Enter opens the highlighted result. Esc closes.

R1 0528 vs Kimi K2.5

Updated October 21, 2026. 48 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 Kimi K2.5
R1 0528DeepSeek
Coding
71.4
Overall
13.1
Output $/M
$2.15
0
Kimi K2.5Moonshot AI
Coding
58.5
Overall
23.5
Output $/M
$2.50
48
vs boards won of 48 shared

Decision reading

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 58.5 for Kimi K2.5, though on 1 benchmark against 2.

Pick Kimi K2.5 when the context window is larger, 262K against 164K tokens, or when what matters is Terminal-Bench Hard (Artificial Analysis run) or WeirdML, where it leads.

Model AR1 0528DeepSeek71.4/1001 independent benchmarkNo cost per solved taskModel BKimi K2.5Moonshot AI58.5/1002 independent benchmarks$0.24 per solved task
Shared results
48
R1 0528 only
11
Kimi K2.5 only
50
Like-for-like categories
8 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 71.4 from 1 benchmark, Kimi K2.5 58.5 from 2 benchmarks.
Widest category
Agentic work, 59.4 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: R1 0528 36.5% against Kimi K2.5 95.9%, 59.4 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.15 against Kimi K2.5 $2.50 per million output tokens, 1.2x apart.
Context window
R1 0528 takes 164K tokens, Kimi K2.5 262K.

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 0528BarsKimi K2.5Ties
Coding05
Intelligence01
Agentic work01
Reasoning08
Math02
Knowledge04
Web design07
General020
All shared boards048
CodingLike-for-likeFour of these boards feed the Vibe Coding Index05
Coding benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
Aider polyglot71.4%Not measuredOnly R1 0528 measured
SWE-bench VerifiedNot measured70.8%Only Kimi K2.5 measured
SWE-bench MultilingualNot measured67.3%Only Kimi K2.5 measured
LMArena WebDevNot measured1437Only Kimi K2.5 measured
AA Coding IndexNot measured46.8Only Kimi K2.5 measured
LiveCodeBench (Vals AI)Not measured83.9%Only Kimi K2.5 measured
SWE-bench Verified (Vals AI)Not measured70.0%Only Kimi K2.5 measured
Vibe Code Bench (Vals AI)Not measured17.5%Only Kimi K2.5 measured
Code migration (Vals AI)Not measured7.0%Only Kimi K2.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured42.0%Only Kimi K2.5 measured
LiveCodeBench (Artificial Analysis run)77.0%Not measuredOnly R1 0528 measured
Terminal-Bench Hard (Artificial Analysis run)15.9%34.8%Kimi K2.5
Terminal-BenchNot measured43.2%Only Kimi K2.5 measured
WeirdML41.6%45.6%Kimi K2.5
ALE-Bench804.1821.6Kimi K2.5
LMArena Text: coding14271483Kimi K2.5
LMArena Text: software and IT14351471Kimi K2.5
LMArena WebDev: ReactNot measured1429Only Kimi K2.5 measured
LMArena WebDev: HTMLNot measured1426Only Kimi K2.5 measured
LMArena WebDev: from an imageNot measured1439Only Kimi K2.5 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
AA Intelligence Index13.123.5Kimi K2.5
Epoch Capabilities IndexNot measured148.1Only Kimi K2.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
Design Arena: agents building web appsNot measured1136Only Kimi K2.5 measured
Design Arena: agents building full-stack appsNot measured1114Only Kimi K2.5 measured
Design Arena: agents building mobile appsNot measured1147Only Kimi K2.5 measured
Design Arena: agents building Android appsNot measured1124Only Kimi K2.5 measured
Design Arena: agents building Godot gamesNot measured1219Only Kimi K2.5 measured
Finance Agent (Vals AI)Not measured35.8%Only Kimi K2.5 measured
Legal Research Bench (Vals AI)Not measured15.9%Only Kimi K2.5 measured
Excel Modeling Benchmark (Vals AI)Not measured28.5%Only Kimi K2.5 measured
τ²-Bench Telecom36.5%95.9%Kimi K2.5
METR time horizons53.8%Not measuredOnly R1 0528 measured
DeepResearch Bench35.1%Not measuredOnly R1 0528 measured
OSWorldNot measured63.3%Only Kimi K2.5 measured
Vending-Bench 2Not measured$1,198Only Kimi K2.5 measured
Neither model has a result on the other 26 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
GPQA DiamondNot measured84.1%Only Kimi K2.5 measured
MMMU Pro (Vals AI)Not measured84.3%Only Kimi K2.5 measured
GPQA Diamond (Artificial Analysis run)81.3%87.9%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)15.8%30.7%Kimi K2.5
GPQA Diamond (Epoch AI run)76.3%Not measuredOnly R1 0528 measured
ARC-AGI21.2%65.3%Kimi K2.5
ARC-AGI-21.1%11.8%Kimi K2.5
SimpleBench40.8%46.8%Kimi K2.5
LMArena Text: hard prompts14151453Kimi K2.5
LMArena Text: expert13941466Kimi K2.5
LMArena Text: hard prompts in English14221460Kimi K2.5
LMArena Vision: diagramsNot measured1282Only Kimi K2.5 measured
LMArena Vision: homeworkNot measured1297Only Kimi K2.5 measured
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
AIMENot measured95.6%Only Kimi K2.5 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%Not measuredOnly R1 0528 measured
MATH level 596.6%Not measuredOnly R1 0528 measured
LMArena Text: math14001470Kimi K2.5
LMArena Text: mathematical work14151473Kimi K2.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
MMLU ProNot measured85.9%Only Kimi K2.5 measured
CaseLaw (Vals AI)Not measured58.7%Only Kimi K2.5 measured
CorpFin (Vals AI)Not measured68.3%Only Kimi K2.5 measured
TaxEval (Vals AI)Not measured74.2%Only Kimi K2.5 measured
MortgageTax (Vals AI)Not measured66.5%Only Kimi K2.5 measured
MedQA (Vals AI)Not measured94.4%Only Kimi K2.5 measured
MedCode (Vals AI)Not measured39.3%Only Kimi K2.5 measured
MMLU Pro (Artificial Analysis run)84.9%Not measuredOnly R1 0528 measured
SimpleQA VerifiedNot measured34.3%Only Kimi K2.5 measured
LMArena Text: science14301459Kimi K2.5
LMArena Text: medicine and healthcare14451448Kimi K2.5
LMArena Text: legal and government14191441Kimi K2.5
LMArena Text: business and finance14021427Kimi K2.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
Design Arena: websites11491249Kimi K2.5
Design Arena: UI components11021236Kimi K2.5
Design Arena: game dev10981207Kimi K2.5
Design Arena: data viz11821219Kimi K2.5
Design Arena: 3D11111205Kimi K2.5
Design Arena: all code categories11391236Kimi K2.5
Design Arena: SVG10381149Kimi K2.5
Design Arena: ASCII artNot measured1165Only Kimi K2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
SAGE (Vals AI)Not measured49.9%Only Kimi K2.5 measured
MedScribe (Vals AI)Not measured76.4%Only Kimi K2.5 measured
IFBench39.6%70.2%Kimi K2.5
Long context reasoning (AA-LCR)55.7%78.0%Kimi K2.5
Fiction.LiveBench75.0%86.1%Kimi K2.5
Creative writing (Lech Mazur)81.9%Not measuredOnly R1 0528 measured
CL-benchNot measured19.3%Only Kimi K2.5 measured
CL-bench LifeNot measured13.2%Only Kimi K2.5 measured
LMArena Text14281445Kimi K2.5
LMArena Text: instruction following13821431Kimi K2.5
LMArena Text: creative writing14051422Kimi K2.5
LMArena VisionNot measured1269Only Kimi K2.5 measured
LMArena Text: English14371453Kimi K2.5
LMArena Text: non-English14121433Kimi K2.5
LMArena Text: Chinese14421494Kimi K2.5
LMArena Text: German14041441Kimi K2.5
LMArena Text: Japanese13911423Kimi K2.5
LMArena Text: Korean13601412Kimi K2.5
LMArena Text: French14171454Kimi K2.5
LMArena Text: Spanish14111450Kimi K2.5
LMArena Text: Russian14231435Kimi K2.5
LMArena Text: Polish14281445Kimi K2.5
LMArena Text: multi-turn14051444Kimi K2.5
LMArena Text: longer queries13911445Kimi K2.5
LMArena Text: writing and language14021425Kimi K2.5
LMArena Text: entertainment and media14001417Kimi K2.5
LMArena Vision: EnglishNot measured1274Only Kimi K2.5 measured
LMArena Vision: ChineseNot measured1328Only Kimi K2.5 measured
LMArena Vision: reading textNot measured1276Only Kimi K2.5 measured
LMArena Vision: humorNot measured1284Only Kimi K2.5 measured
LMArena Vision: captioningNot measured1257Only Kimi K2.5 measured
LMArena Vision: recognizing thingsNot measured1285Only Kimi K2.5 measured
LMArena Vision: creative writingNot measured1269Only Kimi K2.5 measured
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for R1 0528 and Kimi K2.5
BenchmarkR1 0528Kimi K2.5Leader
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
Kimi K2.5$0.0018Fits in one request

