gpt-oss-120b vs Qwen3 235B A22B Instruct 2507
Qwen3 235B A22B Instruct 2507 leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 12.0 to 11.6, and gpt-oss-120b costs 1.6x less per output token ($0.50 vs $0.775 per million). Updated October 22, 2026; 21 benchmarks have a result for both.
gpt-oss-120b or Qwen3 235B A22B Instruct 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 1.6x cheaper ($0.50 vs $0.775 per million) and work measured by SciCode or AA Intelligence Index, where it leads.
- Shared results
- 21
- gpt-oss-120b only
- 64
- Qwen3 235B A22B Instruct 2507 only
- 3
- 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Qwen3 235B A22B Instruct 2507
Qwen3 235B A22B Instruct 2507 leads, 12.0 against 11.6.
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
Qwen3 235B A22B Instruct 2507
Qwen3 235B A22B Instruct 2507 leads, 1058 against 968.
Same board, both measured
Long documents
Listed context window
Qwen3 235B A22B Instruct 2507
Qwen3 235B A22B Instruct 2507 takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-120b
gpt-oss-120b $0.0003, Qwen3 235B A22B Instruct 2507 $0.0005 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 not benchmarked, Qwen3 235B A22B Instruct 2507 not benchmarked.
- Widest category
- Agentic work, 12.6 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): gpt-oss-120b 52.0% against Qwen3 235B A22B Instruct 2507 72.0%, 20.0 points apart on a 0 to 100 scale.
- Output price
- gpt-oss-120b $0.50 against Qwen3 235B A22B Instruct 2507 $0.775 per million output tokens, 1.6x apart.
- Context window
- gpt-oss-120b takes 131K tokens, Qwen3 235B A22B Instruct 2507 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.
| Category | gpt-oss-120b | Bars | Qwen3 235B A22B Instruct 2507 | Ties |
|---|---|---|---|---|
| Coding | 3 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 1 | 1 | ||
| Math | 2 | 0 | ||
| Knowledge | 0 | 1 | ||
| Web design | 1 | 5 | ||
| General | 1 | 3 | ||
| All shared boards | 9 | 12 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index31
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| Aider polyglot | 41.8% | Not measured | Only gpt-oss-120b measured |
| 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% | 78.8% | gpt-oss-120b |
| SciCode | 34.0% | 41.4% | Qwen3 235B A22B Instruct 2507 |
| Terminal-Bench Hard (Artificial Analysis run) | 23.5% | 15.2% | gpt-oss-120b |
| Terminal-Bench | 18.7% | Not measured | Only gpt-oss-120b measured |
| WeirdML | 48.2% | 38.7% | gpt-oss-120b |
| ALE-Bench | 575.6 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: coding | 1379 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: software and IT | 1387 | Not measured | Only gpt-oss-120b measured |
| SciCode | 7.7% | Not measured | Only 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
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.6 | 12.0 | Qwen3 235B A22B Instruct 2507 |
| Epoch Capabilities Index | 139.8 | Not measured | Only gpt-oss-120b measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| AA Agentic Index | 3.7 | Not measured | Only gpt-oss-120b measured |
| τ²-Bench Telecom | 65.8% | 53.2% | 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 |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 52.1% | Only Qwen3 235B A22B Instruct 2507 measured |
| BrowseComp-Plus | 67.0% | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| GPQA Diamond | 78.5% | Not measured | Only gpt-oss-120b measured |
| GPQA Diamond (Artificial Analysis run) | 78.2% | 79.0% | Qwen3 235B A22B Instruct 2507 |
| Humanity's Last Exam (Artificial Analysis run) | 19.6% | 15.9% | gpt-oss-120b |
| GPQA Diamond (Epoch AI run) | 75.8% | Not measured | Only gpt-oss-120b measured |
| ARC-AGI | Not measured | 11.0% | Only Qwen3 235B A22B Instruct 2507 measured |
| ARC-AGI-2 | Not measured | 1.3% | Only Qwen3 235B A22B Instruct 2507 measured |
| 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 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: expert | 1356 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: hard prompts in English | 1368 | Not measured | Only gpt-oss-120b measured |
| Kagi LLM Benchmark | 58.6% | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | 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 | 91.0 | gpt-oss-120b |
| AIME 2025 (Artificial Analysis run) | 93.4% | 91.0% | gpt-oss-120b |
