Text: Korean12361384Qwen3.5 397B A17B
LMArena Text: FrenchNot measured1462Only Qwen3.5 397B A17B measured
LMArena Text: Spanish12671441Qwen3.5 397B A17B
LMArena Text: Russian12781430Qwen3.5 397B A17B
LMArena Text: Polish12521447Qwen3.5 397B A17B
LMArena Text: multi-turn12681446Qwen3.5 397B A17B
LMArena Text: longer queries12501441Qwen3.5 397B A17B
LMArena Text: writing and language12381415Qwen3.5 397B A17B
LMArena Text: entertainment and media12161399Qwen3.5 397B A17B
LMArena Vision: EnglishNot measured1268Only Qwen3.5 397B A17B measured
LMArena Vision: ChineseNot measured1314Only Qwen3.5 397B A17B measured
LMArena Vision: reading textNot measured1271Only Qwen3.5 397B A17B measured
LMArena Vision: humorNot measured1262Only Qwen3.5 397B A17B measured
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing thingsNot measured1265Only Qwen3.5 397B A17B measured
LMArena Vision: creative writingNot measured1260Only Qwen3.5 397B A17B measured
Neither model has a result on the other 17 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 Qwen3.5 397B A17B
Benchmarkgpt-oss-20bQwen3.5 397B A17BLeader
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
Qwen3.5 397B A17B$0.0016Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Qwen3.5 397B A17B$0.027Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Qwen3.5 397B A17B$0.101Fits in one request

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 Qwen3.5 397B A17B
SpecificationOpenAI gpt-oss-20bQwen3.5 397B A17B
MakerOpenAIQwen
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025February 16, 2026
Context window131K262K
Input $/Mtok$0.03$0.39
Output $/Mtok$0.15$2.34
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-20b better than Qwen3.5 397B A17B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 15.6x cheaper ($0.15 vs $2.34 per million) and work measured by SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, gpt-oss-20b or Qwen3.5 397B A17B?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or Qwen3.5 397B A17B?

Qwen3.5 397B A17B, with 262K tokens against 131K.

How many benchmarks is the gpt-oss-20b vs Qwen3.5 397B A17B comparison based on?

43 benchmarks have a result for both models as of October 22, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next