Noometry

Model comparison

Gemini 3.1 Pro Preview vs Gemma 3 4B

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 27.9 on the Noometry Index. Gemma 3 4B costs 90× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 20 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #20 Confirmed

Gemma 3 4B Google

27.9

Rank #320 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and Gemma 3 4B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.1 Pro Preview leads 71.8 to 11.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.1 Pro Preview and 7.5% for Gemma 3 4B.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 131K.
  • Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro PreviewGemma 3 4B
ProviderGoogleGoogle
Noometry Index56.727.9
Released2026-02-192025-03-12
WeightsProprietaryOpen
Context window1.05M131K
Max output66K4K
Input $ / M tokens$2$0.04
Output $ / M tokens$12$0.08
Results tracked7122

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

Category by category

Coding Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 42.7 (#88), Gemma 3 4B: 35.3 (#214)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
LMArena Coding14831230
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1446—
SciCode58.9%—
GSO22.6%—
WeirdML72.1%—
MirrorCode8.9%—
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#33), Gemma 3 4B: 20.7 (#134)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
Terminal-Bench80.2%—
APEX-Agents35.3%—
Berkeley Function Calling Leaderboard—19.6%
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#9), Gemma 3 4B: 12.7 (#330)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
Chess Puzzles55%0%
LMArena Hard Prompts14841253
DTBench97.1%50.9%
LMCA53.8%2.8%
Epoch Capabilities Index154.92116.02
ARC-AGI-277.1%—
SimpleBench79.6%—
Kagi LLM Benchmark—25.2%
NYT Connections (extended)97.4%—
ARC-AGI-198%—
CritPt17.7%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Mystery Game Puzzles34%—
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 61.8 (#28), Gemma 3 4B: 15.8 (#286)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
OTIS Mock AIME 2024-202595.6%7.5%
LMArena Math14851239
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Gemma 3 4B: 11.8 (#294)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
GPQA Diamond94.4%23.2%
Vectara Hallucination Rate10.4%6.4%
LMArena Expert14841223
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—

Multimodal Not comparable

Gemini 3.1 Pro Preview: 38.1 (#60), Gemma 3 4B: —

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
LMArena Vision1296—
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.1 (#11), Gemma 3 4B: 42.7 (#189)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
LMArena Non-English14751273
LMArena German14911281
LMArena Russian14961294
LMArena Chinese1528—
LMArena French1488—
LMArena Japanese1494—
LMArena Korean1458—
LMArena Spanish1480—

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.1 (#31), Gemma 3 4B: 65.4 (#219)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
LMArena Instruction Following14651239

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.3 (#17), Gemma 3 4B: 38.6 (#189)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
LMArena Longer Query14821274
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.3 (#36), Gemma 3 4B: 42.2 (#234)

BenchmarkGemini 3.1 Pro PreviewGemma 3 4B
LMArena Text14801291
LMArena Creative Writing14821270
EQ-Bench Creative Writing14911068
LMArena Multi-Turn14861255
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Gemma 3 4B?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 27.9 on the Noometry Index. Gemma 3 4B costs 90× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview or Gemma 3 4B?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Gemma 3 4B better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 35.3 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 3.1 Pro Preview and Gemma 3 4B share?

20 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Gemma 3 4B has 22.

Related comparisons

Go deeper