Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Qwen3 VL 235B A22B Instruct

gpt-oss-20b leads Qwen3 VL 235B A22B Instruct on the Artificial Analysis Intelligence Index, 10.0 to 9.9, and gpt-oss-20b costs 12.7x less per output token ($0.15 vs $1.90 per million). Updated October 22, 2026; 38 benchmarks have a result for both.

Replace gpt-oss-20b Replace Qwen3 VL 235B A22B Instruct
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
6
Qwen3 VL 235B A22B InstructQwen
Coding
No data
Overall
No data
Output $/M
$1.90
32
vs boards won of 38 shared

gpt-oss-20b or Qwen3 VL 235B A22B Instruct: 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 12.7x cheaper ($0.15 vs $1.90 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3 VL 235B A22B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
38
gpt-oss-20b only
24
Qwen3 VL 235B A22B Instruct 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
gpt-oss-20b not benchmarked, Qwen3 VL 235B A22B Instruct not benchmarked.
Widest category
General, 24.7 points apart on average over 18 shared benchmarks.
Widest single gap
LMArena Text: expert: gpt-oss-20b 1258 against Qwen3 VL 235B A22B Instruct 1442, 30.7 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Qwen3 VL 235B A22B Instruct $1.90 per million output tokens, 12.7x apart.
Context window
gpt-oss-20b takes 131K tokens, Qwen3 VL 235B A22B Instruct 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 VL 235B A22B InstructTies
Coding13
Intelligence10
Agentic work10
Reasoning05
Math22
Knowledge05
General117
All shared boards632
CodingLike-for-likeSix of these boards feed the Vibe Coding Index13
Coding benchmarks for gpt-oss-20b and Qwen3 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
LiveCodeBench (Vals AI)80.4%Not measuredOnly gpt-oss-20b measured
LiveCodeBench (Artificial Analysis run)77.7%64.6%gpt-oss-20b
SciCode38.9%Not measuredOnly gpt-oss-20b measured
Terminal-Bench Hard (Artificial Analysis run)10.6%11.4%Qwen3 VL 235B A22B Instruct
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: coding13071438Qwen3 VL 235B A22B Instruct
LMArena Text: software and IT13111442Qwen3 VL 235B A22B Instruct
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for gpt-oss-20b and Qwen3 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
AA Intelligence Index10.09.9gpt-oss-20b
Epoch Capabilities Index137.7Not measuredOnly gpt-oss-20b measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for gpt-oss-20b and Qwen3 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
τ²-Bench Telecom60.2%54.1%gpt-oss-20b
BrowseComp-Plus50.6%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for gpt-oss-20b and Qwen3 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
GPQA Diamond68.9%Not measuredOnly gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)68.8%77.2%Qwen3 VL 235B A22B Instruct
Humanity's Last Exam (Artificial Analysis run)11.0%11.9%Qwen3 VL 235B A22B Instruct
GPQA Diamond (Epoch AI run)60.8%Not measuredOnly gpt-oss-20b measured
LMArena Text: hard prompts12741428Qwen3 VL 235B A22B Instruct
LMArena Text: expert12581442Qwen3 VL 235B A22B Instruct
LMArena Text: hard prompts in English12921439Qwen3 VL 235B A22B Instruct
LMArena Vision: diagramsNot measured1255Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: homeworkNot measured1277Only Qwen3 VL 235B A22B Instruct measured
Kagi LLM Benchmark53.2%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for gpt-oss-20b and Qwen3 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
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 Index89.388.3gpt-oss-20b
AIME 2025 (Artificial Analysis run)89.3%88.3%gpt-oss-20b
OTIS Mock AIME65.3%Not measuredOnly gpt-oss-20b measured
LMArena Text: math13171425Qwen3 VL 235B A22B Instruct
LMArena Text: mathematical work13051419Qwen3 VL 235B A22B Instruct
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 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
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%83.6%Qwen3 VL 235B A22B Instruct
LMArena Text: science12961444Qwen3 VL 235B A22B Instruct
LMArena Text: medicine and healthcare13101431Qwen3 VL 235B A22B Instruct
LMArena Text: legal and government12801438Qwen3 VL 235B A22B Instruct
LMArena Text: business and finance12841433Qwen3 VL 235B A22B Instruct
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 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
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 index117
General benchmarks for gpt-oss-20b and Qwen3 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
IFBench65.1%56.5%gpt-oss-20b
Long context reasoning (AA-LCR)34.7%63.7%Qwen3 VL 235B A22B Instruct
DTBench68.0%Not measuredOnly gpt-oss-20b measured
LMCA14.5%Not measuredOnly gpt-oss-20b measured
LMArena Text12881420Qwen3 VL 235B A22B Instruct
LMArena Text: instruction following12361406Qwen3 VL 235B A22B Instruct
LMArena Text: creative writing12011366Qwen3 VL 235B A22B Instruct
LMArena VisionNot measured1247Only Qwen3 VL 235B A22B Instruct measured
LMArena Text: English13031429Qwen3 VL 235B A22B Instruct
LMArena Text: non-English12691405Qwen3 VL 235B A22B Instruct
LMArena Text: Chinese13151463Qwen3 VL 235B A22B Instruct
LMArena Text: German12551424Qwen3 VL 235B A22B Instruct
LMArena Text: Japanese12441385Qwen3 VL 235B A22B Instruct
LMArena Text: Korean12361394Qwen3 VL 235B A22B Instruct
LMArena Text: FrenchNot measured1452Only Qwen3 VL 235B A22B Instruct measured
LMArena Text: Spanish12671428Qwen3 VL 235B A22B Instruct
LMArena Text: Russian12781408Qwen3 VL 235B A22B Instruct
LMArena Text: Polish12521419Qwen3 VL 235B A22B Instruct
LMArena Text: multi-turn12681428Qwen3 VL 235B A22B Instruct
LMArena Text: longer queries12501419Qwen3 VL 235B A22B Instruct
LMArena Text: writing and language12381392Qwen3 VL 235B A22B Instruct
LMArena Text: entertainment and media12161368Qwen3 VL 235B A22B Instruct
LMArena Vision: EnglishNot measured1256Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: ChineseNot measured1283Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: reading textNot measured1253Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: humorNot measured1209Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: captioningNot measured1281Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: recognizing thingsNot measured1249Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: creative writingNot measured1220Only Qwen3 VL 235B A22B Instruct 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 VL 235B A22B Instruct
Benchmarkgpt-oss-20bQwen3 VL 235B A22B InstructLeader
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 VL 235B A22B Instruct$0.0012Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Qwen3 VL 235B A22B Instruct$0.016Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Qwen3 VL 235B A22B Instruct$0.061Fits 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 VL 235B A22B Instruct
SpecificationOpenAI gpt-oss-20bQwen3 VL 235B A22B Instruct
MakerOpenAIQwen
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025September 23, 2025
Context window131K262K
Input $/Mtok$0.03$0.21
Output $/Mtok$0.15$1.90
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 VL 235B A22B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 12.7x cheaper ($0.15 vs $1.90 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, gpt-oss-20b or Qwen3 VL 235B A22B Instruct?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Qwen3 VL 235B A22B Instruct costs $0.21 and $1.90. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or Qwen3 VL 235B A22B Instruct?

Qwen3 VL 235B A22B Instruct, with 262K tokens against 131K.

How many benchmarks is the gpt-oss-20b vs Qwen3 VL 235B A22B Instruct comparison based on?

38 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 VL 235B A22B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next