Qwen3.5-122B-A10B vs Qwen3.5 397B A17B
Updated October 21, 2026. 50 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Qwen3.5 397B A17B for coding: it scores 28.6 on the Vibe Coding Index against 22.9 for Qwen3.5-122B-A10B.
Pick Qwen3.5-122B-A10B when output tokens cost 1.1x less.
- Shared results
- 50
- Qwen3.5-122B-A10B only
- 1
- Qwen3.5 397B A17B only
- 15
- 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
Qwen3.5 397B A17B
Qwen3.5 397B A17B scores 28.6 against 22.9.
One benchmark behind each score
Intelligence
AA Intelligence Index
Qwen3.5 397B A17B
Qwen3.5 397B A17B leads, 21.4 against 17.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3.5 397B A17B has a Design Arena: websites result, 1191.
Directional only
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5-122B-A10B
Qwen3.5-122B-A10B $0.0013, Qwen3.5 397B A17B $0.0016 per turn.
List prices
At a glance
- Coding index
- Qwen3.5-122B-A10B 22.9 from 1 benchmark, Qwen3.5 397B A17B 28.6 from 1 benchmark.
- Widest category
- Coding, 6.5 points apart on average over 7 shared benchmarks.
- Widest single gap
- LMArena Text: Japanese: Qwen3.5-122B-A10B 1367 against Qwen3.5 397B A17B 1429, 10.4 points apart on a 0 to 100 scale.
- Output price
- Qwen3.5-122B-A10B $2.08 against Qwen3.5 397B A17B $2.34 per million output tokens, 1.1x apart.
- Context window
- Both take 262K 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 | Qwen3.5-122B-A10B | Bars | Qwen3.5 397B A17B | Ties |
|---|---|---|---|---|
| Coding | 0 | 7 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 8 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 27 | ||
| All shared boards | 0 | 50 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index07
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| LMArena WebDev | 1361 | 1400 | Qwen3.5 397B A17B |
| AA Coding Index | 43.3 | Not measured | Only Qwen3.5-122B-A10B measured |
| SciCode | 39.7% | 44.8% | Qwen3.5 397B A17B |
| Terminal-Bench Hard (Artificial Analysis run) | 31.1% | 40.9% | Qwen3.5 397B A17B |
| ALE-Bench | Not measured | 621.9 | Only Qwen3.5 397B A17B measured |
| LMArena Text: coding | 1436 | 1464 | Qwen3.5 397B A17B |
| LMArena Text: software and IT | 1436 | 1463 | Qwen3.5 397B A17B |
| LMArena WebDev: React | 1353 | 1388 | Qwen3.5 397B A17B |
| LMArena WebDev: HTML | 1351 | 1410 | Qwen3.5 397B A17B |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| AA Intelligence Index | 17.7 | 21.4 | Qwen3.5 397B A17B |
| Epoch Capabilities Index | Not measured | 146.8 | Only Qwen3.5 397B A17B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 93.6% | 95.6% | Qwen3.5 397B A17B |
| APEX-Agents | Not measured | 24.9% | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 85.7% | 89.3% | Qwen3.5 397B A17B |
| Humanity's Last Exam (Artificial Analysis run) | 25.2% | 29.0% | Qwen3.5 397B A17B |
| GPQA Diamond (Epoch AI run) | Not measured | 86.4% | Only Qwen3.5 397B A17B measured |
| Mystery game puzzles | 17.0% | 18.0% | Qwen3.5 397B A17B |
| LMArena Text: hard prompts | 1421 | 1448 | Qwen3.5 397B A17B |
| LMArena Text: expert | 1431 | 1462 | Qwen3.5 397B A17B |
| LMArena Text: hard prompts in English | 1431 | 1450 | Qwen3.5 397B A17B |
| LMArena Vision: diagrams | 1249 | 1277 | Qwen3.5 397B A17B |
| LMArena Vision: homework | 1261 | 1292 | Qwen3.5 397B A17B |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 88.9% | Only Qwen3.5 397B A17B measured |
| FrontierMath, tiers 1 to 3 | Not measured | 31.2% | Only Qwen3.5 397B A17B measured |
| LMArena Text: math | 1431 | 1453 | Qwen3.5 397B A17B |
| LMArena Text: mathematical work | 1431 | 1454 | Qwen3.5 397B A17B |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| LMArena Text: science | 1432 | 1457 | Qwen3.5 397B A17B |
| LMArena Text: medicine and healthcare | 1423 | 1455 | Qwen3.5 397B A17B |
| LMArena Text: legal and government | 1422 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: business and finance | 1414 | 1435 | Qwen3.5 397B A17B |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1191 | Only Qwen3.5 397B A17B measured |
