Model comparison

Gemma 3 4B vs GLM-4.5

GLM-4.5 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-4.5's lead doesn't matter for your workload.

Last verified October 10, 2026. 14 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

GLM-4.5 Z.ai (Zhipu)

42.0

Rank #122 Confirmed

Summary

They share 14 benchmarks with published results for both. Gemma 3 4B scores higher in 1 category and GLM-4.5 in 7 categories; 7 gaps are clear of the uncertainty.
The widest gap is in knowledge, where GLM-4.5 leads 35.9 to 11.8.
The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 57.9% for GLM-4.5.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.

Side by side

Gemma 3 4B and GLM-4.5 specifications
	Gemma 3 4B	GLM-4.5
Provider	Google	Z.ai (Zhipu)
Noometry Index	28.1	42.0
Released	2025-03-12	2025-07-27
Weights	Open	Open
Context window	131K	131K
Max output	4K	98K
Input $ / M tokens	$0.04	$0.60
Output $ / M tokens	$0.08	$2.20
Results tracked	22	27

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

Category by category

Coding GLM-4.5 leads

Gemma 3 4B: 35.9 (#215), GLM-4.5: 41.4 (#125)

Coding benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
LMArena Coding	1230	1434
SWE-bench Verified (bash only)	—	54.2%
WeirdML	—	40.6%
ALE-Bench	—	344.82
AlgoTune	—	1.52

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), GLM-4.5: —

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
Berkeley Function Calling Leaderboard	19.6%	—

Reasoning GLM-4.5 leads

Gemma 3 4B: 13.2 (#335), GLM-4.5: 28.6 (#100)

Reasoning benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
Kagi LLM Benchmark	25.2%	57.9%
LMArena Hard Prompts	1253	1429
Chess Puzzles	0%	—
DTBench	50.9%	—
LMCA	2.8%	—
Epoch Capabilities Index	116.02	—

Math GLM-4.5 leads

Gemma 3 4B: 16.8 (#292), GLM-4.5: 39.0 (#116)

Math benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
LMArena Math	1239	1427
OTIS Mock AIME 2024-2025	7.5%	—

Knowledge GLM-4.5 leads

Gemma 3 4B: 11.8 (#299), GLM-4.5: 35.9 (#179)

Knowledge benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
LMArena Expert	1223	1433
GPQA Diamond	23.2%	—
Humanity's Last Exam	—	8.3%
Confabulations	—	11.3%
Vectara Hallucination Rate	6.4%	—

Multilingual GLM-4.5 leads

Gemma 3 4B: 42.5 (#194), GLM-4.5: 52.8 (#77)

Multilingual benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
LMArena Non-English	1273	1417
LMArena German	1281	1407
LMArena Russian	1294	1414
LMArena Chinese	—	1465
LMArena French	—	1418
LMArena Japanese	—	1415
LMArena Korean	—	1380
LMArena Spanish	—	1454

Instruction Following GLM-4.5 leads

Gemma 3 4B: 65.2 (#225), GLM-4.5: 74.1 (#104)

Instruction Following benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
LMArena Instruction Following	1239	1404

Long Context Too close to call

Gemma 3 4B: 38.7 (#194), GLM-4.5: 38.2 (#201)

Long Context benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
LMArena Longer Query	1273	1412
Fiction.LiveBench	—	58.3%

Writing & Preference GLM-4.5 leads

Gemma 3 4B: 42.0 (#239), GLM-4.5: 57.5 (#127)

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	GLM-4.5
LMArena Text	1291	1430
LMArena Creative Writing	1271	1395
EQ-Bench Creative Writing	1068	1343
LMArena Multi-Turn	1255	1415
Short-Story Creative Writing	—	73.4%

Frequently asked questions

Is Gemma 3 4B better than GLM-4.5?

Which is cheaper, Gemma 3 4B or GLM-4.5?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

Is Gemma 3 4B or GLM-4.5 better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.4 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do Gemma 3 4B and GLM-4.5 share?

14 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GLM-4.5 has 27.