Enter opens the highlighted result. Esc closes.

gpt-oss-120b vs Qwen3 235B A22B Thinking 2507

Qwen3 235B A22B Thinking 2507 leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 12.7 to 11.6, and gpt-oss-120b costs 7.0x less per output token ($0.50 vs $3.50 per million). Updated October 22, 2026; 45 benchmarks have a result for both.

Replace gpt-oss-120b Replace Qwen3 235B A22B Thinking 2507
gpt-oss-120bOpenAI
Coding
No data
Overall
50.0
Output $/M
$0.50
7
Qwen3 235B A22B Thinking 2507Qwen
Coding
No data
Overall
52.9
Output $/M
$3.50
38
vs boards won of 45 shared

gpt-oss-120b 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-120b for output tokens 7.0x cheaper ($0.50 vs $3.50 per million) and a larger context window (131K against 128K tokens).

Model Agpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved taskModel BQwen3 235B A22B Thinking 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
45
gpt-oss-120b only
40
Qwen3 235B A22B Thinking 2507 only
1
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-120b not benchmarked, Qwen3 235B A22B Thinking 2507 not benchmarked.
Widest category
General, 10.9 points apart on average over 20 shared benchmarks.
Widest single gap
Fiction.LiveBench: gpt-oss-120b 44.4% against Qwen3 235B A22B Thinking 2507 75.0%, 30.6 points apart on a 0 to 100 scale.
Output price
gpt-oss-120b $0.50 against Qwen3 235B A22B Thinking 2507 $3.50 per million output tokens, 7.0x apart.
Context window
gpt-oss-120b 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-120bBarsQwen3 235B A22B Thinking 2507Ties
Coding22
Intelligence01
Agentic work11
Reasoning05
Math12
Knowledge04
Web design24
General119
All shared boards738
CodingLike-for-likeSix of these boards feed the Vibe Coding Index22
Coding benchmarks for gpt-oss-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 235B A22B Thinking 2507Leader
Aider polyglot41.8%Not measuredOnly gpt-oss-120b measured
SWE-bench Verified26.0%Not measuredOnly gpt-oss-120b measured
AA Coding Index30.422.1gpt-oss-120b
LiveCodeBench (Vals AI)83.2%Not measuredOnly gpt-oss-120b measured
SWE-bench Verified (Vals AI)33.6%Not measuredOnly gpt-oss-120b measured
LiveCodeBench (Artificial Analysis run)87.8%Not measuredOnly gpt-oss-120b measured
SciCode34.0%Not measuredOnly gpt-oss-120b measured
Terminal-Bench Hard (Artificial Analysis run)23.5%Not measuredOnly gpt-oss-120b measured
Terminal-Bench18.7%Not measuredOnly gpt-oss-120b measured
WeirdML48.2%41.0%gpt-oss-120b
ALE-Bench575.6Not measuredOnly gpt-oss-120b measured
LMArena Text: coding13791424Qwen3 235B A22B Thinking 2507
LMArena Text: software and IT13871431Qwen3 235B A22B Thinking 2507
SciCode7.7%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for gpt-oss-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 235B A22B Thinking 2507Leader
AA Intelligence Index11.612.7Qwen3 235B A22B Thinking 2507
Epoch Capabilities Index139.8Not measuredOnly gpt-oss-120b measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for gpt-oss-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 235B A22B Thinking 2507Leader
AA Agentic Index3.71.3gpt-oss-120b
τ²-Bench Telecom65.8%Not measuredOnly gpt-oss-120b measured
APEX-Agents4.4%Not measuredOnly gpt-oss-120b measured
METR time horizons56.6%Not measuredOnly gpt-oss-120b measured
Vending-Bench 2-$22-$11Qwen3 235B A22B Thinking 2507
BrowseComp-Plus67.0%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for gpt-oss-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 235B A22B Thinking 2507Leader
GPQA Diamond78.5%Not measuredOnly gpt-oss-120b measured
GPQA Diamond (Artificial Analysis run)78.2%Not measuredOnly gpt-oss-120b measured
Humanity's Last Exam (Artificial Analysis run)19.6%Not measuredOnly gpt-oss-120b measured
GPQA Diamond (Epoch AI run)75.8%80.1%Qwen3 235B A22B Thinking 2507
SimpleBench22.1%Not measuredOnly gpt-oss-120b measured
Mystery game puzzles2.0%9.0%Qwen3 235B A22B Thinking 2507
LMArena Text: hard prompts13641416Qwen3 235B A22B Thinking 2507
LMArena Text: expert13561463Qwen3 235B A22B Thinking 2507
LMArena Text: hard prompts in English13681432Qwen3 235B A22B Thinking 2507
Kagi LLM Benchmark58.6%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for gpt-oss-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 235B A22B Thinking 2507Leader
AIME92.6%Not measuredOnly gpt-oss-120b measured
MATH 500 (Vals AI)94.8%Not measuredOnly gpt-oss-120b measured
MGSM (Vals AI)92.0%Not measuredOnly gpt-oss-120b measured
AA Math Index93.4Not measuredOnly gpt-oss-120b measured
AIME 2025 (Artificial Analysis run)93.4%Not measuredOnly gpt-oss-120b measured
OTIS Mock AIME88.9%86.7%gpt-oss-120b
LMArena Text: math13891412Qwen3 235B A22B Thinking 2507
LMArena Text: mathematical work13861435Qwen3 235B A22B Thinking 2507
MathArena15.1%Not measuredOnly gpt-oss-120b 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-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 235B A22B Thinking 2507Leader
MMLU Pro79.2%Not measuredOnly gpt-oss-120b measured
LegalBench (Vals AI)75.9%Not measuredOnly gpt-oss-120b measured
CaseLaw (Vals AI)48.8%Not measuredOnly gpt-oss-120b measured
CorpFin (Vals AI)58.2%Not measuredOnly gpt-oss-120b measured
TaxEval (Vals AI)71.6%Not measuredOnly gpt-oss-120b measured
MedQA (Vals AI)91.4%Not measuredOnly gpt-oss-120b measured
MMLU Pro (Artificial Analysis run)80.8%Not measuredOnly gpt-oss-120b measured
SimpleQA VerifiedNot measured40.4%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text: science13821433Qwen3 235B A22B Thinking 2507
LMArena Text: medicine and healthcare13881456Qwen3 235B A22B Thinking 2507
LMArena Text: legal and government13551415Qwen3 235B A22B Thinking 2507
LMArena Text: business and finance13591413Qwen3 235B A22B Thinking 2507
PRBench Finance43.8%Not measuredOnly gpt-oss-120b measured
PRBench Legal40.2%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index24
Web design benchmarks for gpt-oss-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 235B A22B Thinking 2507Leader
Design Arena: websites9681052Qwen3 235B A22B Thinking 2507
Design Arena: UI components924942Qwen3 235B A22B Thinking 2507
Design Arena: game dev991956gpt-oss-120b
Design Arena: data viz987950gpt-oss-120b
Design Arena: 3D901997Qwen3 235B A22B Thinking 2507
Design Arena: all code categories9621032Qwen3 235B A22B Thinking 2507
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index119
General benchmarks for gpt-oss-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 235B A22B Thinking 2507Leader
IFBench69.0%Not measuredOnly gpt-oss-120b measured
Long context reasoning (AA-LCR)52.0%Not measuredOnly gpt-oss-120b measured
DTBench76.3%80.3%Qwen3 235B A22B Thinking 2507
LMCA22.1%29.3%Qwen3 235B A22B Thinking 2507
Fiction.LiveBench44.4%75.0%Qwen3 235B A22B Thinking 2507
Creative writing (Lech Mazur)77.1%82.4%Qwen3 235B A22B Thinking 2507
Surface Evolver Bench25.0%Not measuredOnly gpt-oss-120b measured
LMArena Text13661415Qwen3 235B A22B Thinking 2507
LMArena Text: instruction following13181386Qwen3 235B A22B Thinking 2507
LMArena Text: creative writing12741384Qwen3 235B A22B Thinking 2507
LMArena Text: English13751429Qwen3 235B A22B Thinking 2507
LMArena Text: non-English13511397Qwen3 235B A22B Thinking 2507
LMArena Text: Chinese13851481Qwen3 235B A22B Thinking 2507
LMArena Text: German13531408Qwen3 235B A22B Thinking 2507
LMArena Text: Japanese13311386Qwen3 235B A22B Thinking 2507
LMArena Text: Korean12821375Qwen3 235B A22B Thinking 2507
LMArena Text: French1370Not measuredOnly gpt-oss-120b measured
LMArena Text: Spanish13891389gpt-oss-120b
LMArena Text: Russian13431401Qwen3 235B A22B Thinking 2507
LMArena Text: Polish13531390Qwen3 235B A22B Thinking 2507
LMArena Text: multi-turn13401406Qwen3 235B A22B Thinking 2507
LMArena Text: longer queries13191400Qwen3 235B A22B Thinking 2507
LMArena Text: writing and language13061388Qwen3 235B A22B Thinking 2507
LMArena Text: entertainment and media12921370Qwen3 235B A22B Thinking 2507
MultiChallenge45.3%Not measuredOnly gpt-oss-120b measured
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-120b and Qwen3 235B A22B Thinking 2507
Benchmarkgpt-oss-120bQwen3 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-120b$0.0003Fits in one request
Qwen3 235B A22B Thinking 2507$0.0022Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

