Enter opens the highlighted result. Esc closes.

Gemma 2 27B vs Nemotron 3 Nano 30B A3B

Nemotron 3 Nano 30B A3B costs 3.0x less per output token than Gemma 2 27B ($0.22 vs $0.65 per million). Updated October 22, 2026; 28 benchmarks have a result for both.

Replace Gemma 2 27B Replace Nemotron 3 Nano 30B A3B
Gemma 2 27BGoogle
Coding
No data
Overall
No data
Output $/M
$0.65
0
Nemotron 3 Nano 30B A3BNVIDIA
Coding
No data
Overall
No data
Output $/M
$0.22
28
vs boards won of 28 shared

Gemma 2 27B or Nemotron 3 Nano 30B A3B: which to pick

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

Pick Gemma 2 27B for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGemma 2 27BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BNemotron 3 Nano 30B A3BNVIDIANot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
28
Gemma 2 27B only
8
Nemotron 3 Nano 30B A3B only
14
Like-for-like categories
5 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
Gemma 2 27B not benchmarked, Nemotron 3 Nano 30B A3B not benchmarked.
Widest category
Reasoning, 28.0 points apart on average over 3 shared benchmarks.
Widest single gap
LMArena Text: expert: Gemma 2 27B 1171 against Nemotron 3 Nano 30B A3B 1355, 30.6 points apart on a 0 to 100 scale.
Output price
Gemma 2 27B $0.65 against Nemotron 3 Nano 30B A3B $0.22 per million output tokens, 3.0x apart.
Context window
Gemma 2 27B takes 8K tokens, Nemotron 3 Nano 30B A3B 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
CategoryGemma 2 27BBarsNemotron 3 Nano 30B A3BTies
Coding02
Reasoning03
Math02
Knowledge04
General017
All shared boards028
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
AA Coding IndexNot measured14.4Only Nemotron 3 Nano 30B A3B measured
LiveCodeBench (Artificial Analysis run)Not measured74.1%Only Nemotron 3 Nano 30B A3B measured
SciCodeNot measured30.6%Only Nemotron 3 Nano 30B A3B measured
Terminal-Bench Hard (Artificial Analysis run)Not measured13.6%Only Nemotron 3 Nano 30B A3B measured
LMArena Text: coding12111378Nemotron 3 Nano 30B A3B
LMArena Text: software and IT12281383Nemotron 3 Nano 30B A3B
Neither model has a result on the other 37 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
AA Intelligence IndexNot measured8.9Only Nemotron 3 Nano 30B A3B measured
Epoch Capabilities Index122.1Not measuredOnly Gemma 2 27B measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
AA Agentic IndexNot measured1.0Only Nemotron 3 Nano 30B A3B measured
τ²-Bench TelecomNot measured40.9%Only Nemotron 3 Nano 30B A3B measured
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
GPQA Diamond (Artificial Analysis run)Not measured75.7%Only Nemotron 3 Nano 30B A3B measured
Humanity's Last Exam (Artificial Analysis run)Not measured11.4%Only Nemotron 3 Nano 30B A3B measured
GPQA Diamond (Epoch AI run)36.5%Not measuredOnly Gemma 2 27B measured
LMArena Text: hard prompts11981348Nemotron 3 Nano 30B A3B
LMArena Text: expert11711355Nemotron 3 Nano 30B A3B
LMArena Text: hard prompts in English12061376Nemotron 3 Nano 30B A3B
Neither model has a result on the other 17 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
AA Math IndexNot measured91.0Only Nemotron 3 Nano 30B A3B measured
AIME 2025 (Artificial Analysis run)Not measured91.0%Only Nemotron 3 Nano 30B A3B measured
OTIS Mock AIME1.4%Not measuredOnly Gemma 2 27B measured
MATH level 527.9%Not measuredOnly Gemma 2 27B measured
LMArena Text: math12121371Nemotron 3 Nano 30B A3B
LMArena Text: mathematical work12211375Nemotron 3 Nano 30B A3B
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
LegalBench (Vals AI)68.0%Not measuredOnly Gemma 2 27B measured
MMLU Pro (Artificial Analysis run)Not measured79.4%Only Nemotron 3 Nano 30B A3B measured
MMLU75.7%Not measuredOnly Gemma 2 27B measured
LMArena Text: science12281353Nemotron 3 Nano 30B A3B
LMArena Text: medicine and healthcare11981349Nemotron 3 Nano 30B A3B
LMArena Text: legal and government12411341Nemotron 3 Nano 30B A3B
LMArena Text: business and finance12081346Nemotron 3 Nano 30B A3B
Neither model has a result on the other 13 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
General benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
IFBenchNot measured71.1%Only Nemotron 3 Nano 30B A3B measured
Long context reasoning (AA-LCR)Not measured38.0%Only Nemotron 3 Nano 30B A3B measured
DTBench48.0%Not measuredOnly Gemma 2 27B measured
LMCA7.1%Not measuredOnly Gemma 2 27B measured
LMArena Text12311348Nemotron 3 Nano 30B A3B
LMArena Text: instruction following12061303Nemotron 3 Nano 30B A3B
LMArena Text: creative writing12401269Nemotron 3 Nano 30B A3B
LMArena Text: English12421377Nemotron 3 Nano 30B A3B
LMArena Text: non-English12171320Nemotron 3 Nano 30B A3B
LMArena Text: Chinese12211383Nemotron 3 Nano 30B A3B
LMArena Text: German12091348Nemotron 3 Nano 30B A3B
LMArena Text: Japanese11751268Nemotron 3 Nano 30B A3B
LMArena Text: Korean11741269Nemotron 3 Nano 30B A3B
LMArena Text: French12481396Nemotron 3 Nano 30B A3B
LMArena Text: Spanish12281376Nemotron 3 Nano 30B A3B
LMArena Text: Russian12341304Nemotron 3 Nano 30B A3B
LMArena Text: Polish12771303Nemotron 3 Nano 30B A3B
LMArena Text: multi-turn12241319Nemotron 3 Nano 30B A3B
LMArena Text: longer queries12301300Nemotron 3 Nano 30B A3B
LMArena Text: writing and language12491283Nemotron 3 Nano 30B A3B
LMArena Text: entertainment and media12121293Nemotron 3 Nano 30B A3B
Neither model has a result on the other 27 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 2 27B and Nemotron 3 Nano 30B A3B
BenchmarkGemma 2 27BNemotron 3 Nano 30B A3BLeader
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

