gpt-oss-120b vs Qwen3.5-Flash
Qwen3.5-Flash costs 1.9x less per output token than gpt-oss-120b ($0.26 vs $0.50 per million). Updated October 22, 2026; 44 benchmarks have a result for both.
gpt-oss-120b or Qwen3.5-Flash: which to pick
Only Qwen3.5-Flash has a coding score, 41.1 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding.
Pick gpt-oss-120b for work measured by ALE-Bench or AIME, where it leads.
- Shared results
- 44
- gpt-oss-120b only
- 41
- Qwen3.5-Flash only
- 11
- Like-for-like categories
- 6 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
Only Qwen3.5-Flash has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only gpt-oss-120b has a AA Intelligence Index result, 11.6.
Directional only
Agentic work
AA Agentic Index
No call
Only gpt-oss-120b has a AA Agentic Index result, 3.7.
Directional only
Reasoning
GPQA Diamond
Qwen3.5-Flash
Qwen3.5-Flash leads, 82.8% against 78.5%.
Same board, both measured
Math
AIME
gpt-oss-120b
gpt-oss-120b leads, 92.6% against 92.5%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.5-Flash
Qwen3.5-Flash leads, 84.1% against 79.2%.
Same board, both measured
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
Qwen3.5-Flash
Qwen3.5-Flash takes 1M tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5-Flash
gpt-oss-120b $0.0003, Qwen3.5-Flash $0.0002 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Qwen3.5-Flash
gpt-oss-120b $0.51, Qwen3.5-Flash $0.40.
Published attempt cost and pass rate
At a glance
- Coding index
- gpt-oss-120b not benchmarked, Qwen3.5-Flash 41.1 from 2 benchmarks.
- Widest category
- Coding, 10.3 points apart on average over 5 shared benchmarks.
- Widest single gap
- SWE-bench Verified (Vals AI): gpt-oss-120b 33.6% against Qwen3.5-Flash 64.4%, 30.8 points apart on a 0 to 100 scale.
- Output price
- gpt-oss-120b $0.50 against Qwen3.5-Flash $0.26 per million output tokens, 1.9x apart.
- Context window
- gpt-oss-120b takes 131K tokens, Qwen3.5-Flash 1M.
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 | Qwen3.5-Flash | Ties |
|---|---|---|---|---|
| Coding | 1 | 4 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 6 | ||
| Math | 2 | 2 | ||
| Knowledge | 0 | 9 | ||
| General | 0 | 19 | ||
| All shared boards | 3 | 41 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index14
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | Leader |
|---|---|---|---|
| Aider polyglot | 41.8% | Not measured | Only gpt-oss-120b measured |
| SWE-bench Verified | 26.0% | Not measured | Only gpt-oss-120b measured |
| LMArena WebDev | Not measured | 1244 | Only Qwen3.5-Flash measured |
| AA Coding Index | 30.4 | Not measured | Only gpt-oss-120b measured |
| LiveCodeBench (Vals AI) | 83.2% | 83.3% | Qwen3.5-Flash |
| SWE-bench Verified (Vals AI) | 33.6% | 64.4% | Qwen3.5-Flash |
| LiveCodeBench (Artificial Analysis run) | 87.8% | Not measured | Only gpt-oss-120b measured |
| SciCode | 34.0% | Not measured | Only gpt-oss-120b measured |
| Terminal-Bench Hard (Artificial Analysis run) | 23.5% | Not measured | Only gpt-oss-120b measured |
| 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 | 265.9 | gpt-oss-120b |
| LMArena Text: coding | 1379 | 1412 | Qwen3.5-Flash |
| LMArena Text: software and IT | 1387 | 1416 | Qwen3.5-Flash |
| LMArena WebDev: React | Not measured | 1229 | Only Qwen3.5-Flash measured |
| LMArena WebDev: HTML | Not measured | 1291 | Only Qwen3.5-Flash measured |
| SciCode | 7.7% | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.6 | Not measured | Only gpt-oss-120b measured |
| Epoch Capabilities Index | 139.8 | 143.5 | Qwen3.5-Flash |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AA Agentic Index | 3.7 | Not measured | Only gpt-oss-120b measured |
| τ²-Bench Telecom | 65.8% | Not measured | Only gpt-oss-120b measured |
| 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 |
| BrowseComp-Plus | 67.0% | Not measured | Only 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 index06
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 78.5% | 82.8% | Qwen3.5-Flash |
| MMMU Pro (Vals AI) | Not measured | 81.9% | Only Qwen3.5-Flash measured |
| GPQA Diamond (Artificial Analysis run) | 78.2% | Not measured | Only gpt-oss-120b measured |
| Humanity's Last Exam (Artificial Analysis run) | 19.6% | Not measured | Only gpt-oss-120b measured |
| GPQA Diamond (Epoch AI run) | 75.8% | 82.3% | Qwen3.5-Flash |
| SimpleBench | 22.1% | Not measured | Only gpt-oss-120b measured |
| Chess puzzles | Not measured | 14.0% | Only Qwen3.5-Flash measured |
| Mystery game puzzles | 2.0% | 20.0% | Qwen3.5-Flash |
| LMArena Text: hard prompts | 1364 | 1403 | Qwen3.5-Flash |
| LMArena Text: expert | 1356 | 1407 | Qwen3.5-Flash |
| LMArena Text: hard prompts in English | 1368 | 1409 | Qwen3.5-Flash |
| 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 index22
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AIME | 92.6% | 92.5% | gpt-oss-120b |
| 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 | Not measured | Only gpt-oss-120b measured |
