Qwen3.5 397B A17B vs Qwen3 Coder 30B A3B Instruct
Updated October 21, 2026. 10 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 Coder 30B A3B Instruct for coding: it scores 60.4 on the Vibe Coding Index against 28.6 for Qwen3.5 397B A17B.
Pick Qwen3.5 397B A17B when what matters is Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 10
- Qwen3.5 397B A17B only
- 55
- Qwen3 Coder 30B A3B Instruct only
- 6
- Like-for-like categories
- 6 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 Coder 30B A3B Instruct
Qwen3 Coder 30B A3B Instruct scores 60.4 against 28.6.
One benchmark behind each score
Intelligence
AA Intelligence Index
Qwen3.5 397B A17B
Qwen3.5 397B A17B leads, 21.4 against 9.6.
Same board, both measured
Web design
Design Arena: websites
Qwen3.5 397B A17B
Qwen3.5 397B A17B leads, 1191 against 1087.
Same board, both measured
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 Coder 30B A3B Instruct
Qwen3.5 397B A17B $0.0016, Qwen3 Coder 30B A3B Instruct $0.0002 per turn.
List prices
At a glance
- Coding index
- Qwen3.5 397B A17B 28.6 from 1 benchmark, Qwen3 Coder 30B A3B Instruct 60.4 from 1 benchmark.
- Widest category
- Agentic work, 61.1 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Qwen3.5 397B A17B 95.6% against Qwen3 Coder 30B A3B Instruct 34.5%, 61.1 points apart on a 0 to 100 scale.
- Output price
- Qwen3.5 397B A17B $2.34 against Qwen3 Coder 30B A3B Instruct $0.28 per million output tokens, 8.4x 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 397B A17B | Bars | Qwen3 Coder 30B A3B Instruct | Ties |
|---|---|---|---|---|
| Coding | 1 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| Web design | 3 | 0 | ||
| General | 2 | 0 | ||
| All shared boards | 10 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index10
| Benchmark | Qwen3.5 397B A17B | Qwen3 Coder 30B A3B Instruct | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 60.4% | Only Qwen3 Coder 30B A3B Instruct measured |
| SWE-bench Lite | Not measured | 49.7% | Only Qwen3 Coder 30B A3B Instruct measured |
| LMArena WebDev | 1400 | Not measured | Only Qwen3.5 397B A17B measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 40.3% | Only Qwen3 Coder 30B A3B Instruct measured |
| SciCode | 44.8% | Not measured | Only Qwen3.5 397B A17B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 40.9% | 15.2% | Qwen3.5 397B A17B |
| ALE-Bench | 621.9 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: coding | 1464 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: software and IT | 1463 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena WebDev: React | 1388 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena WebDev: HTML | 1410 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.5 397B A17B | Qwen3 Coder 30B A3B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.4 | 9.6 | Qwen3.5 397B A17B |
| Epoch Capabilities Index | 146.8 | Not measured | Only Qwen3.5 397B A17B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.5 397B A17B | Qwen3 Coder 30B A3B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 95.6% | 34.5% | Qwen3.5 397B A17B |
| APEX-Agents | 24.9% | Not measured | 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 index20
| Benchmark | Qwen3.5 397B A17B | Qwen3 Coder 30B A3B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 89.3% | 51.6% | Qwen3.5 397B A17B |
| Humanity's Last Exam (Artificial Analysis run) | 29.0% | 3.8% | Qwen3.5 397B A17B |
| GPQA Diamond (Epoch AI run) | 86.4% | Not measured | Only Qwen3.5 397B A17B measured |
| Mystery game puzzles | 18.0% | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: hard prompts | 1448 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: expert | 1462 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: hard prompts in English | 1450 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: diagrams | 1277 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: homework | 1292 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 12 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Qwen3.5 397B A17B | Qwen3 Coder 30B A3B Instruct | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 29.0 | Only Qwen3 Coder 30B A3B Instruct measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 29.0% | Only Qwen3 Coder 30B A3B Instruct measured |
| OTIS Mock AIME | 88.9% | Not measured | Only Qwen3.5 397B A17B measured |
| FrontierMath, tiers 1 to 3 | 31.2% | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: math | 1453 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: mathematical work | 1454 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Qwen3.5 397B A17B | Qwen3 Coder 30B A3B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 70.6% | Only Qwen3 Coder 30B A3B Instruct measured |
