Model comparison

Devstral Small 2505 vs GLM-4.5V

GLM-4.5V is the stronger model overall, scoring 39.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 6.0× less per token, which makes it the better buy when GLM-4.5V's lead doesn't matter for your workload.

Last verified October 10, 2026. 1 shared benchmarks.

Devstral Small 2505

Mistral AI

34.3

Rank #233 Reported

GLM-4.5V Z.ai (Zhipu)

39.8

Rank #158 Confirmed

Summary

They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 0 categories and GLM-4.5V in 2 categories; one gap is clear of the uncertainty.
The widest gap is in reasoning, where GLM-4.5V leads 27.4 to 19.7.
The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 59.8% for GLM-4.5V.
Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.60 / $1.80 for GLM-4.5V.
Devstral Small 2505 accepts more context: 128K tokens versus 64K.

Side by side

Devstral Small 2505 and GLM-4.5V specifications
	Devstral Small 2505	GLM-4.5V
Provider	Mistral AI	Z.ai (Zhipu)
Noometry Index	34.3	39.8
Released	2025-05-07	2025-08-11
Weights	Open	Open
Context window	128K	64K
Max output	128K	16K
Input $ / M tokens	$0.10	$0.60
Output $ / M tokens	$0.30	$1.80
Results tracked	4	15

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

Category by category

Coding Too close to call

Devstral Small 2505: 38.9 (#166), GLM-4.5V: 39.5 (#155)

Coding benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
SWE-bench Verified (bash only)	56.4%	—
SciCode	28.8%	—
LMArena Coding	—	1347

Reasoning GLM-4.5V leads

Devstral Small 2505: 19.7 (#252), GLM-4.5V: 27.4 (#119)

Reasoning benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
Kagi LLM Benchmark	37.7%	59.8%
CritPt	0%	—
LMArena Hard Prompts	—	1334

Math Not comparable

Devstral Small 2505: —, GLM-4.5V: 37.4 (#159)

Math benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
LMArena Math	—	1354

Knowledge Not comparable

Devstral Small 2505: —, GLM-4.5V: 37.5 (#156)

Knowledge benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
LMArena Expert	—	1353

Multimodal Not comparable

Devstral Small 2505: —, GLM-4.5V: 34.3 (#92)

Multimodal benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
LMArena Vision	—	1154

Multilingual Not comparable

Devstral Small 2505: —, GLM-4.5V: 44.6 (#177)

Multilingual benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
LMArena Non-English	—	1303
LMArena Chinese	—	1337
LMArena Russian	—	1298
LMArena Spanish	—	1336

Instruction Following Not comparable

Devstral Small 2505: —, GLM-4.5V: 69.2 (#175)

Instruction Following benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
LMArena Instruction Following	—	1311

Long Context Not comparable

Devstral Small 2505: —, GLM-4.5V: 39.6 (#171)

Long Context benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
LMArena Longer Query	—	1304

Writing & Preference Not comparable

Devstral Small 2505: —, GLM-4.5V: 52.5 (#170)

Writing & Preference benchmarks
Benchmark	Devstral Small 2505	GLM-4.5V
LMArena Text	—	1333
LMArena Creative Writing	—	1295
LMArena Multi-Turn	—	1332

Frequently asked questions

Is Devstral Small 2505 better than GLM-4.5V?

Which is cheaper, Devstral Small 2505 or GLM-4.5V?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GLM-4.5V lists at $0.60 and $1.80.

Is Devstral Small 2505 or GLM-4.5V better for coding?

They score almost the same on coding (38.9 vs 39.5); test both on your own repository before choosing.

Which has the bigger context window?

Devstral Small 2505 does, with 128K tokens against 64K.

How many benchmarks do Devstral Small 2505 and GLM-4.5V share?

1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GLM-4.5V has 15.