Enter opens the highlighted result. Esc closes.

R1 0528 vs GPT-4.1

R1 0528 leads GPT-4.1 on the Artificial Analysis Intelligence Index, 13.1 to 12.7, and R1 0528 costs 3.7x less per output token ($2.18 vs $8.00 per million). Updated October 22, 2026; 58 benchmarks have a result for both.

Replace R1 0528 Replace GPT-4.1
R1 0528DeepSeek
Coding
No data
Overall
46.8
Output $/M
$2.18
53
GPT-4.1OpenAI
Coding
No data
Overall
36.5
Output $/M
$8.00
5
vs boards won of 58 shared

R1 0528 or GPT-4.1: which to pick

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

Pick R1 0528 for output tokens 3.7x cheaper ($2.18 vs $8.00 per million) and work measured by τ²-Bench Telecom or BrowseComp-Plus, where it leads.

Model AR1 0528DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-4.1OpenAINot benchmarkedNo coding benchmark$0.37 per solved task
Shared results
58
R1 0528 only
5
GPT-4.1 only
37
Like-for-like categories
8 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, GPT-4.1 not benchmarked.
Widest category
Math, 23.1 points apart on average over 6 shared benchmarks.
Widest single gap
AIME 2025 (Artificial Analysis run): R1 0528 76.0% against GPT-4.1 34.7%, 41.3 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.18 against GPT-4.1 $8.00 per million output tokens, 3.7x apart.
Context window
R1 0528 takes 164K tokens, GPT-4.1 1.05M.