| OTIS Mock AIME | 88.9% | Not measured | Only gpt-oss-120b measured |
| LMArena Text: math | 1389 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: mathematical work | 1386 | Not measured | Only gpt-oss-120b measured |
| MathArena | 15.1% | Not measured | Only 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 index01
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | 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% | 84.3% | Qwen3 235B A22B Instruct 2507 |
| LMArena Text: science | 1382 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: medicine and healthcare | 1388 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: legal and government | 1355 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: business and finance | 1359 | Not measured | Only gpt-oss-120b measured |
| PRBench Finance | 43.8% | Not measured | Only gpt-oss-120b measured |
| PRBench Legal | 40.2% | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| Design Arena: websites | 968 | 1058 | Qwen3 235B A22B Instruct 2507 |
| Design Arena: UI components | 924 | 963 | Qwen3 235B A22B Instruct 2507 |
| Design Arena: game dev | 991 | 951 | gpt-oss-120b |
| Design Arena: data viz | 987 | 1070 | Qwen3 235B A22B Instruct 2507 |
| Design Arena: 3D | 901 | 994 | Qwen3 235B A22B Instruct 2507 |
| Design Arena: all code categories | 962 | 1038 | Qwen3 235B A22B Instruct 2507 |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | Leader |
|---|---|---|---|
| IFBench | 69.0% | 51.2% | gpt-oss-120b |
| Long context reasoning (AA-LCR) | 52.0% | 72.0% | Qwen3 235B A22B Instruct 2507 |
| DTBench | 76.3% | 78.4% | Qwen3 235B A22B Instruct 2507 |
| LMCA | 22.1% | 23.5% | Qwen3 235B A22B Instruct 2507 |
| Fiction.LiveBench | 44.4% | Not measured | Only gpt-oss-120b measured |
| 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 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: instruction following | 1318 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: creative writing | 1274 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: English | 1375 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: non-English | 1351 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: Chinese | 1385 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: German | 1353 | Not measured | Only gpt-oss-120b measured |
| 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 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: Polish | 1353 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: multi-turn | 1340 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: longer queries | 1319 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: writing and language | 1306 | Not measured | Only gpt-oss-120b measured |
| LMArena Text: entertainment and media | 1292 | Not measured | Only gpt-oss-120b measured |
| MultiChallenge | 45.3% | Not measured | Only 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
| Benchmark | gpt-oss-120b | Qwen3 235B A22B Instruct 2507 | 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
gpt-oss-120b costs less
Repository review
50K input + 3K output tokens
gpt-oss-120b costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | OpenAI gpt-oss-120b | Qwen3 235B A22B Instruct 2507 |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | Open weights | Open weights |
| Released | August 5, 2025 | July 21, 2025 |
| Context window | 131K | 262K |
| Input $/Mtok | $0.10 | $0.145 |
| Output $/Mtok | $0.50 | $0.775 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | $0.51 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is gpt-oss-120b better than Qwen3 235B A22B Instruct 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 1.6x cheaper ($0.50 vs $0.775 per million) and work measured by SciCode or AA Intelligence Index, where it leads.
Which is cheaper, gpt-oss-120b or Qwen3 235B A22B Instruct 2507?
gpt-oss-120b costs $0.10 per million input tokens and $0.50 per million output tokens; Qwen3 235B A22B Instruct 2507 costs $0.145 and $0.775. Cost per solved task is known for gpt-oss-120b only.
Which has the bigger context window, gpt-oss-120b or Qwen3 235B A22B Instruct 2507?
Qwen3 235B A22B Instruct 2507, with 262K tokens against 131K.
How many benchmarks is the gpt-oss-120b vs Qwen3 235B A22B Instruct 2507 comparison based on?
21 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 Instruct 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.