Gemma 2 27B$0.0010Fits in one request
Nemotron 3 Nano 30B A3B$0.0002Fits in one request

Nemotron 3 Nano 30B A3B costs less

Repository review

50K input + 3K output tokens

Gemma 2 27B$0.034Exceeds the context window
Nemotron 3 Nano 30B A3B$0.0034Fits in one request

Nemotron 3 Nano 30B A3B costs less

Agent loop

200K input + 10K output tokens

Gemma 2 27B$0.137Exceeds the context window
Nemotron 3 Nano 30B A3B$0.013Fits in one request

Nemotron 3 Nano 30B A3B 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 Gemma 2 27B and Nemotron 3 Nano 30B A3B
SpecificationGoogle Gemma 2 27BNVIDIA Nemotron 3 Nano 30B A3B
MakerGoogleNVIDIA
WeightsOpen weightsOpen weights
ReleasedJuly 13, 2024December 14, 2025
Context window8K262K
Input $/Mtok$0.65$0.055
Output $/Mtok$0.65$0.22
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 2 27B better than Nemotron 3 Nano 30B A3B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 2 27B for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Gemma 2 27B or Nemotron 3 Nano 30B A3B?

Gemma 2 27B costs $0.65 per million input tokens and $0.65 per million output tokens; Nemotron 3 Nano 30B A3B costs $0.055 and $0.22. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 2 27B or Nemotron 3 Nano 30B A3B?

Nemotron 3 Nano 30B A3B, with 262K tokens against 8K.

How many benchmarks is the Gemma 2 27B vs Nemotron 3 Nano 30B A3B comparison based on?

28 benchmarks have a result for both models as of October 22, 2026. Gemma 2 27B's coding index rests on 0 independent benchmarks and Nemotron 3 Nano 30B A3B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next