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 0528BarsGPT-4.1Ties
Coding70
Intelligence10
Agentic work02
Reasoning90
Math60
Knowledge61
Web design60
General182
All shared boards535
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
Aider polyglot71.4%52.4%R1 0528
SWE-bench VerifiedNot measured39.6%Only GPT-4.1 measured
SWE-bench MultimodalNot measured31.1%Only GPT-4.1 measured
LiveCodeBench (Vals AI)Not measured54.7%Only GPT-4.1 measured
LiveCodeBench (Artificial Analysis run)77.0%45.7%R1 0528
Terminal-Bench Hard (Artificial Analysis run)15.9%13.6%R1 0528
WeirdML41.6%39.0%R1 0528
ALE-Bench804.1558.1R1 0528
LMArena Text: coding14271390R1 0528
LMArena Text: software and IT14351391R1 0528
SciCodeNot measured4.6%Only GPT-4.1 measured
Neither model has a result on the other 32 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
AA Intelligence Index13.112.7R1 0528
Epoch Capabilities IndexNot measured136.7Only GPT-4.1 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
τ²-Bench Telecom36.5%47.1%GPT-4.1
METR time horizons53.8%Not measuredOnly R1 0528 measured
DeepResearch Bench35.1%Not measuredOnly R1 0528 measured
Berkeley Function Calling Leaderboard (BFCL)Not measured54.0%Only GPT-4.1 measured
BrowseComp-Plus16.4%36.4%GPT-4.1
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
Reasoning benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
GPQA DiamondNot measured65.4%Only GPT-4.1 measured
MMMU Pro (Vals AI)Not measured72.4%Only GPT-4.1 measured
GPQA Diamond (Artificial Analysis run)81.3%66.6%R1 0528
Humanity's Last Exam (Artificial Analysis run)15.8%4.2%R1 0528
GPQA Diamond (Epoch AI run)76.3%66.9%R1 0528
ARC-AGI21.2%5.5%R1 0528
ARC-AGI-21.1%0.4%R1 0528
SimpleBench40.8%27.0%R1 0528
Chess puzzlesNot measured3.0%Only GPT-4.1 measured
LMArena Text: hard prompts14151384R1 0528
LMArena Text: expert13941364R1 0528
LMArena Text: hard prompts in English14221393R1 0528
LMArena Vision: diagramsNot measured1215Only GPT-4.1 measured
LMArena Vision: homeworkNot measured1248Only GPT-4.1 measured
Kagi LLM BenchmarkNot measured52.3%Only GPT-4.1 measured
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
AIMENot measured39.6%Only GPT-4.1 measured
MATH 500 (Vals AI)Not measured87.2%Only GPT-4.1 measured
MGSM (Vals AI)Not measured87.7%Only GPT-4.1 measured
AA Math Index76.034.7R1 0528
AIME 2025 (Artificial Analysis run)76.0%34.7%R1 0528
OTIS Mock AIME66.4%38.3%R1 0528
FrontierMath, tiers 1 to 3Not measured6.0%Only GPT-4.1 measured
MATH level 596.6%83.0%R1 0528
LMArena Text: math14001369R1 0528
LMArena Text: mathematical work14151360R1 0528
MathArena12.9%Not measuredOnly R1 0528 measured
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index61
Knowledge benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
MMLU ProNot measured80.5%Only GPT-4.1 measured
LegalBench (Vals AI)Not measured83.1%Only GPT-4.1 measured
CaseLaw (Vals AI)Not measured69.9%Only GPT-4.1 measured
CorpFin (Vals AI)Not measured63.0%Only GPT-4.1 measured
TaxEval (Vals AI)Not measured75.1%Only GPT-4.1 measured
MortgageTax (Vals AI)Not measured65.9%Only GPT-4.1 measured
MedQA (Vals AI)Not measured91.2%Only GPT-4.1 measured
MMLU Pro (Artificial Analysis run)84.9%80.6%R1 0528
SimpleQA VerifiedNot measured31.1%Only GPT-4.1 measured
GeoBenchNot measured72.0%Only GPT-4.1 measured
LMArena Text: science14301382R1 0528
LMArena Text: medicine and healthcare14451379R1 0528
LMArena Text: legal and government14191399R1 0528
LMArena Text: business and finance14021369R1 0528
FACTS Benchmark SuiteNot measured45.8%Only GPT-4.1 measured
PRBench Finance32.7%34.3%GPT-4.1
PRBench Legal36.6%36.5%R1 0528
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
Design Arena: websites11491038R1 0528
Design Arena: UI components1100998R1 0528
Design Arena: game dev10971079R1 0528
Design Arena: data viz11821104R1 0528
Design Arena: 3D1110849R1 0528
Design Arena: all code categories11381025R1 0528
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 index182
General benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
IFBench39.6%43.0%GPT-4.1
Long context reasoning (AA-LCR)55.7%68.3%GPT-4.1
DTBenchNot measured68.3%Only GPT-4.1 measured
LMCANot measured25.6%Only GPT-4.1 measured
Fiction.LiveBench75.0%63.9%R1 0528
Creative writing (Lech Mazur)81.9%Not measuredOnly R1 0528 measured
LMArena Text14281383R1 0528
LMArena Text: instruction following13821367R1 0528
LMArena Text: creative writing14051363R1 0528
LMArena VisionNot measured1210Only GPT-4.1 measured
LMArena Text: English14371392R1 0528
LMArena Text: non-English14121370R1 0528
LMArena Text: Chinese14421382R1 0528
LMArena Text: German14041381R1 0528
LMArena Text: Japanese13911319R1 0528
LMArena Text: Korean13601338R1 0528
LMArena Text: French14171382R1 0528
LMArena Text: Spanish14111376R1 0528
LMArena Text: Russian14231377R1 0528
LMArena Text: Polish14281389R1 0528
LMArena Text: multi-turn14051397R1 0528
LMArena Text: longer queries13911385R1 0528
LMArena Text: writing and language14021371R1 0528
LMArena Text: entertainment and media14001365R1 0528
LMArena Vision: EnglishNot measured1209Only GPT-4.1 measured
LMArena Vision: ChineseNot measured1226Only GPT-4.1 measured
LMArena Vision: reading textNot measured1218Only GPT-4.1 measured
LMArena Vision: humorNot measured1196Only GPT-4.1 measured
LMArena Vision: captioningNot measured1207Only GPT-4.1 measured
LMArena Vision: recognizing thingsNot measured1208Only GPT-4.1 measured
LMArena Vision: creative writingNot measured1210Only GPT-4.1 measured
MultiChallengeNot measured39.4%Only GPT-4.1 measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for R1 0528 and GPT-4.1
BenchmarkR1 0528GPT-4.1Leader
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
GPT-4.1$0.0060Fits in one request

R1 0528 costs less

Repository review

50K input + 3K output tokens

R1 0528$0.032Fits in one request
GPT-4.1$0.124Fits in one request

R1 0528 costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.122Exceeds the context window
GPT-4.1$0.480Fits in one request

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 GPT-4.1
SpecificationDeepSeek R1 0528OpenAI GPT-4.1
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedMay 28, 2025April 14, 2025
Context window164K1.05M
Input $/Mtok$0.50$2.00
Output $/Mtok$2.18$8.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computable$0.37
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than GPT-4.1 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick R1 0528 for output tokens 3.7x cheaper ($2.18 vs $8.00 per million) and work measured by τ²-Bench Telecom or BrowseComp-Plus, where it leads.

Which is cheaper, R1 0528 or GPT-4.1?

R1 0528 costs $0.50 per million input tokens and $2.18 per million output tokens; GPT-4.1 costs $2.00 and $8.00. Cost per solved task is known for GPT-4.1 only.

Which has the bigger context window, R1 0528 or GPT-4.1?

GPT-4.1, with 1.05M tokens against 164K.

How many benchmarks is the R1 0528 vs GPT-4.1 comparison based on?

58 benchmarks have a result for both models as of October 22, 2026. R1 0528's coding index rests on 0 independent benchmarks and GPT-4.1's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next