Noometry

Model comparison

Gemini 1.5 Flash 8B vs Gemma 3 12B

Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.9 on the Noometry Index.

Last verified . 15 shared benchmarks.

Gemini 1.5 Flash 8B Google

29.9

Rank #301 Confirmed

Gemma 3 12B Google

32.1

Rank #262 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Gemini 1.5 Flash 8B scores higher in 2 categories and Gemma 3 12B in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemma 3 12B leads 26.5 to 16.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.6% for Gemini 1.5 Flash 8B and 16.7% for Gemma 3 12B.
  • Gemma 3 12B has downloadable open weights; the other is API-only.

Side by side

Gemini 1.5 Flash 8BGemma 3 12B
ProviderGoogleGoogle
Noometry Index29.932.1
Released2024-10-032025-03-12
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.05
Output $ / M tokens—$0.15
Results tracked2124

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

Category by category

Coding Gemini 1.5 Flash 8B leads

Gemini 1.5 Flash 8B: 35.5 (#225), Gemma 3 12B: 31.7 (#280)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
LMArena Coding12181281
SciCode—17.4%

Agentic & Tool Use Not comparable

Gemini 1.5 Flash 8B: —, Gemma 3 12B: 25.5 (#108)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
Berkeley Function Calling Leaderboard—30.4%

Reasoning Gemini 1.5 Flash 8B leads

Gemini 1.5 Flash 8B: 20.0 (#244), Gemma 3 12B: 15.7 (#313)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
LMArena Hard Prompts12091309
DTBench50%48.8%
CritPt—0%
Chess Puzzles—0%
LMCA—4.5%
Epoch Capabilities Index—123.5

Math Gemma 3 12B leads

Gemini 1.5 Flash 8B: 14.2 (#302), Gemma 3 12B: 22.3 (#279)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
OTIS Mock AIME 2024-20254.6%16.7%
LMArena Math12071307

Knowledge Gemma 3 12B leads

Gemini 1.5 Flash 8B: 16.0 (#289), Gemma 3 12B: 26.5 (#257)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
GPQA Diamond33%39.5%
LMArena Expert11851248
Vectara Hallucination Rate—4.4%

Multimodal Not comparable

Gemini 1.5 Flash 8B: 28.2 (#115), Gemma 3 12B: —

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
LMArena Vision1044—
MindCube—46.7%

Multilingual Gemma 3 12B leads

Gemini 1.5 Flash 8B: 38.5 (#229), Gemma 3 12B: 45.7 (#165)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
LMArena Non-English12151318
LMArena German12061370
LMArena Russian12361335
LMArena Chinese1231—
LMArena French1234—
LMArena Japanese1150—
LMArena Korean1140—
LMArena Spanish1212—

Instruction Following Gemma 3 12B leads

Gemini 1.5 Flash 8B: 62.8 (#236), Gemma 3 12B: 68.6 (#186)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
LMArena Instruction Following11991299

Long Context Gemma 3 12B leads

Gemini 1.5 Flash 8B: 37.0 (#225), Gemma 3 12B: 40.0 (#162)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
LMArena Longer Query12191317

Writing & Preference Gemma 3 12B leads

Gemini 1.5 Flash 8B: 42.8 (#232), Gemma 3 12B: 47.5 (#209)

BenchmarkGemini 1.5 Flash 8BGemma 3 12B
LMArena Text12261334
LMArena Creative Writing12181331
LMArena Multi-Turn11851334
EQ-Bench Creative Writing—1126

Frequently asked questions

Is Gemini 1.5 Flash 8B better than Gemma 3 12B?

Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.9 on the Noometry Index.

Is Gemini 1.5 Flash 8B or Gemma 3 12B better for coding?

Gemini 1.5 Flash 8B scores higher on coding benchmarks: 35.5 versus 31.7 in the Noometry coding category.

How many benchmarks do Gemini 1.5 Flash 8B and Gemma 3 12B share?

15 benchmarks have published results for both models. Gemini 1.5 Flash 8B has 21 scored results on Noometry and Gemma 3 12B has 24.

Related comparisons

Go deeper