Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 Terminus vs Gemma 3 27B

DeepSeek V3.1 Terminus leads Gemma 3 27B on the Artificial Analysis Intelligence Index, 14.8 to 4.9, and Gemma 3 27B costs 3.4x less per output token ($0.30 vs $1.0142 per million). Updated October 22, 2026; 37 benchmarks have a result for both.

Replace DeepSeek V3.1 Terminus Replace Gemma 3 27B
DeepSeek V3.1 TerminusDeepSeek
Coding
No data
Overall
No data
Output $/M
$1.0142
37
Gemma 3 27BGoogle
Coding
No data
Overall
31.4
Output $/M
$0.30
0
vs boards won of 37 shared

DeepSeek V3.1 Terminus or Gemma 3 27B: which to pick

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

Pick DeepSeek V3.1 Terminus for a larger context window (164K against 131K tokens).

Model ADeepSeek V3.1 TerminusDeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGemma 3 27BGoogleNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
37
DeepSeek V3.1 Terminus only
8
Gemma 3 27B only
29
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 V3.1 Terminus not benchmarked, Gemma 3 27B not benchmarked.
Widest category
Math, 51.0 points apart on average over 3 shared benchmarks.
Widest single gap
AA Math Index: DeepSeek V3.1 Terminus 89.7 against Gemma 3 27B 20.7, 69.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 Terminus $1.0142 against Gemma 3 27B $0.30 per million output tokens, 3.4x apart.
Context window
DeepSeek V3.1 Terminus 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 V3.1 TerminusBarsGemma 3 27BTies
Coding60
Intelligence10
Agentic work20
Reasoning50
Math30
Knowledge50
General150
All shared boards370
CodingLike-for-likeSix of these boards feed the Vibe Coding Index60
Coding benchmarks for DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 3 27BLeader
Aider polyglotNot measured4.9%Only Gemma 3 27B measured
AA Coding Index43.510.1DeepSeek V3.1 Terminus
LiveCodeBench (Artificial Analysis run)79.8%13.7%DeepSeek V3.1 Terminus
SciCode38.0%23.3%DeepSeek V3.1 Terminus
Terminal-Bench Hard (Artificial Analysis run)31.8%3.8%DeepSeek V3.1 Terminus
ALE-Bench745.2Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: coding14251322DeepSeek V3.1 Terminus
LMArena Text: software and IT14261354DeepSeek V3.1 Terminus
SciCodeNot measured0.0%Only Gemma 3 27B measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 3 27BLeader
AA Intelligence Index14.84.9DeepSeek V3.1 Terminus
Epoch Capabilities IndexNot measured130.0Only Gemma 3 27B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 3 27BLeader
AA Agentic Index6.80.1DeepSeek V3.1 Terminus
τ²-Bench Telecom37.1%10.5%DeepSeek V3.1 Terminus
Berkeley Function Calling Leaderboard (BFCL)Not measured29.5%Only Gemma 3 27B measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 3 27BLeader
GPQA Diamond (Artificial Analysis run)79.2%42.8%DeepSeek V3.1 Terminus
Humanity's Last Exam (Artificial Analysis run)16.4%4.4%DeepSeek V3.1 Terminus
GPQA Diamond (Epoch AI run)Not measured47.7%Only Gemma 3 27B measured
LMArena Text: hard prompts14261340DeepSeek V3.1 Terminus
LMArena Text: expertNot measured1304Only Gemma 3 27B measured
LMArena Text: hard prompts in English14321353DeepSeek V3.1 Terminus
LMArena Vision: diagramsNot measured1156Only Gemma 3 27B measured
LMArena Vision: homeworkNot measured1160Only Gemma 3 27B measured
Kagi LLM Benchmark57.4%35.1%DeepSeek V3.1 Terminus
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 3 27BLeader
AA Math Index89.720.7DeepSeek V3.1 Terminus
AIME 2025 (Artificial Analysis run)89.7%20.7%DeepSeek V3.1 Terminus
OTIS Mock AIMENot measured22.5%Only Gemma 3 27B measured
MATH level 5Not measured74.0%Only Gemma 3 27B measured
LMArena Text: math14021312DeepSeek V3.1 Terminus
LMArena Text: mathematical workNot measured1327Only Gemma 3 27B measured
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 DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 3 27BLeader
MMLU Pro (Artificial Analysis run)85.1%66.9%DeepSeek V3.1 Terminus
GeoBenchNot measured52.0%Only Gemma 3 27B measured
