Qwen3 30B A3B vs Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B leads Qwen3 30B A3B on the Artificial Analysis Intelligence Index, 11.9 to 7.6, and Qwen3 30B A3B costs 3.0x less per output token ($0.50 vs $1.50 per million). Updated October 21, 2026; 45 benchmarks have a result for both.
Qwen3 30B A3B or Qwen3 Coder 480B A35B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Qwen3 30B A3B for output tokens 3.0x cheaper ($0.50 vs $1.50 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
- Shared results
- 45
- Qwen3 30B A3B only
- 7
- Qwen3 Coder 480B A35B only
- 8
- 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 Coder 480B A35B
Qwen3 Coder 480B A35B leads, 11.9 against 7.6.
Same board, both measured
Web design
Design Arena: websites
Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B leads, 1159 against 955.
Same board, both measured
Long documents
Listed context window
Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B takes 262K tokens against 41K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 30B A3B
Qwen3 30B A3B $0.0004, Qwen3 Coder 480B A35B $0.0010 per turn.
List prices
At a glance
- Coding index
- Qwen3 30B A3B not benchmarked, Qwen3 Coder 480B A35B not benchmarked.
- Widest category
- Web design, 22.2 points apart on average over 5 shared benchmarks.
- Widest single gap
- Long context reasoning (AA-LCR): Qwen3 30B A3B 0.0% against Qwen3 Coder 480B A35B 45.7%, 45.7 points apart on a 0 to 100 scale.
- Output price
- Qwen3 30B A3B $0.50 against Qwen3 Coder 480B A35B $1.50 per million output tokens, 3.0x apart.
- Context window
- Qwen3 30B A3B takes 41K tokens, Qwen3 Coder 480B A35B 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 | Qwen3 30B A3B | Bars | Qwen3 Coder 480B A35B | Ties |
|---|---|---|---|---|
| Coding | 0 | 5 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 1 | 4 | ||
| Math | 2 | 2 | ||
| Knowledge | 0 | 5 | ||
| Web design | 0 | 5 | ||
| General | 1 | 18 | ||
| All shared boards | 4 | 41 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
| Benchmark | Qwen3 30B A3B | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 69.6% | Only Qwen3 Coder 480B A35B measured |
| LMArena WebDev | Not measured | 1275 | Only Qwen3 Coder 480B A35B measured |
| LiveCodeBench (Artificial Analysis run) | 50.6% | 58.5% | Qwen3 Coder 480B A35B |
| Terminal-Bench Hard (Artificial Analysis run) | 6.8% | 18.9% | Qwen3 Coder 480B A35B |
| Terminal-Bench | Not measured | 27.2% | Only Qwen3 Coder 480B A35B measured |
| GSO-Bench | Not measured | 4.9% | Only Qwen3 Coder 480B A35B measured |
| WeirdML | 29.8% | 41.2% | Qwen3 Coder 480B A35B |
| ALE-Bench | Not measured | 461.4 | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: coding | 1337 | 1412 | Qwen3 Coder 480B A35B |
| LMArena Text: software and IT | 1340 | 1393 | Qwen3 Coder 480B A35B |
| LMArena WebDev: React | Not measured | 1257 | Only Qwen3 Coder 480B A35B measured |
| LMArena WebDev: HTML | Not measured | 1287 | 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 index01
| Benchmark | Qwen3 30B A3B | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.6 | 11.9 | Qwen3 Coder 480B A35B |
| Epoch Capabilities Index | 137.3 | Not measured | Only Qwen3 30B A3B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3 30B A3B | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 26.0% | 43.6% | 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 index14
| Benchmark | Qwen3 30B A3B | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 61.6% | 61.8% | Qwen3 Coder 480B A35B |
| Humanity's Last Exam (Artificial Analysis run) | 6.2% | 4.5% | Qwen3 30B A3B |
| GPQA Diamond (Epoch AI run) | 61.7% | Not measured | Only Qwen3 30B A3B measured |
| LMArena Text: hard prompts | 1314 | 1372 | Qwen3 Coder 480B A35B |
| LMArena Text: expert | 1314 | 1338 | Qwen3 Coder 480B A35B |
| LMArena Text: hard prompts in English | 1329 | 1380 | Qwen3 Coder 480B A35B |
| Kagi LLM Benchmark | Not measured | 49.5% | Only Qwen3 Coder 480B A35B measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | Qwen3 30B A3B | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| AA Math Index | 72.3 | 39.3 | Qwen3 30B A3B |
| AIME 2025 (Artificial Analysis run) | 72.3% | 39.3% | Qwen3 30B A3B |
| OTIS Mock AIME | 62.8% | Not measured | Only Qwen3 30B A3B measured |
| LMArena Text: math | 1355 | 1365 | Qwen3 Coder 480B A35B |
| LMArena Text: mathematical work | 1363 | 1367 | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Qwen3 30B A3B | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 77.7% | 78.8% | Qwen3 Coder 480B A35B |
| LMArena Text: science | 1321 | 1347 | Qwen3 Coder 480B A35B |
| LMArena Text: medicine and healthcare | 1318 | 1347 | Qwen3 Coder 480B A35B |
| LMArena Text: legal and government | 1314 | 1358 | Qwen3 Coder 480B A35B |
| LMArena Text: business and finance | 1309 | 1343 | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Qwen3 30B A3B | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| Design Arena: websites | 955 | 1159 | Qwen3 Coder 480B A35B |
| Design Arena: UI components | 946 | 1113 | Qwen3 Coder 480B A35B |
| Design Arena: game dev | 899 | 1099 | Qwen3 Coder 480B A35B |
| Design Arena: data viz | 967 | 1084 | Qwen3 Coder 480B A35B |
| Design Arena: all code categories | 942 | 1143 | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 4 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index118
| Benchmark | Qwen3 30B A3B | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| IFBench | 41.5% | 40.5% | Qwen3 30B A3B |
| Long context reasoning (AA-LCR) | 0.0% | 45.7% | Qwen3 Coder 480B A35B |
| DTBench | 60.3% | Not measured | Only Qwen3 30B A3B measured |
| LMCA | 15.8% | Not measured | Only Qwen3 30B A3B measured |
| Fiction.LiveBench | 40.6% | Not measured | Only Qwen3 30B A3B measured |
| Creative writing (Lech Mazur) | 75.3% | Not measured | Only Qwen3 30B A3B measured |
| LMArena Text | 1317 | 1357 | Qwen3 Coder 480B A35B |
| LMArena Text: instruction following | 1283 | 1355 | Qwen3 Coder 480B A35B |
| LMArena Text: creative writing | 1271 | 1333 | Qwen3 Coder 480B A35B |
| LMArena Text: English | 1335 | 1359 | Qwen3 Coder 480B A35B |
| LMArena Text: non-English | 1295 | 1346 | Qwen3 Coder 480B A35B |
| LMArena Text: Chinese | 1347 | 1357 | Qwen3 Coder 480B A35B |
| LMArena Text: German | 1307 | 1325 | Qwen3 Coder 480B A35B |
| LMArena Text: Japanese | 1254 | 1311 | Qwen3 Coder 480B A35B |
| LMArena Text: Korean | 1261 | 1305 | Qwen3 Coder 480B A35B |
| LMArena Text: French | 1352 | 1398 | Qwen3 Coder 480B A35B |
| LMArena Text: Spanish | 1317 | 1360 | Qwen3 Coder 480B A35B |
| LMArena Text: Russian | 1291 | 1366 | Qwen3 Coder 480B A35B |
| LMArena Text: Polish | 1299 | 1344 | Qwen3 Coder 480B A35B |
| LMArena Text: multi-turn | 1307 | 1366 | Qwen3 Coder 480B A35B |
| LMArena Text: longer queries | 1312 | 1378 | Qwen3 Coder 480B A35B |
| LMArena Text: writing and language | 1290 | 1340 | Qwen3 Coder 480B A35B |
| LMArena Text: entertainment and media | 1258 | 1317 | Qwen3 Coder 480B A35B |
| 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 | Qwen3 30B A3B | Qwen3 Coder 480B A35B | 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 30B A3B costs less
Repository review
50K input + 3K output tokens
Qwen3 30B A3B costs less
Agent loop
200K input + 10K output tokens
Qwen3 30B A3B 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 30B A3B | Qwen3 Coder 480B A35B |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | Open weights | Open weights |
| Released | April 28, 2025 | July 23, 2025 |
| Context window | 41K | 262K |
| Input $/Mtok | $0.12 | $0.30 |
| Output $/Mtok | $0.50 | $1.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3 30B A3B better than Qwen3 Coder 480B A35B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3 30B A3B for output tokens 3.0x cheaper ($0.50 vs $1.50 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
Which is cheaper, Qwen3 30B A3B or Qwen3 Coder 480B A35B?
Qwen3 30B A3B costs $0.12 per million input tokens and $0.50 per million output tokens; Qwen3 Coder 480B A35B costs $0.30 and $1.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen3 30B A3B or Qwen3 Coder 480B A35B?
Qwen3 Coder 480B A35B, with 262K tokens against 41K.
How many benchmarks is the Qwen3 30B A3B vs Qwen3 Coder 480B A35B comparison based on?
45 benchmarks have a result for both models as of October 21, 2026. Qwen3 30B A3B's coding index rests on 0 independent benchmarks and Qwen3 Coder 480B A35B's on 1. Where only one model has a result, the page says so instead of naming a winner.