Enter opens the highlighted result. Esc closes.

Phi 4 vs Step 3.5 Flash

Updated October 21, 2026. 34 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 Step 3.5 Flash
Phi 4Microsoft
Coding
No data
Overall
5.9
Output $/M
$0.14
0
Step 3.5 FlashStepFun
Coding
No data
Overall
17.0
Output $/M
$0.30
34
vs boards won of 34 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 2.1x 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 BStep 3.5 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
34
Phi 4 only
11
Step 3.5 Flash only
1
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, Step 3.5 Flash not benchmarked.
Widest category
Agentic work, 94.4 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Phi 4 0.0% against Step 3.5 Flash 94.4%, 94.4 points apart on a 0 to 100 scale.
Output price
Phi 4 $0.14 against Step 3.5 Flash $0.30 per million output tokens, 2.1x apart.
Context window
Phi 4 takes 16K tokens, Step 3.5 Flash 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 4BarsStep 3.5 FlashTies
Coding03
Intelligence01
Agentic work01
Reasoning05
Math02
Knowledge04
General018
All shared boards034
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
LiveCodeBench (Artificial Analysis run)23.1%Not measuredOnly Phi 4 measured
Terminal-Bench Hard (Artificial Analysis run)3.8%32.6%Step 3.5 Flash
LMArena Text: coding12311436Step 3.5 Flash
LMArena Text: software and IT12281434Step 3.5 Flash
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
AA Intelligence Index5.917.0Step 3.5 Flash
Epoch Capabilities Index130.5Not measuredOnly Phi 4 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
τ²-Bench Telecom0.0%94.4%Step 3.5 Flash
BALROG11.6%Not measuredOnly Phi 4 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
GPQA Diamond (Artificial Analysis run)57.5%83.1%Step 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)3.8%24.5%Step 3.5 Flash
GPQA Diamond (Epoch AI run)56.1%Not measuredOnly Phi 4 measured
LMArena Text: hard prompts12201411Step 3.5 Flash
LMArena Text: expert12031421Step 3.5 Flash
LMArena Text: hard prompts in English12301421Step 3.5 Flash
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
AA Math Index18.0Not measuredOnly Phi 4 measured
AIME 2025 (Artificial Analysis run)18.0%Not measuredOnly Phi 4 measured
OTIS Mock AIME13.8%Not measuredOnly Phi 4 measured
MATH level 564.9%Not measuredOnly Phi 4 measured
LMArena Text: math12461408Step 3.5 Flash
LMArena Text: mathematical work12541421Step 3.5 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
MMLU Pro (Artificial Analysis run)71.4%Not measuredOnly Phi 4 measured
MMLU84.8%Not measuredOnly Phi 4 measured
LMArena Text: science12061415Step 3.5 Flash
LMArena Text: medicine and healthcare12021408Step 3.5 Flash
LMArena Text: legal and government12411408Step 3.5 Flash
LMArena Text: business and finance11991394Step 3.5 Flash
Neither model has a result on the other 11 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
IFBench23.5%66.5%Step 3.5 Flash
Long context reasoning (AA-LCR)0.0%63.0%Step 3.5 Flash
Creative writing (Lech Mazur)62.6%Not measuredOnly Phi 4 measured
LMArena Text12171403Step 3.5 Flash
LMArena Text: instruction following12011385Step 3.5 Flash
LMArena Text: creative writing11811357Step 3.5 Flash
LMArena Text: English12311417Step 3.5 Flash
LMArena Text: non-English11971385Step 3.5 Flash
LMArena Text: Chinese12121446Step 3.5 Flash
LMArena Text: German12221405Step 3.5 Flash
LMArena Text: Japanese11581353Step 3.5 Flash
LMArena Text: Korean11511351Step 3.5 Flash
LMArena Text: French12241421Step 3.5 Flash
LMArena Text: Spanish12341419Step 3.5 Flash
LMArena Text: Russian12091385Step 3.5 Flash
LMArena Text: PolishNot measured1389Only Step 3.5 Flash measured
LMArena Text: multi-turn12061404Step 3.5 Flash
LMArena Text: longer queries12171402Step 3.5 Flash
LMArena Text: writing and language11981372Step 3.5 Flash
LMArena Text: entertainment and media11621360Step 3.5 Flash
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
Image generation benchmarks for Phi 4 and Step 3.5 Flash
BenchmarkPhi 4Step 3.5 FlashLeader
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
Step 3.5 Flash$0.0003Fits in one request

Phi 4 costs less

Repository review

50K input + 3K output tokens

Phi 4$0.0039Exceeds the context window
Step 3.5 Flash$0.0059Fits in one request

Phi 4 costs less

Agent loop

200K input + 10K output tokens

Phi 4$0.015Exceeds the context window
Step 3.5 Flash$0.023Fits 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 Step 3.5 Flash
SpecificationMicrosoft Phi 4StepFun Step 3.5 Flash
MakerMicrosoftStepFun
WeightsOpen weightsOpen weights
ReleasedJanuary 10, 2025January 29, 2026
Context window16K262K
Input $/Mtok$0.07$0.10
Output $/Mtok$0.14$0.30
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Phi 4 better than Step 3.5 Flash 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 2.1x 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 Step 3.5 Flash?

Phi 4 costs $0.07 per million input tokens and $0.14 per million output tokens; Step 3.5 Flash costs $0.10 and $0.30. Cost per solved task is known for neither of them.

Which has the bigger context window, Phi 4 or Step 3.5 Flash?

Step 3.5 Flash, with 262K tokens against 16K.

How many benchmarks is the Phi 4 vs Step 3.5 Flash comparison based on?

34 benchmarks have a result for both models as of October 21, 2026. Phi 4's coding index rests on 0 independent benchmarks and Step 3.5 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next