R1 0528 costs less

Repository review

50K input + 3K output tokens

R1 0528$0.031Fits in one request
Kimi K2.5$0.033Fits in one request

R1 0528 costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.121Exceeds the context window
Kimi K2.5$0.125Fits 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 Kimi K2.5
SpecificationDeepSeek R1 0528MoonshotAI Kimi K2.5
MakerDeepSeekMoonshot AI
WeightsOpen weightsOpen weights
ReleasedMay 28, 2025January 27, 2026
Context window164K262K
Input $/Mtok$0.50$0.50
Output $/Mtok$2.15$2.50
Coding index71.458.5
Independent measurements behind it12
Cost per solved taskNot computable$0.24
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than Kimi K2.5 for coding?

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 58.5 for Kimi K2.5, though on 1 benchmark against 2. Pick Kimi K2.5 when the context window is larger, 262K against 164K tokens, or when what matters is Terminal-Bench Hard (Artificial Analysis run) or WeirdML, where it leads.

Which is cheaper, R1 0528 or Kimi K2.5?

R1 0528 costs $0.50 per million input tokens and $2.15 per million output tokens; Kimi K2.5 costs $0.50 and $2.50. Cost per solved task is known for Kimi K2.5 only.

Which has the bigger context window, R1 0528 or Kimi K2.5?

Kimi K2.5, with 262K tokens against 164K.

How many benchmarks is the R1 0528 vs Kimi K2.5 comparison based on?

48 benchmarks have a result for both models as of October 21, 2026. R1 0528's coding index rests on 1 independent benchmark and Kimi K2.5's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next