Phi 4 vs Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B leads Phi 4 on the Artificial Analysis Intelligence Index, 11.9 to 5.9, and Phi 4 costs 10.7x less per output token ($0.14 vs $1.50 per million). Updated October 21, 2026; 38 benchmarks have a result for both.
Phi 4 or Qwen3 Coder 480B A35B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Phi 4 for output tokens 10.7x cheaper ($0.14 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
- 38
- Phi 4 only
- 8
- Qwen3 Coder 480B A35B only
- 15
- 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 5.9.
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
Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B takes 262K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Phi 4 $0.0001, Qwen3 Coder 480B A35B $0.0010 per turn.
List prices
At a glance
- Coding index
- Phi 4 not benchmarked, Qwen3 Coder 480B A35B not benchmarked.
- Widest category
- Agentic work, 43.6 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Phi 4 0.0% against Qwen3 Coder 480B A35B 45.7%, 45.7 points apart on a 0 to 100 scale.
- Output price
- Phi 4 $0.14 against Qwen3 Coder 480B A35B $1.50 per million output tokens, 10.7x apart.
- Context window
- Phi 4 takes 16K 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 | Phi 4 | Bars | Qwen3 Coder 480B A35B | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 4 | ||
| Knowledge | 0 | 5 | ||
| General | 0 | 18 | ||
| All shared boards | 0 | 38 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | Phi 4 | 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) | 23.1% | 58.5% | Qwen3 Coder 480B A35B |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | 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 | Not measured | 41.2% | Only Qwen3 Coder 480B A35B measured |
| ALE-Bench | Not measured | 461.4 | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: coding | 1231 | 1412 | Qwen3 Coder 480B A35B |
| LMArena Text: software and IT | 1228 | 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 | Phi 4 | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.9 | 11.9 | Qwen3 Coder 480B A35B |
| Epoch Capabilities Index | 130.5 | Not measured | Only Phi 4 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Phi 4 | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 0.0% | 43.6% | Qwen3 Coder 480B A35B |
| BALROG | 11.6% | Not measured | Only Phi 4 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 28.8% | Not measured | Only Phi 4 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Phi 4 | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 57.5% | 61.8% | Qwen3 Coder 480B A35B |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | 4.5% | Qwen3 Coder 480B A35B |
| GPQA Diamond (Epoch AI run) | 56.1% | Not measured | Only Phi 4 measured |
| LMArena Text: hard prompts | 1220 | 1372 | Qwen3 Coder 480B A35B |
| LMArena Text: expert | 1203 | 1338 | Qwen3 Coder 480B A35B |
| LMArena Text: hard prompts in English | 1230 | 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 index04
| Benchmark | Phi 4 | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| AA Math Index | 18.0 | 39.3 | Qwen3 Coder 480B A35B |
| AIME 2025 (Artificial Analysis run) | 18.0% | 39.3% | Qwen3 Coder 480B A35B |
| OTIS Mock AIME | 13.8% | Not measured | Only Phi 4 measured |
| MATH level 5 | 64.9% | Not measured | Only Phi 4 measured |
| LMArena Text: math | 1246 | 1365 | Qwen3 Coder 480B A35B |
| LMArena Text: mathematical work | 1254 | 1367 | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Phi 4 | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 71.4% | 78.8% | Qwen3 Coder 480B A35B |
| MMLU | 84.8% | Not measured | Only Phi 4 measured |
| LMArena Text: science | 1206 | 1347 | Qwen3 Coder 480B A35B |
| LMArena Text: medicine and healthcare | 1202 | 1347 | Qwen3 Coder 480B A35B |
| LMArena Text: legal and government | 1241 | 1358 | Qwen3 Coder 480B A35B |
| LMArena Text: business and finance | 1199 | 1343 | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Phi 4 | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1159 | Only Qwen3 Coder 480B A35B measured |
| Design Arena: UI components | Not measured | 1113 | Only Qwen3 Coder 480B A35B measured |
| Design Arena: game dev | Not measured | 1099 | Only Qwen3 Coder 480B A35B measured |
| Design Arena: data viz | Not measured | 1084 | Only Qwen3 Coder 480B A35B measured |
| Design Arena: all code categories | Not measured | 1143 | 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 index018
| Benchmark | Phi 4 | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| IFBench | 23.5% | 40.5% | Qwen3 Coder 480B A35B |
| Long context reasoning (AA-LCR) | 0.0% | 45.7% | Qwen3 Coder 480B A35B |
| Creative writing (Lech Mazur) | 62.6% | Not measured | Only Phi 4 measured |
| LMArena Text | 1217 | 1357 | Qwen3 Coder 480B A35B |
| LMArena Text: instruction following | 1201 | 1355 | Qwen3 Coder 480B A35B |
| LMArena Text: creative writing | 1181 | 1333 | Qwen3 Coder 480B A35B |
| LMArena Text: English | 1231 | 1359 | Qwen3 Coder 480B A35B |
| LMArena Text: non-English | 1197 | 1346 | Qwen3 Coder 480B A35B |
| LMArena Text: Chinese | 1212 | 1357 | Qwen3 Coder 480B A35B |
| LMArena Text: German | 1222 | 1325 | Qwen3 Coder 480B A35B |
| LMArena Text: Japanese | 1158 | 1311 | Qwen3 Coder 480B A35B |
| LMArena Text: Korean | 1151 | 1305 | Qwen3 Coder 480B A35B |
| LMArena Text: French | 1224 | 1398 | Qwen3 Coder 480B A35B |
| LMArena Text: Spanish | 1234 | 1360 | Qwen3 Coder 480B A35B |
| LMArena Text: Russian | 1209 | 1366 | Qwen3 Coder 480B A35B |
| LMArena Text: Polish | Not measured | 1344 | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: multi-turn | 1206 | 1366 | Qwen3 Coder 480B A35B |
| LMArena Text: longer queries | 1217 | 1378 | Qwen3 Coder 480B A35B |
| LMArena Text: writing and language | 1198 | 1340 | Qwen3 Coder 480B A35B |
| LMArena Text: entertainment and media | 1162 | 1317 | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Phi 4 | 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
Phi 4 costs less
Repository review
50K input + 3K output tokens
Phi 4 costs less
Agent loop
200K input + 10K output tokens
Phi 4 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 | Microsoft Phi 4 | Qwen3 Coder 480B A35B |
|---|---|---|
| Maker | Microsoft | Qwen |
| Weights | Open weights | Open weights |
| Released | January 10, 2025 | July 23, 2025 |
| Context window | 16K | 262K |
| Input $/Mtok | $0.07 | $0.30 |
| Output $/Mtok | $0.14 | $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 Phi 4 better than Qwen3 Coder 480B A35B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Phi 4 for output tokens 10.7x cheaper ($0.14 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, Phi 4 or Qwen3 Coder 480B A35B?
Phi 4 costs $0.07 per million input tokens and $0.14 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, Phi 4 or Qwen3 Coder 480B A35B?
Qwen3 Coder 480B A35B, with 262K tokens against 16K.
How many benchmarks is the Phi 4 vs Qwen3 Coder 480B A35B comparison based on?
38 benchmarks have a result for both models as of October 21, 2026. Phi 4'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.