Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs Gemma 3 27B

DeepSeek V3.2 leads Gemma 3 27B on the Artificial Analysis Intelligence Index, 21.5 to 4.9, and Gemma 3 27B costs 2.9x less per output token ($0.30 vs $0.88 per million). Updated October 21, 2026; 43 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace Gemma 3 27B
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
43
Gemma 3 27BGoogle
Coding
No data
Overall
31.4
Output $/M
$0.30
0
vs boards won of 43 shared

DeepSeek V3.2 or Gemma 3 27B: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Gemma 3 27B has none, so the two cannot be ranked on coding.

Pick Gemma 3 27B for output tokens 2.9x cheaper ($0.30 vs $0.88 per million).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BGemma 3 27BGoogleNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
43
DeepSeek V3.2 only
32
Gemma 3 27B only
23
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
DeepSeek V3.2 30.0 from 3 benchmarks, Gemma 3 27B not benchmarked.
Widest category
Agentic work, 80.1 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.2 90.6% against Gemma 3 27B 10.5%, 80.1 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against Gemma 3 27B $0.30 per million output tokens, 2.9x apart.
Context window
DeepSeek V3.2 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
CategoryDeepSeek V3.2BarsGemma 3 27BTies
Coding50
Intelligence20
Agentic work10
Reasoning50
Math40
Knowledge50
General210
All shared boards430
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 3 27BLeader
Aider polyglotNot measured4.9%Only Gemma 3 27B measured
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev1362Not measuredOnly DeepSeek V3.2 measured
AA Coding Index44.210.1DeepSeek V3.2
LiveCodeBench (Vals AI)80.7%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Verified (Vals AI)67.6%Not measuredOnly DeepSeek V3.2 measured
Vibe Code Bench (Vals AI)5.1%Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)86.2%13.7%DeepSeek V3.2
SciCodeNot measured23.3%Only Gemma 3 27B measured
Terminal-Bench Hard (Artificial Analysis run)35.6%3.8%DeepSeek V3.2
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: coding14531322DeepSeek V3.2
LMArena Text: software and IT14491354DeepSeek V3.2
LMArena WebDev: React1350Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev: HTML1371Not measuredOnly DeepSeek V3.2 measured
SciCodeNot measured0.0%Only Gemma 3 27B measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 3 27BLeader
AA Intelligence Index21.54.9DeepSeek V3.2
Epoch Capabilities Index146.1130.0DeepSeek V3.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 3 27BLeader
AA Agentic IndexNot measured0.1Only Gemma 3 27B measured
τ²-Bench Telecom90.6%10.5%DeepSeek V3.2
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034Not measuredOnly DeepSeek V3.2 measured
Berkeley Function Calling Leaderboard (BFCL)Not measured29.5%Only Gemma 3 27B measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 3 27BLeader
GPQA Diamond80.3%Not measuredOnly DeepSeek V3.2 measured
GPQA Diamond (Artificial Analysis run)84.0%42.8%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)24.6%4.4%DeepSeek V3.2
GPQA Diamond (Epoch AI run)Not measured47.7%Only Gemma 3 27B measured
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: hard prompts14341340DeepSeek V3.2
LMArena Text: expert14361304DeepSeek V3.2
LMArena Text: hard prompts in English14461353DeepSeek V3.2
LMArena Vision: diagramsNot measured1156Only Gemma 3 27B measured
LMArena Vision: homeworkNot measured1160Only Gemma 3 27B measured
Kagi LLM BenchmarkNot measured35.1%Only 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 index40
Math benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 3 27BLeader
AIME84.6%Not measuredOnly DeepSeek V3.2 measured
MGSM (Vals AI)86.0%Not measuredOnly DeepSeek V3.2 measured
AA Math Index92.020.7DeepSeek V3.2
AIME 2025 (Artificial Analysis run)92.0%20.7%DeepSeek V3.2
OTIS Mock AIMENot measured22.5%Only Gemma 3 27B measured
MATH level 5Not measured74.0%Only Gemma 3 27B measured
LMArena Text: math14351312DeepSeek V3.2
LMArena Text: mathematical work14401327DeepSeek V3.2
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 3 27BLeader
MMLU Pro84.9%Not measuredOnly DeepSeek V3.2 measured
LegalBench (Vals AI)76.1%Not measuredOnly DeepSeek V3.2 measured
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%Not measuredOnly DeepSeek V3.2 measured
TaxEval (Vals AI)68.2%Not measuredOnly DeepSeek V3.2 measured
MedQA (Vals AI)93.9%Not measuredOnly DeepSeek V3.2 measured
MMLU Pro (Artificial Analysis run)86.2%66.9%DeepSeek V3.2
GeoBenchNot measured52.0%Only Gemma 3 27B measured
LMArena Text: science14461383DeepSeek V3.2
LMArena Text: medicine and healthcare14401391DeepSeek V3.2
LMArena Text: legal and government14251375DeepSeek V3.2
LMArena Text: business and finance14101360DeepSeek V3.2
FACTS Benchmark SuiteNot measured29.1%Only Gemma 3 27B measured
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 3 27BLeader
Design Arena: websites1175Not measuredOnly DeepSeek V3.2 measured
Design Arena: UI components1149Not measuredOnly DeepSeek V3.2 measured
Design Arena: game dev1132Not measuredOnly DeepSeek V3.2 measured
Design Arena: data viz1158Not measuredOnly DeepSeek V3.2 measured
Design Arena: 3D1133Not measuredOnly DeepSeek V3.2 measured
Design Arena: all code categories1164Not measuredOnly DeepSeek V3.2 measured
Design Arena: SVG1032Not measuredOnly DeepSeek V3.2 measured
Design Arena: ASCII art1083Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index210
General benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 3 27BLeader
IFBench60.7%31.8%DeepSeek V3.2
Long context reasoning (AA-LCR)73.3%7.3%DeepSeek V3.2
DTBench85.6%52.5%DeepSeek V3.2
LMCA28.8%12.3%DeepSeek V3.2
Fiction.LiveBenchNot measured33.3%Only Gemma 3 27B measured
Creative writing (Lech Mazur)Not measured79.9%Only Gemma 3 27B measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251358DeepSeek V3.2
LMArena Text: instruction following14131321DeepSeek V3.2
LMArena Text: creative writing14001345DeepSeek V3.2
LMArena VisionNot measured1165Only Gemma 3 27B measured
LMArena Text: English14391377DeepSeek V3.2
LMArena Text: non-English14091334DeepSeek V3.2
LMArena Text: Chinese14551346DeepSeek V3.2
LMArena Text: German14131362DeepSeek V3.2
LMArena Text: Japanese13741287DeepSeek V3.2
LMArena Text: Korean13701308DeepSeek V3.2
LMArena Text: French14291368DeepSeek V3.2
LMArena Text: Spanish14241349DeepSeek V3.2
LMArena Text: Russian14241349DeepSeek V3.2
LMArena Text: Polish14191345DeepSeek V3.2
LMArena Text: multi-turn14271345DeepSeek V3.2
LMArena Text: longer queries14281333DeepSeek V3.2
LMArena Text: writing and language14071347DeepSeek V3.2
LMArena Text: entertainment and media13951320DeepSeek V3.2
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 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.2 and Gemma 3 27B
BenchmarkDeepSeek V3.2Gemma 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

