Noometry

Model comparison

Gemma 3 12B vs GLM-4.6V

GLM-4.6V is the stronger model overall, scoring 41.3 to 32.1 on the Noometry Index. Gemma 3 12B costs 6.0× less per token, which makes it the better buy when GLM-4.6V's lead doesn't matter for your workload.

Last verified . 10 shared benchmarks.

Gemma 3 12B Google

32.1

Rank #262 Confirmed

GLM-4.6V Z.ai (Zhipu)

41.3

Rank #137 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and GLM-4.6V in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GLM-4.6V leads 27.6 to 15.7.
  • Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.30 / $0.90 for GLM-4.6V.
  • Gemma 3 12B accepts more context: 131K tokens versus 128K.

Side by side

Gemma 3 12BGLM-4.6V
ProviderGoogleZ.ai (Zhipu)
Noometry Index32.141.3
Released2025-03-122025-12-08
WeightsOpenOpen
Context window131K128K
Max output8K33K
Input $ / M tokens$0.05$0.30
Output $ / M tokens$0.15$0.90
Results tracked2412

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

Category by category

Coding GLM-4.6V leads

Gemma 3 12B: 31.7 (#280), GLM-4.6V: 40.9 (#128)

BenchmarkGemma 3 12BGLM-4.6V
LMArena Coding12811390
SciCode17.4%—

Agentic & Tool Use Not comparable

Gemma 3 12B: 25.5 (#108), GLM-4.6V: —

BenchmarkGemma 3 12BGLM-4.6V
Berkeley Function Calling Leaderboard30.4%—

Reasoning GLM-4.6V leads

Gemma 3 12B: 15.7 (#313), GLM-4.6V: 27.6 (#115)

BenchmarkGemma 3 12BGLM-4.6V
LMArena Hard Prompts13091368
CritPt0%—
Chess Puzzles0%—
DTBench48.8%—
LMCA4.5%—
Epoch Capabilities Index123.5—

Math Not comparable

Gemma 3 12B: 22.3 (#279), GLM-4.6V: —

BenchmarkGemma 3 12BGLM-4.6V
OTIS Mock AIME 2024-202516.7%—
LMArena Math1307—

Knowledge GLM-4.6V leads

Gemma 3 12B: 26.5 (#257), GLM-4.6V: 38.0 (#149)

BenchmarkGemma 3 12BGLM-4.6V
LMArena Expert12481371
GPQA Diamond39.5%—
Vectara Hallucination Rate4.4%—

Multimodal Not comparable

Gemma 3 12B: —, GLM-4.6V: 34.8 (#90)

BenchmarkGemma 3 12BGLM-4.6V
LMArena Vision—1164
MindCube46.7%—

Multilingual GLM-4.6V leads

Gemma 3 12B: 45.7 (#165), GLM-4.6V: 48.6 (#141)

BenchmarkGemma 3 12BGLM-4.6V
LMArena Non-English13181359
LMArena Russian13351340
LMArena Chinese—1425
LMArena German1370—

Instruction Following GLM-4.6V leads

Gemma 3 12B: 68.6 (#186), GLM-4.6V: 71.4 (#151)

BenchmarkGemma 3 12BGLM-4.6V
LMArena Instruction Following12991352

Long Context GLM-4.6V leads

Gemma 3 12B: 40.0 (#162), GLM-4.6V: 41.3 (#143)

BenchmarkGemma 3 12BGLM-4.6V
LMArena Longer Query13171358

Writing & Preference GLM-4.6V leads

Gemma 3 12B: 47.5 (#209), GLM-4.6V: 56.6 (#137)

BenchmarkGemma 3 12BGLM-4.6V
LMArena Text13341377
LMArena Creative Writing13311347
LMArena Multi-Turn13341360
EQ-Bench Creative Writing1126—

Frequently asked questions

Is Gemma 3 12B better than GLM-4.6V?

GLM-4.6V is the stronger model overall, scoring 41.3 to 32.1 on the Noometry Index. Gemma 3 12B costs 6.0× less per token, which makes it the better buy when GLM-4.6V's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 12B or GLM-4.6V?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; GLM-4.6V lists at $0.30 and $0.90.

Is Gemma 3 12B or GLM-4.6V better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.9 versus 31.7 in the Noometry coding category.

Which has the bigger context window?

Gemma 3 12B does, with 131K tokens against 128K.

How many benchmarks do Gemma 3 12B and GLM-4.6V share?

10 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and GLM-4.6V has 12.

Related comparisons

Go deeper