Enter opens the highlighted result. Esc closes.

Phi 4 vs Qwen3.5 397B A17B

Updated October 21, 2026. 37 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Phi 4 Replace Qwen3.5 397B A17B
Phi 4Microsoft
Coding
No data
Overall
5.9
Output $/M
$0.14
0
Qwen3.5 397B A17BQwen
Coding
No data
Overall
21.4
Output $/M
$2.34
37
vs boards won of 37 shared

Decision reading

Neither model has a coding score yet, so the two cannot be ranked on coding.

Phi 4 has the edge where output tokens cost 16.7x less, and where what matters is Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model APhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
37
Phi 4 only
8
Qwen3.5 397B A17B only
28
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.

At a glance

Coding index
Phi 4 not benchmarked, Qwen3.5 397B A17B not benchmarked.
Widest category
Agentic work, 95.6 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Phi 4 0.0% against Qwen3.5 397B A17B 95.6%, 95.6 points apart on a 0 to 100 scale.
Output price
Phi 4 $0.14 against Qwen3.5 397B A17B $2.34 per million output tokens, 16.7x apart.
Context window
Phi 4 takes 16K tokens, Qwen3.5 397B A17B 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.

Boards won, where both have a result
CategoryPhi 4BarsQwen3.5 397B A17BTies
Coding03
Intelligence02
Agentic work01
Reasoning06
Math03
Knowledge04
General018
All shared boards037
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
LMArena WebDevNot measured1400Only Qwen3.5 397B A17B measured
LiveCodeBench (Artificial Analysis run)23.1%Not measuredOnly Phi 4 measured
SciCodeNot measured44.8%Only Qwen3.5 397B A17B measured
Terminal-Bench Hard (Artificial Analysis run)3.8%40.9%Qwen3.5 397B A17B
ALE-BenchNot measured621.9Only Qwen3.5 397B A17B measured
LMArena Text: coding12311464Qwen3.5 397B A17B
LMArena Text: software and IT12281463Qwen3.5 397B A17B
LMArena WebDev: ReactNot measured1388Only Qwen3.5 397B A17B measured
LMArena WebDev: HTMLNot measured1410Only Qwen3.5 397B A17B measured
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
AA Intelligence Index5.921.4Qwen3.5 397B A17B
Epoch Capabilities Index130.5146.8Qwen3.5 397B A17B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
τ²-Bench Telecom0.0%95.6%Qwen3.5 397B A17B
APEX-AgentsNot measured24.9%Only Qwen3.5 397B A17B measured
BALROG11.6%Not measuredOnly Phi 4 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
GPQA Diamond (Artificial Analysis run)57.5%89.3%Qwen3.5 397B A17B
Humanity's Last Exam (Artificial Analysis run)3.8%29.0%Qwen3.5 397B A17B
GPQA Diamond (Epoch AI run)56.1%86.4%Qwen3.5 397B A17B
Mystery game puzzlesNot measured18.0%Only Qwen3.5 397B A17B measured
LMArena Text: hard prompts12201448Qwen3.5 397B A17B
LMArena Text: expert12031462Qwen3.5 397B A17B
LMArena Text: hard prompts in English12301450Qwen3.5 397B A17B
LMArena Vision: diagramsNot measured1277Only Qwen3.5 397B A17B measured
LMArena Vision: homeworkNot measured1292Only Qwen3.5 397B A17B measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
AA Math Index18.0Not measuredOnly Phi 4 measured
AIME 2025 (Artificial Analysis run)18.0%Not measuredOnly Phi 4 measured
OTIS Mock AIME13.8%88.9%Qwen3.5 397B A17B
FrontierMath, tiers 1 to 3Not measured31.2%Only Qwen3.5 397B A17B measured
MATH level 564.9%Not measuredOnly Phi 4 measured
LMArena Text: math12461453Qwen3.5 397B A17B
LMArena Text: mathematical work12541454Qwen3.5 397B A17B
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
MMLU Pro (Artificial Analysis run)71.4%Not measuredOnly Phi 4 measured
MMLU84.8%Not measuredOnly Phi 4 measured
LMArena Text: science12061457Qwen3.5 397B A17B
LMArena Text: medicine and healthcare12021455Qwen3.5 397B A17B
LMArena Text: legal and government12411441Qwen3.5 397B A17B
LMArena Text: business and finance11991435Qwen3.5 397B A17B
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
Design Arena: websitesNot measured1191Only Qwen3.5 397B A17B measured
Design Arena: UI componentsNot measured1163Only Qwen3.5 397B A17B measured
Design Arena: game devNot measured1140Only Qwen3.5 397B A17B measured
Design Arena: data vizNot measured1175Only Qwen3.5 397B A17B measured
Design Arena: 3DNot measured1161Only Qwen3.5 397B A17B measured
Design Arena: all code categoriesNot measured1180Only Qwen3.5 397B A17B measured
Design Arena: SVGNot measured1140Only 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 index018
General benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
IFBench23.5%78.8%Qwen3.5 397B A17B
Long context reasoning (AA-LCR)0.0%77.3%Qwen3.5 397B A17B
DTBenchNot measured87.5%Only Qwen3.5 397B A17B measured
LMCANot measured37.9%Only Qwen3.5 397B A17B measured
Creative writing (Lech Mazur)62.6%Not measuredOnly Phi 4 measured
LMArena Text12171437Qwen3.5 397B A17B
LMArena Text: instruction following12011424Qwen3.5 397B A17B
LMArena Text: creative writing11811402Qwen3.5 397B A17B
LMArena VisionNot measured1262Only Qwen3.5 397B A17B measured
LMArena Text: English12311443Qwen3.5 397B A17B
LMArena Text: non-English11971430Qwen3.5 397B A17B
LMArena Text: Chinese12121498Qwen3.5 397B A17B
LMArena Text: German12221445Qwen3.5 397B A17B
LMArena Text: Japanese11581429Qwen3.5 397B A17B
LMArena Text: Korean11511384Qwen3.5 397B A17B
LMArena Text: French12241462Qwen3.5 397B A17B
LMArena Text: Spanish12341441Qwen3.5 397B A17B
LMArena Text: Russian12091430Qwen3.5 397B A17B
LMArena Text: PolishNot measured1447Only Qwen3.5 397B A17B measured
LMArena Text: multi-turn12061446Qwen3.5 397B A17B
LMArena Text: longer queries12171441Qwen3.5 397B A17B
LMArena Text: writing and language11981415Qwen3.5 397B A17B
LMArena Text: entertainment and media11621399Qwen3.5 397B A17B
LMArena Vision: EnglishNot measured1268Only Qwen3.5 397B A17B measured
LMArena Vision: ChineseNot measured1314Only Qwen3.5 397B A17B measured
LMArena Vision: reading textNot measured1271Only Qwen3.5 397B A17B measured
LMArena Vision: humorNot measured1262Only Qwen3.5 397B A17B measured
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing thingsNot measured1265Only Qwen3.5 397B A17B measured
LMArena Vision: creative writingNot measured1260Only Qwen3.5 397B A17B measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Phi 4 and Qwen3.5 397B A17B
BenchmarkPhi 4Qwen3.5 397B A17BLeader
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$0.0001Fits in one request
Qwen3.5 397B A17B$0.0016Fits in one request

