Noometry

Model comparison

Gemma 3 4B vs GLM-4.7

GLM-4.7 is the stronger model overall, scoring 42.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 20× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Last verified . 18 shared benchmarks.

Gemma 3 4B Google

28.1

Rank #326 Confirmed

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and GLM-4.7 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 11.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 83.3% for GLM-4.7.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
  • GLM-4.7 accepts more context: 205K tokens versus 131K.

Side by side

Gemma 3 4BGLM-4.7
ProviderGoogleZ.ai (Zhipu)
Noometry Index28.142.0
Released2025-03-122025-12-22
WeightsOpenOpen
Context window131K205K
Max output4K131K
Input $ / M tokens$0.04$0.60
Output $ / M tokens$0.08$2.20
Results tracked2236

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

Category by category

Coding GLM-4.7 leads

Gemma 3 4B: 35.9 (#215), GLM-4.7: 44.0 (#79)

BenchmarkGemma 3 4BGLM-4.7
LMArena Coding12301454
LMArena WebDev—1435
SciCode—45.1%
ALE-Bench—399.48

Agentic & Tool Use GLM-4.7 leads

Gemma 3 4B: 20.9 (#142), GLM-4.7: 26.5 (#103)

BenchmarkGemma 3 4BGLM-4.7
Terminal-Bench—33.4%
Berkeley Function Calling Leaderboard19.6%—
Vending-Bench 2—2,377

Reasoning GLM-4.7 leads

Gemma 3 4B: 13.2 (#335), GLM-4.7: 24.3 (#164)

BenchmarkGemma 3 4BGLM-4.7
Chess Puzzles0%6%
LMArena Hard Prompts12531443
Epoch Capabilities Index116.02143.51
SimpleBench—47.7%
Kagi LLM Benchmark25.2%—
CritPt—1.7%
DTBench50.9%—
LMCA2.8%—

Math GLM-4.7 leads

Gemma 3 4B: 16.8 (#292), GLM-4.7: 38.6 (#135)

BenchmarkGemma 3 4BGLM-4.7
OTIS Mock AIME 2024-20257.5%83.3%
LMArena Math12391423
ProofBench—6%
FrontierMath (Feb 2025 set)—2.4%
FrontierMath Tier 4 (v1)—0%

Knowledge GLM-4.7 leads

Gemma 3 4B: 11.8 (#299), GLM-4.7: 47.0 (#80)

BenchmarkGemma 3 4BGLM-4.7
GPQA Diamond23.2%83.3%
Vectara Hallucination Rate6.4%11.7%
LMArena Expert12231424
SimpleQA Verified—32.2%

Multilingual GLM-4.7 leads

Gemma 3 4B: 42.5 (#194), GLM-4.7: 52.8 (#79)

BenchmarkGemma 3 4BGLM-4.7
LMArena Non-English12731417
LMArena German12811424
LMArena Russian12941423
LMArena Chinese—1495
LMArena French—1432
LMArena Japanese—1439
LMArena Korean—1399
LMArena Spanish—1434

Instruction Following GLM-4.7 leads

Gemma 3 4B: 65.2 (#225), GLM-4.7: 74.4 (#95)

BenchmarkGemma 3 4BGLM-4.7
LMArena Instruction Following12391411

Long Context GLM-4.7 leads

Gemma 3 4B: 38.7 (#194), GLM-4.7: 42.8 (#116)

BenchmarkGemma 3 4BGLM-4.7
LMArena Longer Query12731432
CL-bench—15.9%
CL-bench Life—10.9%

Writing & Preference GLM-4.7 leads

Gemma 3 4B: 42.0 (#239), GLM-4.7: 60.9 (#93)

BenchmarkGemma 3 4BGLM-4.7
LMArena Text12911435
LMArena Creative Writing12711401
EQ-Bench Creative Writing10681413
LMArena Multi-Turn12551446

Frequently asked questions

Is Gemma 3 4B better than GLM-4.7?

GLM-4.7 is the stronger model overall, scoring 42.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 20× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 4B or GLM-4.7?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Is Gemma 3 4B or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 131K.

How many benchmarks do Gemma 3 4B and GLM-4.7 share?

18 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper