Enter opens the highlighted result. Esc closes.

GPT-4o-mini (2024-07-18) vs Phi 4

Phi 4 costs 4.3x less per output token than GPT-4o-mini (2024-07-18) ($0.14 vs $0.60 per million). Updated October 21, 2026; 33 benchmarks have a result for both.

Replace GPT-4o-mini (2024-07-18) Replace Phi 4
GPT-4o-mini (2024-07-18)OpenAI
Coding
No data
Overall
No data
Output $/M
$0.60
29
Phi 4Microsoft
Coding
No data
Overall
24.7
Output $/M
$0.14
4
vs boards won of 33 shared

GPT-4o-mini (2024-07-18) or Phi 4: which to pick

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

Pick GPT-4o-mini (2024-07-18) for a larger context window (128K against 16K tokens) and work measured by GPQA Diamond (Epoch AI run) or OTIS Mock AIME, where it leads.

Model AGPT-4o-mini (2024-07-18)OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BPhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
33
GPT-4o-mini (2024-07-18) only
13
Phi 4 only
13
Like-for-like categories
6 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.

At a glance

Coding index
GPT-4o-mini (2024-07-18) not benchmarked, Phi 4 not benchmarked.
Widest category
Knowledge, 11.3 points apart on average over 5 shared benchmarks.
Widest single gap
GPQA Diamond (Epoch AI run): GPT-4o-mini (2024-07-18) 37.7% against Phi 4 56.1%, 18.3 points apart on a 0 to 100 scale.
Output price
GPT-4o-mini (2024-07-18) $0.60 against Phi 4 $0.14 per million output tokens, 4.3x apart.
Context window
GPT-4o-mini (2024-07-18) takes 128K tokens, Phi 4 16K.

