Model comparison

GLM-4.6V vs Llama 3-8B

GLM-4.6V is the stronger model overall, scoring 40.9 to 25.3 on the Noometry Index. Llama 3-8B costs 3.2× less per token, which makes it the better buy when GLM-4.6V's lead doesn't matter for your workload.

Last verified October 10, 2026. 11 shared benchmarks.

GLM-4.6V Z.ai (Zhipu)

40.9

Rank #133 Confirmed

Llama 3-8B

Summary

They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 7 categories and Llama 3-8B in 0 categories; 7 gaps are clear of the uncertainty.
The widest gap is in knowledge, where GLM-4.6V leads 37.4 to 7.8.
Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $0.30 / $0.90 for GLM-4.6V.
GLM-4.6V accepts more context: 128K tokens versus 8K.

Side by side

GLM-4.6V and Llama 3-8B specifications
	GLM-4.6V	Llama 3-8B
Provider	Z.ai (Zhipu)	Meta
Noometry Index	40.9	25.3
Released	2025-12-08	2024-04-18
Weights	Open	Open
Context window	128K	8K
Max output	33K	8K
Input $ / M tokens	$0.30	$0.14
Output $ / M tokens	$0.90	$0.14
Results tracked	12	34

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

Category by category

Coding GLM-4.6V leads

GLM-4.6V: 40.2 (#128), Llama 3-8B: 30.5 (#285)

Coding benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
LMArena Coding	1390	1152
BigCodeBench Instruct	—	31.9%
BigCodeBench Complete	—	36.9%
HumanEval+	—	56.7%
MBPP+	—	54.8%

Reasoning GLM-4.6V leads

GLM-4.6V: 26.5 (#117), Llama 3-8B: 13.8 (#321)

Reasoning benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
LMArena Hard Prompts	1368	1133
Chess Puzzles	—	0%
DTBench	—	43.9%
Adversarial NLI	—	57.3%
Epoch Capabilities Index	—	116.33
ForecastBench	—	58.6
WinoGrande	—	75.7%

Math Not comparable

GLM-4.6V: —, Llama 3-8B: 8.3 (#317)

Math benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
OTIS Mock AIME 2024-2025	—	1.9%
LMArena Math	—	1151
MATH Level 5	—	6.1%

Knowledge GLM-4.6V leads

GLM-4.6V: 37.4 (#148), Llama 3-8B: 7.8 (#303)

Knowledge benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
LMArena Expert	1372	1113
GPQA Diamond	—	26.1%
ARC (AI2) Challenge	—	82.8%
MMLU	—	68.8%
OpenBookQA	—	82.6%
TriviaQA	—	67.7%

Multimodal Not comparable

GLM-4.6V: 34.2 (#83), Llama 3-8B: —

Multimodal benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
LMArena Vision	1164	—

Multilingual GLM-4.6V leads

GLM-4.6V: 48.8 (#135), Llama 3-8B: 31.0 (#256)

Multilingual benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
LMArena Non-English	1359	1098
LMArena Chinese	1426	1076
LMArena Russian	1341	1109
LMArena French	—	1158
LMArena German	—	1104
LMArena Japanese	—	967
LMArena Korean	—	1003
LMArena Spanish	—	1172

Instruction Following GLM-4.6V leads

GLM-4.6V: 71.6 (#145), Llama 3-8B: 58.7 (#255)

Instruction Following benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
LMArena Instruction Following	1351	1127

Long Context GLM-4.6V leads

GLM-4.6V: 41.3 (#138), Llama 3-8B: 34.2 (#246)

Long Context benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
LMArena Longer Query	1358	1128

Writing & Preference GLM-4.6V leads

GLM-4.6V: 56.8 (#132), Llama 3-8B: 37.7 (#251)

Writing & Preference benchmarks
Benchmark	GLM-4.6V	Llama 3-8B
LMArena Text	1377	1166
LMArena Creative Writing	1347	1150
LMArena Multi-Turn	1359	1152

Frequently asked questions

Is GLM-4.6V better than Llama 3-8B?

Which is cheaper, GLM-4.6V or Llama 3-8B?

Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; GLM-4.6V lists at $0.30 and $0.90.

Is GLM-4.6V or Llama 3-8B better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.2 versus 30.5 in the Noometry coding category.

Which has the bigger context window?

GLM-4.6V does, with 128K tokens against 8K.

How many benchmarks do GLM-4.6V and Llama 3-8B share?

11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Llama 3-8B has 34.