Enter opens the highlighted result. Esc closes.

R1 0528 vs o3 Mini

R1 0528 leads o3 Mini on the Artificial Analysis Intelligence Index, 13.1 to 12.5, and R1 0528 costs 2.0x less per output token ($2.18 vs $4.40 per million). Updated October 22, 2026; 47 benchmarks have a result for both.

Replace R1 0528 Replace o3 Mini
R1 0528DeepSeek
Coding
No data
Overall
46.8
Output $/M
$2.18
41
o3 MiniOpenAI
Coding
No data
Overall
38.0
Output $/M
$4.40
6
vs boards won of 47 shared

R1 0528 or o3 Mini: which to pick

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

Pick R1 0528 for output tokens 2.0x cheaper ($2.18 vs $4.40 per million) and work measured by WeirdML or GPQA Diamond (Epoch AI run), where it leads.

Model AR1 0528DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel Bo3 MiniOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
47
R1 0528 only
13
o3 Mini only
24
Like-for-like categories
7 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
R1 0528 not benchmarked, o3 Mini not benchmarked.
Widest category
General, 16.1 points apart on average over 21 shared benchmarks.
Widest single gap
IFBench: R1 0528 39.6% against o3 Mini 67.1%, 27.6 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.18 against o3 Mini $4.40 per million output tokens, 2.0x apart.
Context window
R1 0528 takes 164K tokens, o3 Mini 200K.

