Enter opens the highlighted result. Esc closes.

Phi 4 vs Mistral Small 3

Updated October 21, 2026. 36 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 Mistral Small 3
Phi 4Microsoft
Coding
No data
Overall
5.9
Output $/M
$0.14
12
Mistral Small 3Mistral AI
Coding
No data
Overall
6.7
Output $/M
$0.08
22
vs boards won of 36 shared, 2 tied

Decision reading

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

Phi 4 has the edge where what matters is LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model APhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMistral Small 3Mistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
36
Phi 4 only
9
Mistral Small 3 only
0
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, Mistral Small 3 not benchmarked.
Widest category
Agentic work, 19.6 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Phi 4 0.0% against Mistral Small 3 19.6%, 19.6 points apart on a 0 to 100 scale.
Output price
Phi 4 $0.14 against Mistral Small 3 $0.08 per million output tokens, 1.8x apart.
Context window
Phi 4 takes 16K tokens, Mistral Small 3 33K.

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 4BarsMistral Small 3Ties
Coding03
Intelligence01
Agentic work01
Reasoning221 tie
Math40
Knowledge23
General4121 tie
All shared boards12222 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Phi 4 and Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
LiveCodeBench (Artificial Analysis run)23.1%25.2%Mistral Small 3
Terminal-Bench Hard (Artificial Analysis run)3.8%Not measuredOnly Phi 4 measured
LMArena Text: coding12311246Mistral Small 3
LMArena Text: software and IT12281248Mistral Small 3
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 Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
AA Intelligence Index5.96.7Mistral Small 3
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 Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
τ²-Bench Telecom0.0%19.6%Mistral Small 3
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 index22
Reasoning benchmarks for Phi 4 and Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
GPQA Diamond (Artificial Analysis run)57.5%46.2%Phi 4
Humanity's Last Exam (Artificial Analysis run)3.8%3.8%Tie
GPQA Diamond (Epoch AI run)56.1%Not measuredOnly Phi 4 measured
LMArena Text: hard prompts12201233Mistral Small 3
LMArena Text: expert12031202Phi 4
LMArena Text: hard prompts in English12301243Mistral Small 3
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Phi 4 and Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
AA Math Index18.04.3Phi 4
AIME 2025 (Artificial Analysis run)18.0%4.3%Phi 4
OTIS Mock AIME13.8%Not measuredOnly Phi 4 measured
MATH level 564.9%Not measuredOnly Phi 4 measured
LMArena Text: math12461240Phi 4
LMArena Text: mathematical work12541243Phi 4
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index23
Knowledge benchmarks for Phi 4 and Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
MMLU Pro (Artificial Analysis run)71.4%65.2%Phi 4
MMLU84.8%Not measuredOnly Phi 4 measured
LMArena Text: science12061235Mistral Small 3
LMArena Text: medicine and healthcare12021215Mistral Small 3
LMArena Text: legal and government12411219Phi 4
LMArena Text: business and finance11991205Mistral Small 3
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 Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index412
General benchmarks for Phi 4 and Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
IFBench23.5%26.4%Mistral Small 3
Long context reasoning (AA-LCR)0.0%0.0%Tie
Creative writing (Lech Mazur)62.6%Not measuredOnly Phi 4 measured
LMArena Text12171234Mistral Small 3
LMArena Text: instruction following12011214Mistral Small 3
LMArena Text: creative writing11811194Mistral Small 3
LMArena Text: English12311256Mistral Small 3
LMArena Text: non-English11971198Mistral Small 3
LMArena Text: Chinese12121204Phi 4
LMArena Text: German12221211Phi 4
LMArena Text: Japanese11581111Phi 4
LMArena Text: Korean11511188Mistral Small 3
LMArena Text: French12241204Phi 4
LMArena Text: Spanish1234Not measuredOnly Phi 4 measured
LMArena Text: Russian12091216Mistral Small 3
LMArena Text: multi-turn12061217Mistral Small 3
LMArena Text: longer queries12171246Mistral Small 3
LMArena Text: writing and language11981214Mistral Small 3
LMArena Text: entertainment and media11621184Mistral Small 3
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
Image generation benchmarks for Phi 4 and Mistral Small 3
BenchmarkPhi 4Mistral Small 3Leader
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
Mistral Small 3$0.0001Fits in one request

Mistral Small 3 costs less

Repository review

50K input + 3K output tokens

Phi 4$0.0039Exceeds the context window
Mistral Small 3$0.0027Exceeds the context window

Mistral Small 3 costs less

Agent loop

200K input + 10K output tokens

Phi 4$0.015Exceeds the context window
Mistral Small 3$0.011Exceeds the context window

Mistral Small 3 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 Mistral Small 3
SpecificationMicrosoft Phi 4Mistral Small 3
MakerMicrosoftMistral AI
WeightsOpen weightsOpen weights
ReleasedJanuary 10, 2025January 30, 2025
Context window16K33K
Input $/Mtok$0.07$0.05
Output $/Mtok$0.14$0.08
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Phi 4 better than Mistral Small 3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Phi 4 has the edge where what matters is LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Phi 4 or Mistral Small 3?

Phi 4 costs $0.07 per million input tokens and $0.14 per million output tokens; Mistral Small 3 costs $0.05 and $0.08. Cost per solved task is known for neither of them.

Which has the bigger context window, Phi 4 or Mistral Small 3?

Mistral Small 3, with 33K tokens against 16K.

How many benchmarks is the Phi 4 vs Mistral Small 3 comparison based on?

36 benchmarks have a result for both models as of October 21, 2026. Phi 4's coding index rests on 0 independent benchmarks and Mistral Small 3's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next