gpt-oss-120b$0.0065Fits in one request
Qwen3 235B A22B Thinking 2507$0.033Fits in one request

gpt-oss-120b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-120b$0.025Exceeds the context window
Qwen3 235B A22B Thinking 2507$0.125Exceeds the context window

gpt-oss-120b 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-120b and Qwen3 235B A22B Thinking 2507
SpecificationOpenAI gpt-oss-120bQwen3 235B A22B Thinking 2507
MakerOpenAIQwen
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025July 25, 2025
Context window131K128K
Input $/Mtok$0.10$0.45
Output $/Mtok$0.50$3.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved task$0.51Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-120b 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-120b for output tokens 7.0x cheaper ($0.50 vs $3.50 per million) and a larger context window (131K against 128K tokens).

Which is cheaper, gpt-oss-120b or Qwen3 235B A22B Thinking 2507?

gpt-oss-120b costs $0.10 per million input tokens and $0.50 per million output tokens; Qwen3 235B A22B Thinking 2507 costs $0.45 and $3.50. Cost per solved task is known for gpt-oss-120b only.

Which has the bigger context window, gpt-oss-120b or Qwen3 235B A22B Thinking 2507?

gpt-oss-120b, with 131K tokens against 128K.

How many benchmarks is the gpt-oss-120b vs Qwen3 235B A22B Thinking 2507 comparison based on?

45 benchmarks have a result for both models as of October 22, 2026. gpt-oss-120b's coding index rests on 1 independent benchmark 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