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 0528Barso3 MiniTies
Coding51
Intelligence10
Agentic work10
Reasoning63
Math31
Knowledge50
General201
All shared boards416
CodingLike-for-likeSix of these boards feed the Vibe Coding Index51
Coding benchmarks for R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
Aider polyglot71.4%60.4%R1 0528
SWE-bench VerifiedNot measured42.4%Only o3 Mini measured
SWE-bench LiteNot measured32.3%Only o3 Mini measured
LiveCodeBench (Vals AI)Not measured71.5%Only o3 Mini measured
LiveCodeBench (Artificial Analysis run)77.0%73.4%R1 0528
SciCodeNot measured42.8%Only o3 Mini measured
Terminal-Bench Hard (Artificial Analysis run)15.9%6.8%R1 0528
GSO-BenchNot measured1.3%Only o3 Mini measured
WeirdML41.6%43.7%o3 Mini
CybenchNot measured22.5%Only o3 Mini measured
ALE-Bench804.1Not measuredOnly R1 0528 measured
LMArena Text: coding14271378R1 0528
LMArena Text: software and IT14351364R1 0528
SciCodeNot measured7.7%Only o3 Mini measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
AA Intelligence Index13.112.5R1 0528
Epoch Capabilities IndexNot measured140.2Only o3 Mini measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
τ²-Bench Telecom36.5%31.3%R1 0528
METR time horizons53.8%Not measuredOnly R1 0528 measured
DeepResearch Bench35.1%Not measuredOnly R1 0528 measured
BrowseComp-Plus16.4%Not measuredOnly R1 0528 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index63
Reasoning benchmarks for R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
GPQA DiamondNot measured75.5%Only o3 Mini measured
GPQA Diamond (Artificial Analysis run)81.3%77.3%R1 0528
Humanity's Last Exam (Artificial Analysis run)15.8%12.0%R1 0528
GPQA Diamond (Epoch AI run)76.3%77.0%o3 Mini
ARC-AGI21.2%34.5%o3 Mini
ARC-AGI-21.1%3.0%o3 Mini
SimpleBench40.8%22.8%R1 0528
Chess puzzlesNot measured15.0%Only o3 Mini measured
Mystery game puzzlesNot measured7.0%Only o3 Mini measured
LMArena Text: hard prompts14151365R1 0528
LMArena Text: expert13941364R1 0528
LMArena Text: hard prompts in English14221375R1 0528
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index31
Math benchmarks for R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
AIMENot measured86.5%Only o3 Mini measured
MATH 500 (Vals AI)Not measured91.8%Only o3 Mini measured
MGSM (Vals AI)Not measured91.3%Only o3 Mini measured
AA Math Index76.0Not measuredOnly R1 0528 measured
AIME 2025 (Artificial Analysis run)76.0%Not measuredOnly R1 0528 measured
OTIS Mock AIME66.4%76.9%o3 Mini
FrontierMath, tiers 1 to 3Not measured18.6%Only o3 Mini measured
FrontierMath, tier 4Not measured0.0%Only o3 Mini measured
MATH level 596.6%96.5%R1 0528
LMArena Text: math14001396R1 0528
LMArena Text: mathematical work14151399R1 0528
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
MMLU ProNot measured78.7%Only o3 Mini measured
LegalBench (Vals AI)Not measured71.5%Only o3 Mini measured
CorpFin (Vals AI)Not measured45.3%Only o3 Mini measured
TaxEval (Vals AI)Not measured69.4%Only o3 Mini measured
MedQA (Vals AI)Not measured94.8%Only o3 Mini measured
MMLU Pro (Artificial Analysis run)84.9%80.2%R1 0528
SimpleQA VerifiedNot measured15.3%Only o3 Mini measured
LMArena Text: science14301339R1 0528
LMArena Text: medicine and healthcare14451330R1 0528
LMArena Text: legal and government14191328R1 0528
LMArena Text: business and finance14021313R1 0528
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
Design Arena: websites1149Not measuredOnly R1 0528 measured
Design Arena: UI components1100Not measuredOnly R1 0528 measured
Design Arena: game dev1097Not measuredOnly R1 0528 measured
Design Arena: data viz1182Not measuredOnly R1 0528 measured
Design Arena: 3D1110Not measuredOnly R1 0528 measured
Design Arena: all code categories1138Not measuredOnly R1 0528 measured
Design Arena: SVG1038Not 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 index201
General benchmarks for R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
IFBench39.6%67.1%o3 Mini
Long context reasoning (AA-LCR)55.7%43.0%R1 0528
DTBenchNot measured68.8%Only o3 Mini measured
LMCANot measured19.0%Only o3 Mini measured
Fiction.LiveBench75.0%50.0%R1 0528
Creative writing (Lech Mazur)81.9%61.7%R1 0528
LMArena Text14281337R1 0528
LMArena Text: instruction following13821337R1 0528
LMArena Text: creative writing14051286R1 0528
LMArena Text: English14371351R1 0528
LMArena Text: non-English14121319R1 0528
LMArena Text: Chinese14421379R1 0528
LMArena Text: German14041303R1 0528
LMArena Text: Japanese13911286R1 0528
LMArena Text: Korean13601313R1 0528
LMArena Text: French14171334R1 0528
LMArena Text: Spanish14111321R1 0528
LMArena Text: Russian14231304R1 0528
LMArena Text: Polish14281294R1 0528
LMArena Text: multi-turn14051320R1 0528
LMArena Text: longer queries13911343R1 0528
LMArena Text: writing and language14021313R1 0528
LMArena Text: entertainment and media14001283R1 0528
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 R1 0528 and o3 Mini
BenchmarkR1 0528o3 MiniLeader
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
o3 Mini$0.0033Fits in one request

R1 0528 costs less

Repository review

50K input + 3K output tokens

R1 0528$0.032Fits in one request
o3 Mini$0.068Fits in one request

R1 0528 costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.122Exceeds the context window
o3 Mini$0.264Exceeds the context window

R1 0528 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 o3 Mini
SpecificationDeepSeek R1 0528OpenAI o3 Mini
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedMay 28, 2025January 31, 2025
Context window164K200K
Input $/Mtok$0.50$1.10
Output $/Mtok$2.18$4.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than o3 Mini for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick R1 0528 for output tokens 2.0x cheaper ($2.18 vs $4.40 per million) and work measured by WeirdML or GPQA Diamond (Epoch AI run), where it leads.

Which is cheaper, R1 0528 or o3 Mini?

R1 0528 costs $0.50 per million input tokens and $2.18 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for neither of them.

Which has the bigger context window, R1 0528 or o3 Mini?

o3 Mini, with 200K tokens against 164K.

How many benchmarks is the R1 0528 vs o3 Mini comparison based on?

47 benchmarks have a result for both models as of October 22, 2026. R1 0528's coding index rests on 0 independent benchmarks and o3 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next