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
CategoryGPT-4o-mini (2024-07-18)BarsPhi 4Ties
Coding20
Agentic work10
Reasoning31
Math22
Knowledge41
General170
All shared boards294
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
Aider polyglot3.6%Not measuredOnly GPT-4o-mini (2024-07-18) measured
LiveCodeBench (Artificial Analysis run)Not measured23.1%Only Phi 4 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured3.8%Only Phi 4 measured
WeirdML11.8%Not measuredOnly GPT-4o-mini (2024-07-18) measured
LMArena Text: coding12901231GPT-4o-mini (2024-07-18)
LMArena Text: software and IT12911228GPT-4o-mini (2024-07-18)
Neither model has a result on the other 33 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
AA Intelligence IndexNot measured5.9Only Phi 4 measured
Epoch Capabilities IndexNot measured130.5Only Phi 4 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
τ²-Bench TelecomNot measured0.0%Only Phi 4 measured
BALROG17.4%11.6%GPT-4o-mini (2024-07-18)
Berkeley Function Calling Leaderboard (BFCL)Not measured28.8%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 index31
Reasoning benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
GPQA Diamond (Artificial Analysis run)Not measured57.5%Only Phi 4 measured
Humanity's Last Exam (Artificial Analysis run)Not measured3.8%Only Phi 4 measured
GPQA Diamond (Epoch AI run)37.7%56.1%Phi 4
SimpleBench10.7%Not measuredOnly GPT-4o-mini (2024-07-18) measured
Chess puzzles3.0%Not measuredOnly GPT-4o-mini (2024-07-18) measured
Mystery game puzzles12.0%Not measuredOnly GPT-4o-mini (2024-07-18) measured
VPCT34.0%Not measuredOnly GPT-4o-mini (2024-07-18) measured
LMArena Text: hard prompts12671220GPT-4o-mini (2024-07-18)
LMArena Text: expert12341203GPT-4o-mini (2024-07-18)
LMArena Text: hard prompts in English12781230GPT-4o-mini (2024-07-18)
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
AA Math IndexNot measured18.0Only Phi 4 measured
AIME 2025 (Artificial Analysis run)Not measured18.0%Only Phi 4 measured
OTIS Mock AIME6.9%13.8%Phi 4
FrontierMath, tiers 1 to 30.7%Not measuredOnly GPT-4o-mini (2024-07-18) measured
MATH level 552.6%64.9%Phi 4
LMArena Text: math12671246GPT-4o-mini (2024-07-18)
LMArena Text: mathematical work12711254GPT-4o-mini (2024-07-18)
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
Knowledge benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
MMLU Pro (Artificial Analysis run)Not measured71.4%Only Phi 4 measured
SimpleQA Verified8.3%Not measuredOnly GPT-4o-mini (2024-07-18) measured
MMLU76.7%84.8%Phi 4
GeoBench64.0%Not measuredOnly GPT-4o-mini (2024-07-18) measured
LMArena Text: science12861206GPT-4o-mini (2024-07-18)
LMArena Text: medicine and healthcare12821202GPT-4o-mini (2024-07-18)
LMArena Text: legal and government13051241GPT-4o-mini (2024-07-18)
LMArena Text: business and finance12651199GPT-4o-mini (2024-07-18)
Neither model has a result on the other 10 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
General benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
IFBenchNot measured23.5%Only Phi 4 measured
Long context reasoning (AA-LCR)Not measured0.0%Only Phi 4 measured
Creative writing (Lech Mazur)67.2%62.6%GPT-4o-mini (2024-07-18)
LMArena Text12861217GPT-4o-mini (2024-07-18)
LMArena Text: instruction following12581201GPT-4o-mini (2024-07-18)
LMArena Text: creative writing12681181GPT-4o-mini (2024-07-18)
LMArena Vision1066Not measuredOnly GPT-4o-mini (2024-07-18) measured
LMArena Text: English13011231GPT-4o-mini (2024-07-18)
LMArena Text: non-English12661197GPT-4o-mini (2024-07-18)
LMArena Text: Chinese12651212GPT-4o-mini (2024-07-18)
LMArena Text: German12721222GPT-4o-mini (2024-07-18)
LMArena Text: Japanese12161158GPT-4o-mini (2024-07-18)
LMArena Text: Korean11951151GPT-4o-mini (2024-07-18)
LMArena Text: French12971224GPT-4o-mini (2024-07-18)
LMArena Text: Spanish12761234GPT-4o-mini (2024-07-18)
LMArena Text: Russian12751209GPT-4o-mini (2024-07-18)
LMArena Text: Polish1244Not measuredOnly GPT-4o-mini (2024-07-18) measured
LMArena Text: multi-turn12851206GPT-4o-mini (2024-07-18)
LMArena Text: longer queries12891217GPT-4o-mini (2024-07-18)
LMArena Text: writing and language12821198GPT-4o-mini (2024-07-18)
LMArena Text: entertainment and media12531162GPT-4o-mini (2024-07-18)
LMArena Vision: English1072Not measuredOnly GPT-4o-mini (2024-07-18) measured
LMArena Vision: Chinese1033Not measuredOnly GPT-4o-mini (2024-07-18) measured
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
Image generation benchmarks for GPT-4o-mini (2024-07-18) and Phi 4
BenchmarkGPT-4o-mini (2024-07-18)Phi 4Leader
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

GPT-4o-mini (2024-07-18)$0.0004Fits in one request
Phi 4$0.0001Fits in one request

Phi 4 costs less

Repository review

50K input + 3K output tokens

GPT-4o-mini (2024-07-18)$0.0093Fits in one request
Phi 4$0.0039Exceeds the context window

Phi 4 costs less

Agent loop

200K input + 10K output tokens

GPT-4o-mini (2024-07-18)$0.036Exceeds the context window
Phi 4$0.015Exceeds the context window

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 GPT-4o-mini (2024-07-18) and Phi 4
SpecificationOpenAI GPT-4o-mini (2024-07-18)Microsoft Phi 4
MakerOpenAIMicrosoft
WeightsNo public weights listedOpen weights
ReleasedJuly 18, 2024January 10, 2025
Context window128K16K
Input $/Mtok$0.15$0.07
Output $/Mtok$0.60$0.14
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o-mini (2024-07-18) better than Phi 4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4o-mini (2024-07-18) for a larger context window (128K against 16K tokens) and work measured by GPQA Diamond (Epoch AI run) or OTIS Mock AIME, where it leads.

Which is cheaper, GPT-4o-mini (2024-07-18) or Phi 4?

GPT-4o-mini (2024-07-18) costs $0.15 per million input tokens and $0.60 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4o-mini (2024-07-18) or Phi 4?

GPT-4o-mini (2024-07-18), with 128K tokens against 16K.

How many benchmarks is the GPT-4o-mini (2024-07-18) vs Phi 4 comparison based on?

33 benchmarks have a result for both models as of October 21, 2026. GPT-4o-mini (2024-07-18)'s coding index rests on 0 independent benchmarks and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next