gpt-oss-120b vs Qwen3 32B
Updated October 21, 2026. 42 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Qwen3 32B for coding: it scores 40.0 on the Vibe Coding Index against 34.5 for gpt-oss-120b, though on 1 benchmark against 2.
Pick gpt-oss-120b when what matters is Aider polyglot or LiveCodeBench (Artificial Analysis run), where it leads.
- Shared results
- 42
- gpt-oss-120b only
- 36
- Qwen3 32B only
- 0
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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.
Coding
Vibe Coding Index, four public coding benchmarks
Qwen3 32B
Qwen3 32B scores 40.0 against 34.5.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
gpt-oss-120b
gpt-oss-120b leads, 11.6 against 7.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only gpt-oss-120b has a AA Agentic Index result, 3.7.
Directional only
Reasoning
GPQA Diamond
No call
Only gpt-oss-120b has a GPQA Diamond result, 78.5%.
Directional only
Math
AIME
No call
Only gpt-oss-120b has a AIME result, 92.6%.
Directional only
Knowledge
MMLU Pro
No call
Only gpt-oss-120b has a MMLU Pro result, 79.2%.
Directional only
Web design
Design Arena: websites
No call
Only gpt-oss-120b has a Design Arena: websites result, 968.
Directional only
Long documents
Listed context window
No call
Both take 131K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 32B
gpt-oss-120b $0.0004, Qwen3 32B $0.0002 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only gpt-oss-120b has the number, $0.51.
Directional only
At a glance
- Coding index
- gpt-oss-120b 34.5 from 2 benchmarks, Qwen3 32B 40.0 from 1 benchmark.
- Widest category
- Agentic work, 36.0 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): gpt-oss-120b 52.0% against Qwen3 32B 0.0%, 52.0 points apart on a 0 to 100 scale.
- Output price
- gpt-oss-120b $0.60 against Qwen3 32B $0.28 per million output tokens, 2.1x 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.
| Category | gpt-oss-120b | Bars | Qwen3 32B | Ties |
|---|---|---|---|---|
| Coding | 5 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 1 | ||
| Math | 3 | 2 | ||
| Knowledge | 5 | 0 | ||
| General | 14 | 3 | ||
| All shared boards | 35 | 7 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index51
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| Aider polyglot | 41.8% | 40.0% | gpt-oss-120b |
| SWE-bench Verified | 26.0% | Not measured | Only gpt-oss-120b measured |
| AA Coding Index | 30.4 | Not measured | Only gpt-oss-120b measured |
| LiveCodeBench (Vals AI) | 83.2% | Not measured | Only gpt-oss-120b measured |
| SWE-bench Verified (Vals AI) | 33.6% | Not measured | Only gpt-oss-120b measured |
| LiveCodeBench (Artificial Analysis run) | 87.8% | 54.6% | gpt-oss-120b |
| SciCode | 34.0% | 36.0% | Qwen3 32B |
| Terminal-Bench Hard (Artificial Analysis run) | 23.5% | 3.0% | gpt-oss-120b |
| Terminal-Bench | 18.7% | Not measured | Only gpt-oss-120b measured |
| WeirdML | 48.2% | Not measured | Only gpt-oss-120b measured |
| ALE-Bench | 575.6 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: coding | 1379 | 1357 | gpt-oss-120b |
| LMArena Text: software and IT | 1387 | 1366 | gpt-oss-120b |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.6 | 7.3 | gpt-oss-120b |
| Epoch Capabilities Index | 139.8 | 138.4 | gpt-oss-120b |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| AA Agentic Index | 3.7 | Not measured | Only gpt-oss-120b measured |
| τ²-Bench Telecom | 65.8% | 29.8% | gpt-oss-120b |
| APEX-Agents | 4.4% | Not measured | Only gpt-oss-120b measured |
| METR time horizons | 56.6% | Not measured | Only gpt-oss-120b measured |
| Vending-Bench 2 | -$22 | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| GPQA Diamond | 78.5% | Not measured | Only gpt-oss-120b measured |
| GPQA Diamond (Artificial Analysis run) | 78.2% | 66.8% | gpt-oss-120b |
| Humanity's Last Exam (Artificial Analysis run) | 19.6% | 7.4% | gpt-oss-120b |
| GPQA Diamond (Epoch AI run) | 75.8% | 65.7% | gpt-oss-120b |
| SimpleBench | 22.1% | Not measured | Only gpt-oss-120b measured |
| Mystery game puzzles | 2.0% | Not measured | Only gpt-oss-120b measured |
| LMArena Text: hard prompts | 1364 | 1334 | gpt-oss-120b |
| LMArena Text: expert | 1356 | 1362 | Qwen3 32B |
| LMArena Text: hard prompts in English | 1368 | 1350 | gpt-oss-120b |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| AIME | 92.6% | Not measured | Only gpt-oss-120b measured |
| MATH 500 (Vals AI) | 94.8% | Not measured | Only gpt-oss-120b measured |
| MGSM (Vals AI) | 92.0% | Not measured | Only gpt-oss-120b measured |
| AA Math Index | 93.4 | 73.0 | gpt-oss-120b |
| AIME 2025 (Artificial Analysis run) | 93.4% | 73.0% | gpt-oss-120b |
| OTIS Mock AIME | 88.9% | 66.9% | gpt-oss-120b |
