Noometry

Model comparison

Gemma 3 4B vs GLM-4.6

GLM-4.6 is the stronger model overall, scoring 40.9 to 27.9 on the Noometry Index. Gemma 3 4B costs 20× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

Last verified . 16 shared benchmarks.

Gemma 3 4B Google

27.9

Rank #320 Confirmed

GLM-4.6 Z.ai (Zhipu)

40.9

Rank #132 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and GLM-4.6 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.6 leads 39.6 to 11.8.
  • The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 19.6% for Gemma 3 4B and 72.4% for GLM-4.6.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
  • GLM-4.6 accepts more context: 205K tokens versus 131K.

Side by side

Gemma 3 4BGLM-4.6
ProviderGoogleZ.ai (Zhipu)
Noometry Index27.940.9
Released2025-03-122025-09-30
WeightsOpenOpen
Context window131K205K
Max output4K131K
Input $ / M tokens$0.04$0.60
Output $ / M tokens$0.08$2.20
Results tracked2229

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

Category by category

Coding GLM-4.6 leads

Gemma 3 4B: 35.3 (#214), GLM-4.6: 39.9 (#137)

BenchmarkGemma 3 4BGLM-4.6
LMArena Coding12301449
SWE-bench Verified (bash only)—55.4%
LMArena WebDev—1339
SciCode—38.4%
ALE-Bench—340.82

Agentic & Tool Use GLM-4.6 leads

Gemma 3 4B: 20.7 (#134), GLM-4.6: 32.1 (#60)

BenchmarkGemma 3 4BGLM-4.6
Berkeley Function Calling Leaderboard19.6%72.4%
Terminal-Bench—24.5%

Reasoning GLM-4.6 leads

Gemma 3 4B: 12.7 (#330), GLM-4.6: 23.1 (#168)

BenchmarkGemma 3 4BGLM-4.6
Kagi LLM Benchmark25.2%47.4%
LMArena Hard Prompts12531440
CritPt—1.1%
Chess Puzzles0%—
DTBench50.9%—
LMCA2.8%—
Epoch Capabilities Index116.02—

Math GLM-4.6 leads

Gemma 3 4B: 15.8 (#286), GLM-4.6: 36.4 (#115)

BenchmarkGemma 3 4BGLM-4.6
LMArena Math12391431
OTIS Mock AIME 2024-20257.5%—
FrontierMath (Feb 2025 set)—3.8%
FrontierMath Tier 4 (v1)—2.1%

Knowledge GLM-4.6 leads

Gemma 3 4B: 11.8 (#294), GLM-4.6: 39.6 (#118)

BenchmarkGemma 3 4BGLM-4.6
Vectara Hallucination Rate6.4%9.5%
LMArena Expert12231432
GPQA Diamond23.2%—

Multilingual GLM-4.6 leads

Gemma 3 4B: 42.7 (#189), GLM-4.6: 53.6 (#62)

BenchmarkGemma 3 4BGLM-4.6
LMArena Non-English12731426
LMArena German12811447
LMArena Russian12941418
LMArena Chinese—1500
LMArena French—1459
LMArena Japanese—1394
LMArena Korean—1401
LMArena Spanish—1436

Instruction Following GLM-4.6 leads

Gemma 3 4B: 65.4 (#219), GLM-4.6: 74.5 (#93)

BenchmarkGemma 3 4BGLM-4.6
LMArena Instruction Following12391410

Long Context GLM-4.6 leads

Gemma 3 4B: 38.6 (#189), GLM-4.6: 43.4 (#91)

BenchmarkGemma 3 4BGLM-4.6
LMArena Longer Query12741423

Writing & Preference GLM-4.6 leads

Gemma 3 4B: 42.2 (#234), GLM-4.6: 61.3 (#86)

BenchmarkGemma 3 4BGLM-4.6
LMArena Text12911440
LMArena Creative Writing12701411
EQ-Bench Creative Writing10681411
LMArena Multi-Turn12551427

Frequently asked questions

Is Gemma 3 4B better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 40.9 to 27.9 on the Noometry Index. Gemma 3 4B costs 20× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 4B or GLM-4.6?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

Is Gemma 3 4B or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 35.3 in the Noometry coding category.

Which has the bigger context window?

GLM-4.6 does, with 205K tokens against 131K.

How many benchmarks do Gemma 3 4B and GLM-4.6 share?

16 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GLM-4.6 has 29.

Related comparisons

Go deeper