Noometry

Model comparison

Gemma 2B vs GPT-4.1 nano

Gemma 2B is the stronger model overall, scoring 29.1 to 27.7 on the Noometry Index.

Last verified . 12 shared benchmarks.

Gemma 2B Google

29.1

Rank #305 Confirmed

GPT-4.1 nano OpenAI

27.7

Rank #322 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Gemma 2B scores higher in 4 categories and GPT-4.1 nano in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where GPT-4.1 nano leads 68.0 to 48.8.
  • Gemma 2B has downloadable open weights; the other is API-only.

Side by side

Gemma 2BGPT-4.1 nano
ProviderGoogleOpenAI
Noometry Index29.127.7
Released2024-02-212025-04-14
WeightsOpenProprietary
Context window—1.05M
Max output—33K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.40
Results tracked2338

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Gemma 2B leads

Gemma 2B: 28.9 (#300), GPT-4.1 nano: 23.8 (#325)

BenchmarkGemma 2BGPT-4.1 nano
LMArena Coding10101306
Aider Polyglot—8.9%
SciCode—25.9%
WeirdML—19%
HumanEval+20.7%—
MBPP+34.1%—

Agentic & Tool Use Not comparable

Gemma 2B: —, GPT-4.1 nano: 26.3 (#98)

BenchmarkGemma 2BGPT-4.1 nano
Berkeley Function Calling Leaderboard—33%

Reasoning Gemma 2B leads

Gemma 2B: 17.9 (#275), GPT-4.1 nano: 8.6 (#344)

BenchmarkGemma 2BGPT-4.1 nano
LMArena Hard Prompts9891286
Epoch Capabilities Index93.57129.62
ARC-AGI-2—0%
Kagi LLM Benchmark—33.3%
ARC-AGI-1—0%
CritPt—0%
DTBench—52.5%
LMCA—5.5%
BIG-Bench Hard35.2%—
HellaSwag71.4%—
PIQA77.3%—
WinoGrande65.4%—

Math Gemma 2B leads

Gemma 2B: 27.6 (#237), GPT-4.1 nano: 25.5 (#246)

BenchmarkGemma 2BGPT-4.1 nano
LMArena Math10091274
OTIS Mock AIME 2024-2025—28.9%
Omni-MATH—36.7%
MATH Level 5—70%
FrontierMath (Feb 2025 set)—1%
GSM8K17.7%—

Knowledge Not comparable

Gemma 2B: —, GPT-4.1 nano: 21.8 (#268)

BenchmarkGemma 2BGPT-4.1 nano
GPQA Diamond—48.9%
SimpleQA Verified—6%
MMLU-Pro—55%
GPQA (HELM)—50.7%
LMArena Expert—1272
ARC (AI2) Challenge42.1%—
BoolQ69.4%—
MMLU42.3%—
TriviaQA53.2%—

Multimodal Not comparable

Gemma 2B: —, GPT-4.1 nano: 28.6 (#108)

BenchmarkGemma 2BGPT-4.1 nano
LMArena Vision—1063

Multilingual GPT-4.1 nano leads

Gemma 2B: 23.1 (#289), GPT-4.1 nano: 41.8 (#200)

BenchmarkGemma 2BGPT-4.1 nano
LMArena Non-English9581260
LMArena Chinese9861270
LMArena Russian9371261
LMArena German—1288
LMArena Japanese—1199

Instruction Following GPT-4.1 nano leads

Gemma 2B: 48.8 (#297), GPT-4.1 nano: 68.0 (#188)

BenchmarkGemma 2BGPT-4.1 nano
LMArena Instruction Following9711267
IFEval—84.3%

Long Context Gemma 2B leads

Gemma 2B: 29.9 (#286), GPT-4.1 nano: 23.7 (#291)

BenchmarkGemma 2BGPT-4.1 nano
LMArena Longer Query9811283
Fiction.LiveBench—25%

Writing & Preference GPT-4.1 nano leads

Gemma 2B: 24.1 (#303), GPT-4.1 nano: 40.7 (#238)

BenchmarkGemma 2BGPT-4.1 nano
LMArena Text10021285
LMArena Creative Writing9861260
LMArena Multi-Turn9451277
EQ-Bench Creative Writing—946
WildBench—81.2%

Frequently asked questions

Is Gemma 2B better than GPT-4.1 nano?

Gemma 2B is the stronger model overall, scoring 29.1 to 27.7 on the Noometry Index.

Is Gemma 2B or GPT-4.1 nano better for coding?

Gemma 2B scores higher on coding benchmarks: 28.9 versus 23.8 in the Noometry coding category.

How many benchmarks do Gemma 2B and GPT-4.1 nano share?

12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and GPT-4.1 nano has 38.

Related comparisons

Go deeper