| Design Arena: UI components | Not measured | 1163 | Only Qwen3.5 397B A17B measured |
| Design Arena: game dev | Not measured | 1141 | Only Qwen3.5 397B A17B measured |
| Design Arena: data viz | Not measured | 1175 | Only Qwen3.5 397B A17B measured |
| Design Arena: 3D | Not measured | 1161 | Only Qwen3.5 397B A17B measured |
| Design Arena: all code categories | Not measured | 1180 | Only Qwen3.5 397B A17B measured |
| Design Arena: SVG | Not measured | 1139 | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index027
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| IFBench | 75.7% | 78.8% | Qwen3.5 397B A17B |
| Long context reasoning (AA-LCR) | 76.3% | 77.3% | Qwen3.5 397B A17B |
| DTBench | 84.3% | 87.5% | Qwen3.5 397B A17B |
| LMCA | 32.2% | 37.9% | Qwen3.5 397B A17B |
| LMArena Text | 1417 | 1437 | Qwen3.5 397B A17B |
| LMArena Text: instruction following | 1399 | 1424 | Qwen3.5 397B A17B |
| LMArena Text: creative writing | 1368 | 1402 | Qwen3.5 397B A17B |
| LMArena Vision | 1244 | 1262 | Qwen3.5 397B A17B |
| LMArena Text: English | 1428 | 1443 | Qwen3.5 397B A17B |
| LMArena Text: non-English | 1401 | 1430 | Qwen3.5 397B A17B |
| LMArena Text: Chinese | 1463 | 1498 | Qwen3.5 397B A17B |
| LMArena Text: German | 1425 | 1445 | Qwen3.5 397B A17B |
| LMArena Text: Japanese | 1367 | 1429 | Qwen3.5 397B A17B |
| LMArena Text: Korean | 1353 | 1384 | Qwen3.5 397B A17B |
| LMArena Text: French | 1443 | 1462 | Qwen3.5 397B A17B |
| LMArena Text: Spanish | 1425 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: Russian | 1400 | 1430 | Qwen3.5 397B A17B |
| LMArena Text: Polish | 1398 | 1447 | Qwen3.5 397B A17B |
| LMArena Text: multi-turn | 1416 | 1446 | Qwen3.5 397B A17B |
| LMArena Text: longer queries | 1410 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: writing and language | 1387 | 1415 | Qwen3.5 397B A17B |
| LMArena Text: entertainment and media | 1366 | 1399 | Qwen3.5 397B A17B |
| LMArena Vision: English | 1249 | 1268 | Qwen3.5 397B A17B |
| LMArena Vision: Chinese | 1301 | 1314 | Qwen3.5 397B A17B |
| LMArena Vision: reading text | 1251 | 1271 | Qwen3.5 397B A17B |
| LMArena Vision: humor | 1243 | 1262 | Qwen3.5 397B A17B |
| LMArena Vision: captioning | Not measured | 1230 | Only Qwen3.5 397B A17B measured |
| LMArena Vision: recognizing things | Not measured | 1265 | Only Qwen3.5 397B A17B measured |
| LMArena Vision: creative writing | 1220 | 1260 | Qwen3.5 397B A17B |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5 397B A17B | 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
Qwen3.5-122B-A10B costs less
Repository review
50K input + 3K output tokens
Qwen3.5-122B-A10B costs less
Agent loop
200K input + 10K output tokens
Qwen3.5-122B-A10B 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 | Qwen3.5-122B-A10B | Qwen3.5 397B A17B |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | Open weights | Open weights |
| Released | February 25, 2026 | February 16, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.26 | $0.39 |
| Output $/Mtok | $2.08 | $2.34 |
| Coding index | 22.9 | 28.6 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.5-122B-A10B better than Qwen3.5 397B A17B for coding?
Pick Qwen3.5 397B A17B for coding: it scores 28.6 on the Vibe Coding Index against 22.9 for Qwen3.5-122B-A10B. Pick Qwen3.5-122B-A10B when output tokens cost 1.1x less.
Which is cheaper, Qwen3.5-122B-A10B or Qwen3.5 397B A17B?
Qwen3.5-122B-A10B costs $0.26 per million input tokens and $2.08 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen3.5-122B-A10B or Qwen3.5 397B A17B?
Neither: both take 262K tokens.
How many benchmarks is the Qwen3.5-122B-A10B vs Qwen3.5 397B A17B comparison based on?
50 benchmarks have a result for both models as of October 21, 2026. Qwen3.5-122B-A10B's coding index rests on 1 independent benchmark and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.