Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Qwen3 235B A22B Thinking 2507

Qwen3 235B A22B Thinking 2507 leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 12.7 to 10.0, and gpt-oss-20b costs 23.3x less per output token ($0.15 vs $3.50 per million). Updated October 22, 2026; 35 benchmarks have a result for both.

Replace gpt-oss-20b Replace Qwen3 235B A22B Thinking 2507
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
0
Qwen3 235B A22B Thinking 2507Qwen
Coding
No data
Overall
52.9
Output $/M
$3.50
35
vs boards won of 35 shared

gpt-oss-20b or Qwen3 235B A22B Thinking 2507: 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 23.3x cheaper ($0.15 vs $3.50 per million) and a larger context window (131K against 128K tokens).

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3 235B A22B Thinking 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
35
gpt-oss-20b only
28
Qwen3 235B A22B Thinking 2507 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 235B A22B Thinking 2507 not benchmarked.
Widest category
Reasoning, 25.1 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Text: expert: gpt-oss-20b 1258 against Qwen3 235B A22B Thinking 2507 1463, 34.2 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Qwen3 235B A22B Thinking 2507 $3.50 per million output tokens, 23.3x apart.
Context window
gpt-oss-20b takes 131K tokens, Qwen3 235B A22B Thinking 2507 128K.

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 235B A22B Thinking 2507Ties
Coding03
Intelligence01
Reasoning04
Math03
Knowledge04
Web design02
General018
All shared boards035
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
AA Coding IndexNot measured22.1Only Qwen3 235B A22B Thinking 2507 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%Not measuredOnly gpt-oss-20b measured
Terminal-Bench Hard (Artificial Analysis run)10.6%Not measuredOnly gpt-oss-20b measured
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
WeirdML40.9%41.0%Qwen3 235B A22B Thinking 2507
ALE-Bench566.0Not measuredOnly gpt-oss-20b measured
LMArena Text: coding13071424Qwen3 235B A22B Thinking 2507
LMArena Text: software and IT13111431Qwen3 235B A22B Thinking 2507
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
AA Intelligence Index10.012.7Qwen3 235B A22B Thinking 2507
Epoch Capabilities Index137.7Not measuredOnly gpt-oss-20b measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Agentic work benchmarks for gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
AA Agentic IndexNot measured1.3Only Qwen3 235B A22B Thinking 2507 measured
τ²-Bench Telecom60.2%Not measuredOnly gpt-oss-20b measured
Vending-Bench 2Not measured-$11Only Qwen3 235B A22B Thinking 2507 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 index04
Reasoning benchmarks for gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
GPQA Diamond68.9%Not measuredOnly gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)68.8%Not measuredOnly gpt-oss-20b measured
Humanity's Last Exam (Artificial Analysis run)11.0%Not measuredOnly gpt-oss-20b measured
GPQA Diamond (Epoch AI run)60.8%80.1%Qwen3 235B A22B Thinking 2507
Mystery game puzzlesNot measured9.0%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text: hard prompts12741416Qwen3 235B A22B Thinking 2507
LMArena Text: expert12581463Qwen3 235B A22B Thinking 2507
LMArena Text: hard prompts in English12921432Qwen3 235B A22B Thinking 2507
Kagi LLM Benchmark53.2%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
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%86.7%Qwen3 235B A22B Thinking 2507
LMArena Text: math13171412Qwen3 235B A22B Thinking 2507
LMArena Text: mathematical work13051435Qwen3 235B A22B Thinking 2507
MathArena12.8%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
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
SimpleQA VerifiedNot measured40.4%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text: science12961433Qwen3 235B A22B Thinking 2507
LMArena Text: medicine and healthcare13101456Qwen3 235B A22B Thinking 2507
LMArena Text: legal and government12801415Qwen3 235B A22B Thinking 2507
LMArena Text: business and finance12841413Qwen3 235B A22B Thinking 2507
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index02
Web design benchmarks for gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
Design Arena: websites8521052Qwen3 235B A22B Thinking 2507
Design Arena: UI componentsNot measured942Only Qwen3 235B A22B Thinking 2507 measured
Design Arena: game devNot measured956Only Qwen3 235B A22B Thinking 2507 measured
Design Arena: data viz933950Qwen3 235B A22B Thinking 2507
Design Arena: 3DNot measured997Only Qwen3 235B A22B Thinking 2507 measured
Design Arena: all code categoriesNot measured1032Only Qwen3 235B A22B Thinking 2507 measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
IFBench65.1%Not measuredOnly gpt-oss-20b measured
Long context reasoning (AA-LCR)34.7%Not measuredOnly gpt-oss-20b measured
DTBench68.0%80.3%Qwen3 235B A22B Thinking 2507
LMCA14.5%29.3%Qwen3 235B A22B Thinking 2507
Fiction.LiveBenchNot measured75.0%Only Qwen3 235B A22B Thinking 2507 measured
Creative writing (Lech Mazur)Not measured82.4%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text12881415Qwen3 235B A22B Thinking 2507
LMArena Text: instruction following12361386Qwen3 235B A22B Thinking 2507
LMArena Text: creative writing12011384Qwen3 235B A22B Thinking 2507
LMArena Text: English13031429Qwen3 235B A22B Thinking 2507
LMArena Text: non-English12691397Qwen3 235B A22B Thinking 2507
LMArena Text: Chinese13151481Qwen3 235B A22B Thinking 2507
LMArena Text: German12551408Qwen3 235B A22B Thinking 2507
LMArena Text: Japanese12441386Qwen3 235B A22B Thinking 2507
LMArena Text: Korean12361375Qwen3 235B A22B Thinking 2507
LMArena Text: Spanish12671389Qwen3 235B A22B Thinking 2507
LMArena Text: Russian12781401Qwen3 235B A22B Thinking 2507
LMArena Text: Polish12521390Qwen3 235B A22B Thinking 2507
LMArena Text: multi-turn12681406Qwen3 235B A22B Thinking 2507
LMArena Text: longer queries12501400Qwen3 235B A22B Thinking 2507
LMArena Text: writing and language12381388Qwen3 235B A22B Thinking 2507
LMArena Text: entertainment and media12161370Qwen3 235B A22B Thinking 2507
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 gpt-oss-20b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-20bQwen3 235B A22B Thinking 2507Leader
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 235B A22B Thinking 2507$0.0022Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Qwen3 235B A22B Thinking 2507$0.033Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Qwen3 235B A22B Thinking 2507$0.125Exceeds 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 235B A22B Thinking 2507
SpecificationOpenAI gpt-oss-20bQwen3 235B A22B Thinking 2507
MakerOpenAIQwen
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025July 25, 2025
Context window131K128K
Input $/Mtok$0.03$0.45
Output $/Mtok$0.15$3.50
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 235B A22B Thinking 2507 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 23.3x cheaper ($0.15 vs $3.50 per million) and a larger context window (131K against 128K tokens).

Which is cheaper, gpt-oss-20b or Qwen3 235B A22B Thinking 2507?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Qwen3 235B A22B Thinking 2507 costs $0.45 and $3.50. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or Qwen3 235B A22B Thinking 2507?

gpt-oss-20b, with 131K tokens against 128K.

How many benchmarks is the gpt-oss-20b vs Qwen3 235B A22B Thinking 2507 comparison based on?

35 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 235B A22B Thinking 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next