Qwen3 Coder 480B A35B vs Qwen3 VL 30B A3B Instruct
Qwen3 Coder 480B A35B leads Qwen3 VL 30B A3B Instruct on the Artificial Analysis Intelligence Index, 11.9 to 7.9, and Qwen3 VL 30B A3B Instruct costs 2.1x less per output token ($0.70 vs $1.50 per million). Updated October 21, 2026; 10 benchmarks have a result for both.
Qwen3 Coder 480B A35B or Qwen3 VL 30B A3B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Qwen3 Coder 480B A35B for work measured by LiveCodeBench (Artificial Analysis run) or GPQA Diamond (Artificial Analysis run), where it leads.
- Shared results
- 10
- Qwen3 Coder 480B A35B only
- 43
- Qwen3 VL 30B A3B Instruct only
- 0
- Like-for-like categories
- 7 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 Coder 480B A35B
Qwen3 Coder 480B A35B leads, 11.9 against 7.9.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3 Coder 480B A35B has a Design Arena: websites result, 1159.
Directional only
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 VL 30B A3B Instruct
Qwen3 Coder 480B A35B $0.0010, Qwen3 VL 30B A3B Instruct $0.0006 per turn.
List prices
At a glance
- Coding index
- Qwen3 Coder 480B A35B not benchmarked, Qwen3 VL 30B A3B Instruct not benchmarked.
- Widest category
- Math, 43.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- AA Math Index: Qwen3 Coder 480B A35B 39.3 against Qwen3 VL 30B A3B Instruct 82.3, 43.0 points apart on a 0 to 100 scale.
- Output price
- Qwen3 Coder 480B A35B $1.50 against Qwen3 VL 30B A3B Instruct $0.70 per million output tokens, 2.1x 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 Coder 480B A35B | Bars | Qwen3 VL 30B A3B Instruct | Ties |
|---|---|---|---|---|
| Coding | 1 | 1 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 0 | 2 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 1 | ||
| General | 0 | 1 | ||
| All shared boards | 3 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index11
| Benchmark | Qwen3 Coder 480B A35B | Qwen3 VL 30B A3B Instruct | Leader |
|---|---|---|---|
| SWE-bench Verified | 69.6% | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena WebDev | 1275 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LiveCodeBench (Artificial Analysis run) | 58.5% | 69.7% | Qwen3 VL 30B A3B Instruct |
| Terminal-Bench Hard (Artificial Analysis run) | 18.9% | 6.1% | Qwen3 Coder 480B A35B |
| Terminal-Bench | 27.2% | Not measured | Only Qwen3 Coder 480B A35B measured |
| GSO-Bench | 4.9% | Not measured | Only Qwen3 Coder 480B A35B measured |
| WeirdML | 41.2% | Not measured | Only Qwen3 Coder 480B A35B measured |
| ALE-Bench | 461.4 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: coding | 1412 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: software and IT | 1393 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena WebDev: React | 1257 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena WebDev: HTML | 1287 | Not measured | Only Qwen3 Coder 480B A35B 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 Coder 480B A35B | Qwen3 VL 30B A3B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.9 | 7.9 | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3 Coder 480B A35B | Qwen3 VL 30B A3B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 43.6% | 19.9% | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 40 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3 Coder 480B A35B | Qwen3 VL 30B A3B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 61.8% | 72.0% | Qwen3 VL 30B A3B Instruct |
| Humanity's Last Exam (Artificial Analysis run) | 4.5% | 8.9% | Qwen3 VL 30B A3B Instruct |
| LMArena Text: hard prompts | 1372 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: expert | 1338 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: hard prompts in English | 1380 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Kagi LLM Benchmark | 49.5% | Not measured | Only Qwen3 Coder 480B A35B measured |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3 Coder 480B A35B | Qwen3 VL 30B A3B Instruct | Leader |
|---|---|---|---|
| AA Math Index | 39.3 | 82.3 | Qwen3 VL 30B A3B Instruct |
| AIME 2025 (Artificial Analysis run) | 39.3% | 82.3% | Qwen3 VL 30B A3B Instruct |
| LMArena Text: math | 1365 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: mathematical work | 1367 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3 Coder 480B A35B | Qwen3 VL 30B A3B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 78.8% | 80.7% | Qwen3 VL 30B A3B Instruct |
| LMArena Text: science | 1347 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: medicine and healthcare | 1347 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: legal and government | 1358 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: business and finance | 1343 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Qwen3 Coder 480B A35B | Qwen3 VL 30B A3B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1159 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Design Arena: UI components | 1113 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Design Arena: game dev | 1099 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Design Arena: data viz | 1084 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Design Arena: all code categories | 1143 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Neither model has a result on the other 4 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3 Coder 480B A35B | Qwen3 VL 30B A3B Instruct | Leader |
|---|---|---|---|
| IFBench | 40.5% | 45.1% | Qwen3 VL 30B A3B Instruct |
| Long context reasoning (AA-LCR) | 45.7% | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text | 1357 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: instruction following | 1355 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: creative writing | 1333 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: English | 1359 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: non-English | 1346 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: Chinese | 1357 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: German | 1325 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: Japanese | 1311 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: Korean | 1305 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: French | 1398 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: Spanish | 1360 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: Russian | 1366 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: Polish | 1344 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: multi-turn | 1366 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: longer queries | 1378 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: writing and language | 1340 | Not measured | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: entertainment and media | 1317 | Not measured | Only Qwen3 Coder 480B A35B measured |
| Neither model has a result on the other 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3 Coder 480B A35B | Qwen3 VL 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 VL 30B A3B Instruct costs less
Repository review
50K input + 3K output tokens
Qwen3 VL 30B A3B Instruct costs less
Agent loop
200K input + 10K output tokens
Qwen3 VL 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 Coder 480B A35B | Qwen3 VL 30B A3B Instruct |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | Open weights | Open weights |
| Released | July 23, 2025 | October 6, 2025 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.30 | $0.20 |
| Output $/Mtok | $1.50 | $0.70 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3 Coder 480B A35B better than Qwen3 VL 30B A3B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3 Coder 480B A35B for work measured by LiveCodeBench (Artificial Analysis run) or GPQA Diamond (Artificial Analysis run), where it leads.
Which is cheaper, Qwen3 Coder 480B A35B or Qwen3 VL 30B A3B Instruct?
Qwen3 Coder 480B A35B costs $0.30 per million input tokens and $1.50 per million output tokens; Qwen3 VL 30B A3B Instruct costs $0.20 and $0.70. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen3 Coder 480B A35B or Qwen3 VL 30B A3B Instruct?
Neither: both take 262K tokens.
How many benchmarks is the Qwen3 Coder 480B A35B vs Qwen3 VL 30B A3B Instruct comparison based on?
10 benchmarks have a result for both models as of October 21, 2026. Qwen3 Coder 480B A35B's coding index rests on 1 independent benchmark and Qwen3 VL 30B A3B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.