Enter opens the highlighted result. Esc closes.

R1 0528 vs Phi 4

Updated October 21, 2026. 42 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace R1 0528 Replace Phi 4
R1 0528DeepSeek
Coding
No data
Overall
13.1
Output $/M
$2.18
42
Phi 4Microsoft
Coding
No data
Overall
5.9
Output $/M
$0.14
0
vs boards won of 42 shared

Decision reading

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

R1 0528 has the edge where the context window is larger, 164K against 16K tokens.

Model AR1 0528DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BPhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
42
R1 0528 only
17
Phi 4 only
3
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
R1 0528 not benchmarked, Phi 4 not benchmarked.
Widest category
Math, 42.2 points apart on average over 6 shared benchmarks.
Widest single gap
AA Math Index: R1 0528 76.0 against Phi 4 18.0, 58.0 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.18 against Phi 4 $0.14 per million output tokens, 15.6x apart.
Context window
R1 0528 takes 164K 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
CategoryR1 0528BarsPhi 4Ties
Coding40
Intelligence10
Agentic work10
Reasoning60
Math60
Knowledge50
General190
All shared boards420
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for R1 0528 and Phi 4
BenchmarkR1 0528Phi 4Leader
Aider polyglot71.4%Not measuredOnly R1 0528 measured
LiveCodeBench (Artificial Analysis run)77.0%23.1%R1 0528
Terminal-Bench Hard (Artificial Analysis run)15.9%3.8%R1 0528
WeirdML41.6%Not measuredOnly R1 0528 measured
ALE-Bench804.1Not measuredOnly R1 0528 measured
LMArena Text: coding14271231R1 0528
LMArena Text: software and IT14351228R1 0528
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for R1 0528 and Phi 4
BenchmarkR1 0528Phi 4Leader
AA Intelligence Index13.15.9R1 0528
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 R1 0528 and Phi 4
BenchmarkR1 0528Phi 4Leader
τ²-Bench Telecom36.5%0.0%R1 0528
METR time horizons53.8%Not measuredOnly R1 0528 measured
BALROGNot measured11.6%Only Phi 4 measured
DeepResearch Bench35.1%Not measuredOnly R1 0528 measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for R1 0528 and Phi 4
BenchmarkR1 0528Phi 4Leader
GPQA Diamond (Artificial Analysis run)81.3%57.5%R1 0528
Humanity's Last Exam (Artificial Analysis run)15.8%3.8%R1 0528
GPQA Diamond (Epoch AI run)76.3%56.1%R1 0528
ARC-AGI21.2%Not measuredOnly R1 0528 measured
ARC-AGI-21.1%Not measuredOnly R1 0528 measured
SimpleBench40.8%Not measuredOnly R1 0528 measured
LMArena Text: hard prompts14151220R1 0528
LMArena Text: expert13941203R1 0528
LMArena Text: hard prompts in English14221230R1 0528
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for R1 0528 and Phi 4
BenchmarkR1 0528Phi 4Leader
AA Math Index76.018.0R1 0528
AIME 2025 (Artificial Analysis run)76.0%18.0%R1 0528
OTIS Mock AIME66.4%13.8%R1 0528
MATH level 596.6%64.9%R1 0528
LMArena Text: math14001246R1 0528
LMArena Text: mathematical work14151254R1 0528
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for R1 0528 and Phi 4
BenchmarkR1 0528Phi 4Leader
MMLU Pro (Artificial Analysis run)84.9%71.4%R1 0528
MMLUNot measured84.8%Only Phi 4 measured
LMArena Text: science14301206R1 0528
LMArena Text: medicine and healthcare14451202R1 0528
LMArena Text: legal and government14191241R1 0528
LMArena Text: business and finance14021199R1 0528
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 R1 0528 and Phi 4
BenchmarkR1 0528Phi 4Leader
Design Arena: websites1149Not measuredOnly R1 0528 measured
Design Arena: UI components1103Not measuredOnly R1 0528 measured
Design Arena: game dev1097Not measuredOnly R1 0528 measured
Design Arena: data viz1182Not measuredOnly R1 0528 measured
Design Arena: 3D1111Not measuredOnly R1 0528 measured
Design Arena: all code categories1139Not measuredOnly R1 0528 measured
Design Arena: SVG1039Not measuredOnly R1 0528 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for R1 0528 and Phi 4
BenchmarkR1 0528Phi 4Leader
IFBench39.6%23.5%R1 0528
Long context reasoning (AA-LCR)55.7%0.0%R1 0528
Fiction.LiveBench75.0%Not measuredOnly R1 0528 measured
Creative writing (Lech Mazur)81.9%62.6%R1 0528
LMArena Text14281217R1 0528
LMArena Text: instruction following13821201R1 0528
LMArena Text: creative writing14051181R1 0528
LMArena Text: English14371231R1 0528
LMArena Text: non-English14121197R1 0528
LMArena Text: Chinese14421212R1 0528
LMArena Text: German14041222R1 0528
LMArena Text: Japanese13911158R1 0528
LMArena Text: Korean13601151R1 0528
LMArena Text: French14171224R1 0528
LMArena Text: Spanish14111234R1 0528
LMArena Text: Russian14231209R1 0528
LMArena Text: Polish1428Not measuredOnly R1 0528 measured
LMArena Text: multi-turn14051206R1 0528
LMArena Text: longer queries13911217R1 0528
LMArena Text: writing and language14021198R1 0528
LMArena Text: entertainment and media14001162R1 0528
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for R1 0528 and Phi 4
BenchmarkR1 0528Phi 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

R1 0528$0.0016Fits in one request
Phi 4$0.0001Fits in one request

Phi 4 costs less

Repository review

50K input + 3K output tokens

R1 0528$0.032Fits in one request
Phi 4$0.0039Exceeds the context window

Phi 4 costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.122Exceeds 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 R1 0528 and Phi 4
SpecificationDeepSeek R1 0528Microsoft Phi 4
MakerDeepSeekMicrosoft
WeightsOpen weightsOpen weights
ReleasedMay 28, 2025January 10, 2025
Context window164K16K
Input $/Mtok$0.50$0.07
Output $/Mtok$2.18$0.14
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than Phi 4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. R1 0528 has the edge where the context window is larger, 164K against 16K tokens.

Which is cheaper, R1 0528 or Phi 4?

R1 0528 costs $0.50 per million input tokens and $2.18 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, R1 0528 or Phi 4?

R1 0528, with 164K tokens against 16K.

How many benchmarks is the R1 0528 vs Phi 4 comparison based on?

42 benchmarks have a result for both models as of October 21, 2026. R1 0528'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