LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

R1 0528 vs Gemma 3 27B

Updated October 21, 2026. 45 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 Gemma 3 27B
R1 0528DeepSeek
Coding
71.4
Overall
13.1
Output $/M
$2.15
45
Gemma 3 27BGoogle
Coding
4.9
Overall
4.9
Output $/M
$0.35
0
vs boards won of 45 shared

Decision reading

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 4.9 for Gemma 3 27B.

Pick Gemma 3 27B when output tokens cost 6.1x less.

Model AR1 0528DeepSeek71.4/1001 independent benchmarkNo cost per solved taskModel BGemma 3 27BGoogle4.9/1001 independent benchmarkNo cost per solved task
Shared results
45
R1 0528 only
14
Gemma 3 27B only
17
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 71.4 from 1 benchmark, Gemma 3 27B 4.9 from 1 benchmark.
Widest category
Coding, 34.6 points apart on average over 5 shared benchmarks.
Widest single gap
Aider polyglot: R1 0528 71.4% against Gemma 3 27B 4.9%, 66.5 points apart on a 0 to 100 scale.
Output price
R1 0528 $2.15 against Gemma 3 27B $0.35 per million output tokens, 6.1x apart.
Context window
R1 0528 takes 164K tokens, Gemma 3 27B 131K.

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 0528BarsGemma 3 27BTies
Coding50
Intelligence10
Agentic work10
Reasoning60
Math60
Knowledge50
General210
All shared boards450
CodingLike-for-likeFour of these boards feed the Vibe Coding Index50
Coding benchmarks for R1 0528 and Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
Aider polyglot71.4%4.9%R1 0528
AA Coding IndexNot measured10.1Only Gemma 3 27B measured
LiveCodeBench (Artificial Analysis run)77.0%13.7%R1 0528
SciCodeNot measured23.3%Only Gemma 3 27B measured
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: coding14271322R1 0528
LMArena Text: software and IT14351354R1 0528
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for R1 0528 and Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
AA Intelligence Index13.14.9R1 0528
Epoch Capabilities IndexNot measured130.0Only Gemma 3 27B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for R1 0528 and Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
AA Agentic IndexNot measured0.1Only Gemma 3 27B measured
τ²-Bench Telecom36.5%10.5%R1 0528
METR time horizons53.8%Not measuredOnly R1 0528 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 Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
GPQA Diamond (Artificial Analysis run)81.3%42.8%R1 0528
Humanity's Last Exam (Artificial Analysis run)15.8%4.4%R1 0528
GPQA Diamond (Epoch AI run)76.3%47.7%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 prompts14151340R1 0528
LMArena Text: expert13941304R1 0528
LMArena Text: hard prompts in English14221353R1 0528
LMArena Vision: diagramsNot measured1156Only Gemma 3 27B measured
LMArena Vision: homeworkNot measured1160Only Gemma 3 27B measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for R1 0528 and Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
AA Math Index76.020.7R1 0528
AIME 2025 (Artificial Analysis run)76.0%20.7%R1 0528
OTIS Mock AIME66.4%22.5%R1 0528
MATH level 596.6%74.0%R1 0528
LMArena Text: math14001312R1 0528
LMArena Text: mathematical work14151327R1 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 Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
MMLU Pro (Artificial Analysis run)84.9%66.9%R1 0528
GeoBenchNot measured52.0%Only Gemma 3 27B measured
LMArena Text: science14301383R1 0528
LMArena Text: medicine and healthcare14451391R1 0528
LMArena Text: legal and government14191375R1 0528
LMArena Text: business and finance14021360R1 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 Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
Design Arena: websites1149Not measuredOnly R1 0528 measured
Design Arena: UI components1102Not measuredOnly R1 0528 measured
Design Arena: game dev1098Not 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: 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 index210
General benchmarks for R1 0528 and Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
IFBench39.6%31.8%R1 0528
Long context reasoning (AA-LCR)55.7%7.3%R1 0528
DTBenchNot measured52.5%Only Gemma 3 27B measured
LMCANot measured12.3%Only Gemma 3 27B measured
Fiction.LiveBench75.0%33.3%R1 0528
Creative writing (Lech Mazur)81.9%79.9%R1 0528
LMArena Text14281358R1 0528
LMArena Text: instruction following13821321R1 0528
LMArena Text: creative writing14051345R1 0528
LMArena VisionNot measured1165Only Gemma 3 27B measured
LMArena Text: English14371377R1 0528
LMArena Text: non-English14121334R1 0528
LMArena Text: Chinese14421346R1 0528
LMArena Text: German14041362R1 0528
LMArena Text: Japanese13911287R1 0528
LMArena Text: Korean13601308R1 0528
LMArena Text: French14171368R1 0528
LMArena Text: Spanish14111349R1 0528
LMArena Text: Russian14231349R1 0528
LMArena Text: Polish14281345R1 0528
LMArena Text: multi-turn14051345R1 0528
LMArena Text: longer queries13911333R1 0528
LMArena Text: writing and language14021347R1 0528
LMArena Text: entertainment and media14001320R1 0528
LMArena Vision: EnglishNot measured1188Only Gemma 3 27B measured
LMArena Vision: ChineseNot measured1164Only Gemma 3 27B measured
LMArena Vision: reading textNot measured1156Only Gemma 3 27B measured
LMArena Vision: humorNot measured1166Only Gemma 3 27B measured
LMArena Vision: captioningNot measured1151Only Gemma 3 27B measured
LMArena Vision: recognizing thingsNot measured1196Only Gemma 3 27B measured
LMArena Vision: creative writingNot measured1177Only Gemma 3 27B measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for R1 0528 and Gemma 3 27B
BenchmarkR1 0528Gemma 3 27BLeader
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
Gemma 3 27B$0.0003Fits in one request

Gemma 3 27B costs less

Repository review

50K input + 3K output tokens

R1 0528$0.031Fits in one request
Gemma 3 27B$0.0050Fits in one request

Gemma 3 27B costs less

Agent loop

200K input + 10K output tokens

R1 0528$0.121Exceeds the context window
Gemma 3 27B$0.019Exceeds the context window

Gemma 3 27B 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 Gemma 3 27B
SpecificationDeepSeek R1 0528Google Gemma 3 27B
MakerDeepSeekGoogle
WeightsOpen weightsOpen weights
ReleasedMay 28, 2025March 12, 2025
Context window164K131K
Input $/Mtok$0.50$0.08
Output $/Mtok$2.15$0.35
Coding index71.44.9
Independent measurements behind it11
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is R1 0528 better than Gemma 3 27B for coding?

Pick R1 0528 for coding: it scores 71.4 on the Vibe Coding Index against 4.9 for Gemma 3 27B. Pick Gemma 3 27B when output tokens cost 6.1x less.

Which is cheaper, R1 0528 or Gemma 3 27B?

R1 0528 costs $0.50 per million input tokens and $2.15 per million output tokens; Gemma 3 27B costs $0.08 and $0.35. Cost per solved task is known for neither of them.

Which has the bigger context window, R1 0528 or Gemma 3 27B?

R1 0528, with 164K tokens against 131K.

How many benchmarks is the R1 0528 vs Gemma 3 27B comparison based on?

45 benchmarks have a result for both models as of October 21, 2026. R1 0528's coding index rests on 1 independent benchmark and Gemma 3 27B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next