Noometry

Model comparison

Claude 3 Sonnet vs Gemma 3 12B

Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.0 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Gemma 3 12B Google

32.1

Rank #262 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and Gemma 3 12B in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 3 12B leads 22.3 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 16.7% for Gemma 3 12B.
  • Gemma 3 12B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetGemma 3 12B
ProviderAnthropicGoogle
Noometry Index29.032.1
Released2024-02-292025-03-12
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.05
Output $ / M tokens—$0.15
Results tracked3024

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

Category by category

Coding Gemma 3 12B leads

Claude 3 Sonnet: 29.6 (#302), Gemma 3 12B: 31.7 (#280)

BenchmarkClaude 3 SonnetGemma 3 12B
LMArena Coding12231281
SciCode—17.4%
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Gemma 3 12B: 25.5 (#108)

BenchmarkClaude 3 SonnetGemma 3 12B
Berkeley Function Calling Leaderboard—30.4%

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 20.5 (#237), Gemma 3 12B: 15.7 (#313)

BenchmarkClaude 3 SonnetGemma 3 12B
LMArena Hard Prompts11971309
DTBench53.6%48.8%
Epoch Capabilities Index120.7123.5
CritPt—0%
Chess Puzzles—0%
LMCA—4.5%
WinoGrande75.1%—

Math Gemma 3 12B leads

Claude 3 Sonnet: 10.7 (#310), Gemma 3 12B: 22.3 (#279)

BenchmarkClaude 3 SonnetGemma 3 12B
OTIS Mock AIME 2024-20252.5%16.7%
LMArena Math12131307
MATH Level 518.2%—

Knowledge Gemma 3 12B leads

Claude 3 Sonnet: 21.1 (#276), Gemma 3 12B: 26.5 (#257)

BenchmarkClaude 3 SonnetGemma 3 12B
GPQA Diamond40.6%39.5%
LMArena Expert11731248
Vectara Hallucination Rate—4.4%
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Gemma 3 12B: —

BenchmarkClaude 3 SonnetGemma 3 12B
LMArena Vision984—
MindCube—46.7%

Multilingual Gemma 3 12B leads

Claude 3 Sonnet: 37.8 (#234), Gemma 3 12B: 45.7 (#165)

BenchmarkClaude 3 SonnetGemma 3 12B
LMArena Non-English12051318
LMArena German12041370
LMArena Russian12271335
LMArena Chinese1189—
LMArena French1229—
LMArena Japanese1131—
LMArena Korean1128—
LMArena Spanish1204—

Instruction Following Gemma 3 12B leads

Claude 3 Sonnet: 62.8 (#235), Gemma 3 12B: 68.6 (#186)

BenchmarkClaude 3 SonnetGemma 3 12B
LMArena Instruction Following11991299

Long Context Gemma 3 12B leads

Claude 3 Sonnet: 36.7 (#228), Gemma 3 12B: 40.0 (#162)

BenchmarkClaude 3 SonnetGemma 3 12B
LMArena Longer Query12111317

Writing & Preference Gemma 3 12B leads

Claude 3 Sonnet: 42.1 (#238), Gemma 3 12B: 47.5 (#209)

BenchmarkClaude 3 SonnetGemma 3 12B
LMArena Text12181334
LMArena Creative Writing11861331
LMArena Multi-Turn12271334
EQ-Bench Creative Writing—1126

Frequently asked questions

Is Claude 3 Sonnet better than Gemma 3 12B?

Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Gemma 3 12B better for coding?

Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Gemma 3 12B share?

16 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemma 3 12B has 24.

Related comparisons

Go deeper