Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 Terminus vs Gemma 3 4B

DeepSeek V3.1 Terminus leads Gemma 3 4B on the Artificial Analysis Intelligence Index, 14.8 to 4.8, and Gemma 3 4B costs 13.5x less per output token ($0.075 vs $1.0142 per million). Updated October 21, 2026; 34 benchmarks have a result for both.

Replace DeepSeek V3.1 Terminus Replace Gemma 3 4B
DeepSeek V3.1 TerminusDeepSeek
Coding
No data
Overall
No data
Output $/M
$1.0142
34
Gemma 3 4BGoogle
Coding
No data
Overall
22.6
Output $/M
$0.075
0
vs boards won of 34 shared

DeepSeek V3.1 Terminus or Gemma 3 4B: 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 4BGoogleNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
34
DeepSeek V3.1 Terminus only
11
Gemma 3 4B only
8
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 4B not benchmarked.
Widest category
Math, 60.4 points apart on average over 3 shared benchmarks.
Widest single gap
AA Math Index: DeepSeek V3.1 Terminus 89.7 against Gemma 3 4B 12.7, 77.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 Terminus $1.0142 against Gemma 3 4B $0.075 per million output tokens, 13.5x apart.
Context window
DeepSeek V3.1 Terminus takes 164K tokens, Gemma 3 4B 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 4BTies
Coding50
Intelligence10
Agentic work10
Reasoning50
Math30
Knowledge50
General140
All shared boards340
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for DeepSeek V3.1 Terminus and Gemma 3 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
AA Coding Index43.52.7DeepSeek V3.1 Terminus
LiveCodeBench (Artificial Analysis run)79.8%11.2%DeepSeek V3.1 Terminus
SciCode38.0%Not measuredOnly DeepSeek V3.1 Terminus measured
Terminal-Bench Hard (Artificial Analysis run)31.8%0.8%DeepSeek V3.1 Terminus
ALE-Bench745.2Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: coding14251230DeepSeek V3.1 Terminus
LMArena Text: software and IT14261269DeepSeek V3.1 Terminus
SciCodeNot measured0.0%Only Gemma 3 4B measured
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.1 Terminus and Gemma 3 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
AA Intelligence Index14.84.8DeepSeek V3.1 Terminus
Epoch Capabilities IndexNot measured115.9Only Gemma 3 4B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.1 Terminus and Gemma 3 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
AA Agentic Index6.8Not measuredOnly DeepSeek V3.1 Terminus measured
τ²-Bench Telecom37.1%5.0%DeepSeek V3.1 Terminus
Berkeley Function Calling Leaderboard (BFCL)Not measured19.6%Only Gemma 3 4B 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 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
GPQA Diamond (Artificial Analysis run)79.2%29.1%DeepSeek V3.1 Terminus
Humanity's Last Exam (Artificial Analysis run)16.4%5.3%DeepSeek V3.1 Terminus
GPQA Diamond (Epoch AI run)Not measured23.2%Only Gemma 3 4B measured
LMArena Text: hard prompts14261253DeepSeek V3.1 Terminus
LMArena Text: expertNot measured1223Only Gemma 3 4B measured
LMArena Text: hard prompts in English14321253DeepSeek V3.1 Terminus
Kagi LLM Benchmark57.4%25.2%DeepSeek V3.1 Terminus
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for DeepSeek V3.1 Terminus and Gemma 3 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
AA Math Index89.712.7DeepSeek V3.1 Terminus
AIME 2025 (Artificial Analysis run)89.7%12.7%DeepSeek V3.1 Terminus
OTIS Mock AIMENot measured7.5%Only Gemma 3 4B measured
LMArena Text: math14021239DeepSeek V3.1 Terminus
LMArena Text: mathematical workNot measured1256Only Gemma 3 4B measured
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.1 Terminus and Gemma 3 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
MMLU Pro (Artificial Analysis run)85.1%41.7%DeepSeek V3.1 Terminus
LMArena Text: science14511306DeepSeek V3.1 Terminus
LMArena Text: medicine and healthcare14681342DeepSeek V3.1 Terminus
LMArena Text: legal and government14571327DeepSeek V3.1 Terminus
LMArena Text: business and finance14141311DeepSeek V3.1 Terminus
Neither model has a result on the other 13 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 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
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 viz1167Not 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 index140
General benchmarks for DeepSeek V3.1 Terminus and Gemma 3 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
IFBench57.0%28.3%DeepSeek V3.1 Terminus
Long context reasoning (AA-LCR)69.3%6.7%DeepSeek V3.1 Terminus
DTBench81.3%50.9%DeepSeek V3.1 Terminus
LMCA28.6%2.8%DeepSeek V3.1 Terminus
LMArena Text14191291DeepSeek V3.1 Terminus
LMArena Text: instruction following14041239DeepSeek V3.1 Terminus
LMArena Text: creative writing14031270DeepSeek V3.1 Terminus
LMArena Text: English14291300DeepSeek V3.1 Terminus
LMArena Text: non-English14081273DeepSeek V3.1 Terminus
LMArena Text: GermanNot measured1281Only Gemma 3 4B measured
LMArena Text: Russian14351294DeepSeek V3.1 Terminus
LMArena Text: Polish1427Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: multi-turn14111255DeepSeek V3.1 Terminus
LMArena Text: longer queries14221273DeepSeek V3.1 Terminus
LMArena Text: writing and language14091288DeepSeek V3.1 Terminus
LMArena Text: entertainment and media13911233DeepSeek V3.1 Terminus
Neither model has a result on the other 30 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 4B
BenchmarkDeepSeek V3.1 TerminusGemma 3 4BLeader
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 4B$0.0001Fits in one request

Gemma 3 4B costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1 Terminus$0.018Fits in one request
Gemma 3 4B$0.0025Fits in one request

Gemma 3 4B costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1 Terminus$0.071Exceeds the context window
Gemma 3 4B$0.0097Exceeds the context window

Gemma 3 4B 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 4B
SpecificationDeepSeek V3.1 TerminusGoogle Gemma 3 4B
MakerDeepSeekGoogle
WeightsOpen weightsOpen weights
ReleasedSeptember 22, 2025March 13, 2025
Context window164K131K
Input $/Mtok$0.3063$0.045
Output $/Mtok$1.0142$0.075
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 4B 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 4B?

DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; Gemma 3 4B costs $0.045 and $0.075. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.1 Terminus or Gemma 3 4B?

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

How many benchmarks is the DeepSeek V3.1 Terminus vs Gemma 3 4B comparison based on?

34 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.1 Terminus's coding index rests on 0 independent benchmarks and Gemma 3 4B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next