LMArena Text: science14511383DeepSeek V3.1 Terminus
LMArena Text: medicine and healthcare14681391DeepSeek V3.1 Terminus
LMArena Text: legal and government14571375DeepSeek V3.1 Terminus
LMArena Text: business and finance14141360DeepSeek V3.1 Terminus
FACTS Benchmark SuiteNot measured29.1%Only Gemma 3 27B measured
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 DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 3 27BLeader
Design Arena: websites1187Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: UI components1182Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: game dev1131Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: data viz1168Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: 3D1141Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: all code categories1175Not measuredOnly DeepSeek V3.1 Terminus measured
Design Arena: SVG1065Not measuredOnly DeepSeek V3.1 Terminus measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
General benchmarks for DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 3 27BLeader
IFBench57.0%31.8%DeepSeek V3.1 Terminus
Long context reasoning (AA-LCR)69.3%7.3%DeepSeek V3.1 Terminus
DTBench81.3%52.5%DeepSeek V3.1 Terminus
LMCA28.6%12.3%DeepSeek V3.1 Terminus
Fiction.LiveBenchNot measured33.3%Only Gemma 3 27B measured
Creative writing (Lech Mazur)Not measured79.9%Only Gemma 3 27B measured
LMArena Text14191358DeepSeek V3.1 Terminus
LMArena Text: instruction following14041321DeepSeek V3.1 Terminus
LMArena Text: creative writing14031345DeepSeek V3.1 Terminus
LMArena VisionNot measured1165Only Gemma 3 27B measured
LMArena Text: English14291377DeepSeek V3.1 Terminus
LMArena Text: non-English14081334DeepSeek V3.1 Terminus
LMArena Text: ChineseNot measured1346Only Gemma 3 27B measured
LMArena Text: GermanNot measured1362Only Gemma 3 27B measured
LMArena Text: JapaneseNot measured1287Only Gemma 3 27B measured
LMArena Text: KoreanNot measured1308Only Gemma 3 27B measured
LMArena Text: FrenchNot measured1368Only Gemma 3 27B measured
LMArena Text: SpanishNot measured1349Only Gemma 3 27B measured
LMArena Text: Russian14351349DeepSeek V3.1 Terminus
LMArena Text: Polish14271345DeepSeek V3.1 Terminus
LMArena Text: multi-turn14111345DeepSeek V3.1 Terminus
LMArena Text: longer queries14221333DeepSeek V3.1 Terminus
LMArena Text: writing and language14091347DeepSeek V3.1 Terminus
LMArena Text: entertainment and media13911320DeepSeek V3.1 Terminus
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 DeepSeek V3.1 Terminus and Gemma 3 27B
BenchmarkDeepSeek V3.1 TerminusGemma 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 V3.1 Terminus$0.0008Fits in one request
Gemma 3 27B$0.0002Fits in one request

Gemma 3 27B costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1 Terminus$0.018Fits in one request
Gemma 3 27B$0.0049Fits in one request

Gemma 3 27B costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1 Terminus$0.071Exceeds 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 V3.1 Terminus and Gemma 3 27B
SpecificationDeepSeek V3.1 TerminusGoogle Gemma 3 27B
MakerDeepSeekGoogle
WeightsOpen weightsOpen weights
ReleasedSeptember 22, 2025March 12, 2025
Context window164K131K
Input $/Mtok$0.3063$0.08
Output $/Mtok$1.0142$0.30
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 Terminus better than Gemma 3 27B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 Terminus for a larger context window (164K against 131K tokens).

Which is cheaper, DeepSeek V3.1 Terminus or Gemma 3 27B?

DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; Gemma 3 27B costs $0.08 and $0.30. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.1 Terminus or Gemma 3 27B?

DeepSeek V3.1 Terminus, with 164K tokens against 131K.

How many benchmarks is the DeepSeek V3.1 Terminus vs Gemma 3 27B comparison based on?

37 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.1 Terminus's coding index rests on 0 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