| AIME 2025 (Artificial Analysis run) | 93.4% | Not measured | Only gpt-oss-120b measured |
| OTIS Mock AIME | 88.9% | 84.4% | gpt-oss-120b |
| FrontierMath, tiers 1 to 3 | Not measured | 18.2% | Only Qwen3.5-Flash measured |
| LMArena Text: math | 1389 | 1407 | Qwen3.5-Flash |
| LMArena Text: mathematical work | 1386 | 1413 | Qwen3.5-Flash |
| MathArena | 15.1% | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index09
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | Leader |
|---|---|---|---|
| MMLU Pro | 79.2% | 84.1% | Qwen3.5-Flash |
| LegalBench (Vals AI) | 75.9% | 84.3% | Qwen3.5-Flash |
| CaseLaw (Vals AI) | 48.8% | 56.0% | Qwen3.5-Flash |
| CorpFin (Vals AI) | 58.2% | 63.6% | Qwen3.5-Flash |
| TaxEval (Vals AI) | 71.6% | 72.2% | Qwen3.5-Flash |
| MortgageTax (Vals AI) | Not measured | 67.4% | Only Qwen3.5-Flash measured |
| MedQA (Vals AI) | 91.4% | Not measured | Only gpt-oss-120b measured |
| MedCode (Vals AI) | Not measured | 33.0% | Only Qwen3.5-Flash measured |
| MMLU Pro (Artificial Analysis run) | 80.8% | Not measured | Only gpt-oss-120b measured |
| SimpleQA Verified | Not measured | 20.3% | Only Qwen3.5-Flash measured |
| LMArena Text: science | 1382 | 1415 | Qwen3.5-Flash |
| LMArena Text: medicine and healthcare | 1388 | 1407 | Qwen3.5-Flash |
| LMArena Text: legal and government | 1355 | 1398 | Qwen3.5-Flash |
| LMArena Text: business and finance | 1359 | 1394 | Qwen3.5-Flash |
| 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 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 968 | Not measured | Only gpt-oss-120b measured |
| Design Arena: UI components | 924 | Not measured | Only gpt-oss-120b measured |
| Design Arena: game dev | 991 | 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 | 962 | 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 index019
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 42.5% | Only Qwen3.5-Flash measured |
| MedScribe (Vals AI) | Not measured | 70.6% | Only Qwen3.5-Flash measured |
| IFBench | 69.0% | Not measured | Only gpt-oss-120b measured |
| Long context reasoning (AA-LCR) | 52.0% | Not measured | Only gpt-oss-120b measured |
| DTBench | 76.3% | 82.9% | Qwen3.5-Flash |
| LMCA | 22.1% | 29.1% | Qwen3.5-Flash |
| 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 | 1397 | Qwen3.5-Flash |
| LMArena Text: instruction following | 1318 | 1374 | Qwen3.5-Flash |
| LMArena Text: creative writing | 1274 | 1343 | Qwen3.5-Flash |
| LMArena Text: English | 1375 | 1404 | Qwen3.5-Flash |
| LMArena Text: non-English | 1351 | 1385 | Qwen3.5-Flash |
| LMArena Text: Chinese | 1385 | 1445 | Qwen3.5-Flash |
| LMArena Text: German | 1353 | 1390 | Qwen3.5-Flash |
| LMArena Text: Japanese | 1331 | 1369 | Qwen3.5-Flash |
| LMArena Text: Korean | 1282 | 1344 | Qwen3.5-Flash |
| LMArena Text: French | 1370 | 1413 | Qwen3.5-Flash |
| LMArena Text: Spanish | 1389 | 1400 | Qwen3.5-Flash |
| LMArena Text: Russian | 1343 | 1380 | Qwen3.5-Flash |
| LMArena Text: Polish | 1353 | 1376 | Qwen3.5-Flash |
| LMArena Text: multi-turn | 1340 | 1393 | Qwen3.5-Flash |
| LMArena Text: longer queries | 1319 | 1392 | Qwen3.5-Flash |
| LMArena Text: writing and language | 1306 | 1369 | Qwen3.5-Flash |
| LMArena Text: entertainment and media | 1292 | 1347 | Qwen3.5-Flash |
| MultiChallenge | 45.3% | Not measured | Only gpt-oss-120b measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | gpt-oss-120b | Qwen3.5-Flash | 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
Qwen3.5-Flash costs less
Repository review
50K input + 3K output tokens
Qwen3.5-Flash costs less
Agent loop
200K input + 10K output tokens
Qwen3.5-Flash 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 | Qwen3.5-Flash |
|---|---|---|
| Maker | OpenAI | Qwen |
| Weights | Open weights | No public weights listed |
| Released | August 5, 2025 | February 25, 2026 |
| Context window | 131K | 1M |
| Input $/Mtok | $0.10 | $0.065 |
| Output $/Mtok | $0.50 | $0.26 |
| Coding index | Not benchmarked | 41.1 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $0.51 | $0.40 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is gpt-oss-120b better than Qwen3.5-Flash for coding?
Only Qwen3.5-Flash has a coding score, 41.1 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding. Pick gpt-oss-120b for work measured by ALE-Bench or AIME, where it leads.
Which is cheaper, gpt-oss-120b or Qwen3.5-Flash?
gpt-oss-120b costs $0.10 per million input tokens and $0.50 per million output tokens; Qwen3.5-Flash costs $0.065 and $0.26. Per solved SWE-bench Verified task, gpt-oss-120b costs $0.51 and Qwen3.5-Flash $0.40.
Which has the bigger context window, gpt-oss-120b or Qwen3.5-Flash?
Qwen3.5-Flash, with 1M tokens against 131K.
How many benchmarks is the gpt-oss-120b vs Qwen3.5-Flash comparison based on?
44 benchmarks have a result for both models as of October 22, 2026. gpt-oss-120b's coding index rests on 1 independent benchmark and Qwen3.5-Flash's on 2. Where only one model has a result, the page says so instead of naming a winner.