Noometry

Model comparison

Gemma 3 12B vs Hunyuan Turbos 20250226

Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 32.1 on the Noometry Index.

Last verified . 12 shared benchmarks.

Gemma 3 12B Google

32.1

Rank #262 Confirmed

Hunyuan Turbos 20250226 Tencent

41.3

Rank #139 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and Hunyuan Turbos 20250226 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Hunyuan Turbos 20250226 leads 37.5 to 22.3.
  • Gemma 3 12B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 12BHunyuan Turbos 20250226
ProviderGoogleTencent
Noometry Index32.141.3
Released2025-03-12—
WeightsOpenProprietary
Context window131K—
Max output8K—
Input $ / M tokens$0.05—
Output $ / M tokens$0.15—
Results tracked2416

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

Category by category

Coding Hunyuan Turbos 20250226 leads

Gemma 3 12B: 31.7 (#280), Hunyuan Turbos 20250226: 40.0 (#152)

BenchmarkGemma 3 12BHunyuan Turbos 20250226
LMArena Coding12811361
SciCode17.4%—

Agentic & Tool Use Not comparable

Gemma 3 12B: 25.5 (#108), Hunyuan Turbos 20250226: —

BenchmarkGemma 3 12BHunyuan Turbos 20250226
Berkeley Function Calling Leaderboard30.4%—

Reasoning Hunyuan Turbos 20250226 leads

Gemma 3 12B: 15.7 (#313), Hunyuan Turbos 20250226: 27.8 (#113)

BenchmarkGemma 3 12BHunyuan Turbos 20250226
LMArena Hard Prompts13091374
CritPt0%—
Chess Puzzles0%—
DTBench48.8%—
LMCA4.5%—
Epoch Capabilities Index123.5—

Math Hunyuan Turbos 20250226 leads

Gemma 3 12B: 22.3 (#279), Hunyuan Turbos 20250226: 37.5 (#154)

BenchmarkGemma 3 12BHunyuan Turbos 20250226
LMArena Math13071359
OTIS Mock AIME 2024-202516.7%—

Knowledge Hunyuan Turbos 20250226 leads

Gemma 3 12B: 26.5 (#257), Hunyuan Turbos 20250226: 37.0 (#161)

BenchmarkGemma 3 12BHunyuan Turbos 20250226
LMArena Expert12481339
GPQA Diamond39.5%—
Vectara Hallucination Rate4.4%—

Multimodal Not comparable

Gemma 3 12B: —, Hunyuan Turbos 20250226: —

BenchmarkGemma 3 12BHunyuan Turbos 20250226
MindCube46.7%—

Multilingual Hunyuan Turbos 20250226 leads

Gemma 3 12B: 45.7 (#165), Hunyuan Turbos 20250226: 48.9 (#136)

BenchmarkGemma 3 12BHunyuan Turbos 20250226
LMArena Non-English13181363
LMArena German13701355
LMArena Russian13351368
LMArena Chinese—1417
LMArena French—1391
LMArena Japanese—1342
LMArena Korean—1351

Instruction Following Hunyuan Turbos 20250226 leads

Gemma 3 12B: 68.6 (#186), Hunyuan Turbos 20250226: 71.0 (#158)

BenchmarkGemma 3 12BHunyuan Turbos 20250226
LMArena Instruction Following12991344

Long Context Hunyuan Turbos 20250226 leads

Gemma 3 12B: 40.0 (#162), Hunyuan Turbos 20250226: 41.6 (#136)

BenchmarkGemma 3 12BHunyuan Turbos 20250226
LMArena Longer Query13171366

Writing & Preference Hunyuan Turbos 20250226 leads

Gemma 3 12B: 47.5 (#209), Hunyuan Turbos 20250226: 57.4 (#128)

BenchmarkGemma 3 12BHunyuan Turbos 20250226
LMArena Text13341377
LMArena Creative Writing13311359
LMArena Multi-Turn13341387
EQ-Bench Creative Writing1126—

Frequently asked questions

Is Gemma 3 12B better than Hunyuan Turbos 20250226?

Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 32.1 on the Noometry Index.

Is Gemma 3 12B or Hunyuan Turbos 20250226 better for coding?

Hunyuan Turbos 20250226 scores higher on coding benchmarks: 40.0 versus 31.7 in the Noometry coding category.

How many benchmarks do Gemma 3 12B and Hunyuan Turbos 20250226 share?

12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Hunyuan Turbos 20250226 has 16.

Related comparisons

Go deeper