| LMArena Text: science | 1457 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: medicine and healthcare | 1455 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: legal and government | 1441 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: business and finance | 1435 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Qwen3.5 397B A17B | Qwen3 Coder 30B A3B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1191 | 1087 | Qwen3.5 397B A17B |
| Design Arena: UI components | 1163 | 1046 | Qwen3.5 397B A17B |
| Design Arena: game dev | 1141 | Not measured | Only Qwen3.5 397B A17B measured |
| Design Arena: data viz | 1175 | 1085 | Qwen3.5 397B A17B |
| Design Arena: 3D | 1161 | Not measured | Only Qwen3.5 397B A17B measured |
| Design Arena: all code categories | 1180 | Not measured | Only Qwen3.5 397B A17B measured |
| Design Arena: SVG | 1139 | Not measured | 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 index20
| Benchmark | Qwen3.5 397B A17B | Qwen3 Coder 30B A3B Instruct | Leader |
|---|---|---|---|
| IFBench | 78.8% | 32.7% | Qwen3.5 397B A17B |
| Long context reasoning (AA-LCR) | 77.3% | 32.7% | Qwen3.5 397B A17B |
| DTBench | 87.5% | Not measured | Only Qwen3.5 397B A17B measured |
| LMCA | 37.9% | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text | 1437 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: instruction following | 1424 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: creative writing | 1402 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision | 1262 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: English | 1443 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: non-English | 1430 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Chinese | 1498 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: German | 1445 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Japanese | 1429 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Korean | 1384 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: French | 1462 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Spanish | 1441 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Russian | 1430 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Polish | 1447 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: multi-turn | 1446 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: longer queries | 1441 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: writing and language | 1415 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: entertainment and media | 1399 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: English | 1268 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: Chinese | 1314 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: reading text | 1271 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: humor | 1262 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: captioning | 1230 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: recognizing things | 1265 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: creative writing | 1260 | Not measured | Only Qwen3.5 397B A17B measured |
| 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 397B A17B | Qwen3 Coder 30B A3B Instruct | 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 Coder 30B A3B Instruct costs less
Repository review
50K input + 3K output tokens
Qwen3 Coder 30B A3B Instruct costs less
Agent loop
200K input + 10K output tokens
Qwen3 Coder 30B A3B Instruct 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 397B A17B | Qwen3 Coder 30B A3B Instruct |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | Open weights | Open weights |
| Released | February 16, 2026 | July 31, 2025 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.39 | $0.07 |
| Output $/Mtok | $2.34 | $0.28 |
| Coding index | 28.6 | 60.4 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.5 397B A17B better than Qwen3 Coder 30B A3B Instruct for coding?
Pick Qwen3 Coder 30B A3B Instruct for coding: it scores 60.4 on the Vibe Coding Index against 28.6 for Qwen3.5 397B A17B. Pick Qwen3.5 397B A17B when what matters is Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Qwen3.5 397B A17B or Qwen3 Coder 30B A3B Instruct?
Qwen3.5 397B A17B costs $0.39 per million input tokens and $2.34 per million output tokens; Qwen3 Coder 30B A3B Instruct costs $0.07 and $0.28. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen3.5 397B A17B or Qwen3 Coder 30B A3B Instruct?
Neither: both take 262K tokens.
How many benchmarks is the Qwen3.5 397B A17B vs Qwen3 Coder 30B A3B Instruct comparison based on?
10 benchmarks have a result for both models as of October 21, 2026. Qwen3.5 397B A17B's coding index rests on 1 independent benchmark and Qwen3 Coder 30B A3B Instruct's on 1. Where only one model has a result, the page says so instead of naming a winner.