Noometry

Model comparison

Gemini 3.1 Pro Preview vs Gemma 3 12B

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 32.1 on the Noometry Index. Gemma 3 12B costs 60× 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 . 22 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Gemma 3 12B Google

32.1

Rank #262 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and Gemma 3 12B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 15.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.1 Pro Preview and 16.7% for Gemma 3 12B.
  • Gemma 3 12B is cheaper at $0.05 / $0.15 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 12B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro PreviewGemma 3 12B
ProviderGoogleGoogle
Noometry Index56.732.1
Released2026-02-192025-03-12
WeightsProprietaryOpen
Context window1.05M131K
Max output66K8K
Input $ / M tokens$2$0.05
Output $ / M tokens$12$0.15
Results tracked7124

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: 42.5 (#99), Gemma 3 12B: 31.7 (#280)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
SciCode58.9%17.4%
LMArena Coding14841281
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1447—
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 (#34), Gemma 3 12B: 25.5 (#108)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
Terminal-Bench80.2%—
APEX-Agents35.3%—
Berkeley Function Calling Leaderboard—30.4%
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 (#12), Gemma 3 12B: 15.7 (#313)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
CritPt17.7%0%
Chess Puzzles55%0%
LMArena Hard Prompts14851309
DTBench97.1%48.8%
LMCA53.8%4.5%
Epoch Capabilities Index154.77123.5
ARC-AGI-277.1%—
SimpleBench79.6%—
NYT Connections (extended)97.4%—
ARC-AGI-198%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Mystery Game Puzzles34%—
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Gemma 3 12B: 22.3 (#279)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
OTIS Mock AIME 2024-202595.6%16.7%
LMArena Math14851307
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 12B: 26.5 (#257)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
GPQA Diamond94.4%39.5%
Vectara Hallucination Rate10.4%4.4%
LMArena Expert14851248
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—

Multimodal Not comparable

Gemini 3.1 Pro Preview: 37.9 (#69), Gemma 3 12B: —

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
LMArena Vision1296—
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—
MindCube—46.7%

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), Gemma 3 12B: 45.7 (#165)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
LMArena Non-English14771318
LMArena German14911370
LMArena Russian14981335
LMArena Chinese1529—
LMArena French1487—
LMArena Japanese1493—
LMArena Korean1455—
LMArena Spanish1479—

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Gemma 3 12B: 68.6 (#186)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
LMArena Instruction Following14661299

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Gemma 3 12B: 40.0 (#162)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
LMArena Longer Query14831317
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), Gemma 3 12B: 47.5 (#209)

BenchmarkGemini 3.1 Pro PreviewGemma 3 12B
LMArena Text14811334
LMArena Creative Writing14821331
EQ-Bench Creative Writing14911126
LMArena Multi-Turn14881334
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Gemma 3 12B?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 32.1 on the Noometry Index. Gemma 3 12B costs 60× 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 12B?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Gemma 3 12B better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 31.7 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 12B share?

22 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Gemma 3 12B has 24.

Related comparisons

Go deeper