Noometry

Model comparison

Gemma 3 12B vs GLM-4.5V

GLM-4.5V is the stronger model overall, scoring 39.2 to 31.8 on the Noometry Index. Gemma 3 12B costs 12× less per token, which makes it the better buy when GLM-4.5V's lead doesn't matter for your workload.

Last verified . 11 shared benchmarks.

Gemma 3 12B Google

31.8

Rank #255 Confirmed

GLM-4.5V Z.ai (Zhipu)

39.2

Rank #158 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Gemma 3 12B scores higher in 2 categories and GLM-4.5V in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.5V leads 34.7 to 21.0.
  • Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.60 / $1.80 for GLM-4.5V.
  • Gemma 3 12B accepts more context: 131K tokens versus 64K.

Side by side

Gemma 3 12BGLM-4.5V
ProviderGoogleZ.ai (Zhipu)
Noometry Index31.839.2
Released2025-03-122025-08-11
WeightsOpenOpen
Context window131K64K
Max output8K16K
Input $ / M tokens$0.05$0.60
Output $ / M tokens$0.15$1.80
Results tracked2415

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

Category by category

Coding GLM-4.5V leads

Gemma 3 12B: 31.2 (#276), GLM-4.5V: 38.9 (#152)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Coding12811347
SciCode17.4%—

Agentic & Tool Use Not comparable

Gemma 3 12B: 25.3 (#101), GLM-4.5V: —

BenchmarkGemma 3 12BGLM-4.5V
Berkeley Function Calling Leaderboard30.4%—

Reasoning GLM-4.5V leads

Gemma 3 12B: 15.2 (#307), GLM-4.5V: 26.5 (#118)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Hard Prompts13091335
Kagi LLM Benchmark—59.8%
CritPt0%—
Chess Puzzles0%—
DTBench48.8%—
LMCA4.5%—
Epoch Capabilities Index123.49—

Math GLM-4.5V leads

Gemma 3 12B: 21.0 (#273), GLM-4.5V: 34.7 (#157)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Math13071353
OTIS Mock AIME 2024-202516.7%—

Knowledge GLM-4.5V leads

Gemma 3 12B: 26.5 (#250), GLM-4.5V: 36.8 (#155)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Expert12481353
GPQA Diamond39.5%—
Vectara Hallucination Rate4.4%—

Multimodal Not comparable

Gemma 3 12B: —, GLM-4.5V: 33.6 (#86)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Vision—1154
MindCube46.7%—

Multilingual Gemma 3 12B leads

Gemma 3 12B: 45.9 (#160), GLM-4.5V: 44.9 (#172)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Non-English13181304
LMArena Russian13351299
LMArena Chinese—1338
LMArena German1370—
LMArena Spanish—1335

Instruction Following Too close to call

Gemma 3 12B: 68.8 (#179), GLM-4.5V: 69.4 (#170)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Instruction Following12991311

Long Context Too close to call

Gemma 3 12B: 40.0 (#157), GLM-4.5V: 39.6 (#166)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Longer Query13171305

Writing & Preference GLM-4.5V leads

Gemma 3 12B: 47.7 (#205), GLM-4.5V: 52.7 (#162)

BenchmarkGemma 3 12BGLM-4.5V
LMArena Text13341333
LMArena Creative Writing13311295
LMArena Multi-Turn13341333
EQ-Bench Creative Writing1126—

Frequently asked questions

Is Gemma 3 12B better than GLM-4.5V?

GLM-4.5V is the stronger model overall, scoring 39.2 to 31.8 on the Noometry Index. Gemma 3 12B costs 12× less per token, which makes it the better buy when GLM-4.5V's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 12B or GLM-4.5V?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; GLM-4.5V lists at $0.60 and $1.80.

Is Gemma 3 12B or GLM-4.5V better for coding?

GLM-4.5V scores higher on coding benchmarks: 38.9 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

Gemma 3 12B does, with 131K tokens against 64K.

How many benchmarks do Gemma 3 12B and GLM-4.5V share?

11 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and GLM-4.5V has 15.

Related comparisons

Go deeper