DeepSeek V3.2$0.0007Fits in one request
Gemma 3 27B$0.0002Fits in one request

Gemma 3 27B costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
Gemma 3 27B$0.0049Fits in one request

Gemma 3 27B costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds 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 DeepSeek V3.2 and Gemma 3 27B
SpecificationDeepSeek V3.2Google Gemma 3 27B
MakerDeepSeekGoogle
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025March 12, 2025
Context window164K131K
Input $/Mtok$0.29$0.08
Output $/Mtok$0.88$0.30
Coding index30.0Not benchmarked
Independent measurements behind it30
Cost per solved task$0.99Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than Gemma 3 27B for coding?

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Gemma 3 27B has none, so the two cannot be ranked on coding. Pick Gemma 3 27B for output tokens 2.9x cheaper ($0.30 vs $0.88 per million).

Which is cheaper, DeepSeek V3.2 or Gemma 3 27B?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Gemma 3 27B costs $0.08 and $0.30. Cost per solved task is known for DeepSeek V3.2 only.

Which has the bigger context window, DeepSeek V3.2 or Gemma 3 27B?

DeepSeek V3.2, with 164K tokens against 131K.

How many benchmarks is the DeepSeek V3.2 vs Gemma 3 27B comparison based on?

43 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and Gemma 3 27B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next