Phi 4 costs less

Repository review

50K input + 3K output tokens

Phi 4$0.0039Exceeds the context window
Qwen3.5 397B A17B$0.027Fits in one request

Phi 4 costs less

Agent loop

200K input + 10K output tokens

Phi 4$0.015Exceeds the context window
Qwen3.5 397B A17B$0.101Fits in one request

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.

Specifications of Phi 4 and Qwen3.5 397B A17B
SpecificationMicrosoft Phi 4Qwen3.5 397B A17B
MakerMicrosoftQwen
WeightsOpen weightsOpen weights
ReleasedJanuary 10, 2025February 16, 2026
Context window16K262K
Input $/Mtok$0.07$0.39
Output $/Mtok$0.14$2.34
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Phi 4 better than Qwen3.5 397B A17B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Phi 4 has the edge where output tokens cost 16.7x less, and where what matters is Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Phi 4 or Qwen3.5 397B A17B?

Phi 4 costs $0.07 per million input tokens and $0.14 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, Phi 4 or Qwen3.5 397B A17B?

Qwen3.5 397B A17B, with 262K tokens against 16K.

How many benchmarks is the Phi 4 vs Qwen3.5 397B A17B comparison based on?

37 benchmarks have a result for both models as of October 21, 2026. Phi 4's coding index rests on 0 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next