| LMArena Text: math | 1389 | 1399 | Qwen3 32B |
| LMArena Text: mathematical work | 1386 | 1420 | Qwen3 32B |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| MMLU Pro | 79.2% | Not measured | Only gpt-oss-120b measured |
| LegalBench (Vals AI) | 75.9% | Not measured | Only gpt-oss-120b measured |
| CaseLaw (Vals AI) | 48.8% | Not measured | Only gpt-oss-120b measured |
| CorpFin (Vals AI) | 58.2% | Not measured | Only gpt-oss-120b measured |
| TaxEval (Vals AI) | 71.6% | Not measured | Only gpt-oss-120b measured |
| MedQA (Vals AI) | 91.4% | Not measured | Only gpt-oss-120b measured |
| MMLU Pro (Artificial Analysis run) | 80.8% | 79.8% | gpt-oss-120b |
| LMArena Text: science | 1382 | 1372 | gpt-oss-120b |
| LMArena Text: medicine and healthcare | 1388 | 1368 | gpt-oss-120b |
| LMArena Text: legal and government | 1355 | 1324 | gpt-oss-120b |
| LMArena Text: business and finance | 1359 | 1318 | gpt-oss-120b |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| Design Arena: websites | 968 | Not measured | Only gpt-oss-120b measured |
| Design Arena: UI components | 927 | Not measured | Only gpt-oss-120b measured |
| Design Arena: game dev | 992 | Not measured | Only gpt-oss-120b measured |
| Design Arena: data viz | 987 | Not measured | Only gpt-oss-120b measured |
| Design Arena: 3D | 901 | Not measured | Only gpt-oss-120b measured |
| Design Arena: all code categories | 963 | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index143
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| IFBench | 69.0% | 36.3% | gpt-oss-120b |
| Long context reasoning (AA-LCR) | 52.0% | 0.0% | gpt-oss-120b |
| DTBench | 76.3% | 67.5% | gpt-oss-120b |
| LMCA | 22.1% | 17.3% | gpt-oss-120b |
| Fiction.LiveBench | 44.4% | 74.2% | Qwen3 32B |
| Creative writing (Lech Mazur) | 77.1% | Not measured | Only gpt-oss-120b measured |
| Surface Evolver Bench | 25.0% | Not measured | Only gpt-oss-120b measured |
| LMArena Text | 1366 | 1340 | gpt-oss-120b |
| LMArena Text: instruction following | 1318 | 1305 | gpt-oss-120b |
| LMArena Text: creative writing | 1274 | 1297 | Qwen3 32B |
| LMArena Text: English | 1375 | 1359 | gpt-oss-120b |
| LMArena Text: non-English | 1351 | 1317 | gpt-oss-120b |
| LMArena Text: Chinese | 1385 | 1357 | gpt-oss-120b |
| LMArena Text: German | 1353 | 1341 | gpt-oss-120b |
| LMArena Text: Japanese | 1331 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: Korean | 1282 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: French | 1370 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: Spanish | 1389 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: Russian | 1343 | 1311 | gpt-oss-120b |
| LMArena Text: Polish | 1353 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: multi-turn | 1340 | 1331 | gpt-oss-120b |
| LMArena Text: longer queries | 1319 | 1327 | Qwen3 32B |
| LMArena Text: writing and language | 1306 | 1298 | gpt-oss-120b |
| LMArena Text: entertainment and media | 1292 | 1279 | gpt-oss-120b |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | gpt-oss-120b | Qwen3 32B | Leader |
|---|---|---|---|
| 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
Qwen3 32B costs less
Repository review
50K input + 3K output tokens
Qwen3 32B costs less
Agent loop
200K input + 10K output tokens
Qwen3 32B 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.
| Specification | OpenAI gpt-oss-120b | Qwen3 32B |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | Open weights | Open weights |
| Released | August 5, 2025 | April 28, 2025 |
| Context window | 131K | 131K |
| Input $/Mtok | $0.15 | $0.08 |
| Output $/Mtok | $0.60 | $0.28 |
| Coding index | 34.5 | 40.0 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $0.51 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is gpt-oss-120b better than Qwen3 32B for coding?
Pick Qwen3 32B for coding: it scores 40.0 on the Vibe Coding Index against 34.5 for gpt-oss-120b, though on 1 benchmark against 2. Pick gpt-oss-120b when what matters is Aider polyglot or LiveCodeBench (Artificial Analysis run), where it leads.
Which is cheaper, gpt-oss-120b or Qwen3 32B?
gpt-oss-120b costs $0.15 per million input tokens and $0.60 per million output tokens; Qwen3 32B costs $0.08 and $0.28. Cost per solved task is known for gpt-oss-120b only.
Which has the bigger context window, gpt-oss-120b or Qwen3 32B?
Neither: both take 131K tokens.
How many benchmarks is the gpt-oss-120b vs Qwen3 32B comparison based on?
42 benchmarks have a result for both models as of October 21, 2026. gpt-oss-120b's coding index rests on 2 independent benchmarks and Qwen3 32B's on 1. Where only one model has a result, the page says so instead of naming a winner.