Model comparison

Devstral Small 2505 vs GLM-4.5-Air

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 34.3 on the Noometry Index. Devstral Small 2505 costs 2.8× less per token, which makes it the better buy when GLM-4.5-Air'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-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

Summary

They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 1 category and GLM-4.5-Air in 1 category; 2 gaps are clear of the uncertainty.
The widest gap is in coding, where Devstral Small 2505 leads 38.9 to 33.3.
The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 43% for GLM-4.5-Air.
Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
GLM-4.5-Air accepts more context: 131K tokens versus 128K.

Side by side

Devstral Small 2505 and GLM-4.5-Air specifications
	Devstral Small 2505	GLM-4.5-Air
Provider	Mistral AI	Z.ai (Zhipu)
Noometry Index	34.3	38.9
Released	2025-05-07	2025-07-20
Weights	Open	Open
Context window	128K	131K
Max output	128K	98K
Input $ / M tokens	$0.10	$0.20
Output $ / M tokens	$0.30	$1.10
Results tracked	4	27

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

Category by category

Coding Devstral Small 2505 leads

Devstral Small 2505: 38.9 (#166), GLM-4.5-Air: 33.3 (#259)

Coding benchmarks
Benchmark	Devstral Small 2505	GLM-4.5-Air
SWE-bench Verified (bash only)	56.4%	—
SciCode	28.8%	—
GSO	—	2.9%
LMArena Coding	—	1397

Reasoning GLM-4.5-Air leads

Devstral Small 2505: 19.7 (#252), GLM-4.5-Air: 24.1 (#166)

Reasoning benchmarks
Benchmark	Devstral Small 2505	GLM-4.5-Air
Kagi LLM Benchmark	37.7%	43%
CritPt	0%	—
LMArena Hard Prompts	—	1379
ForecastBench	—	59.2

Math Not comparable

Devstral Small 2505: —, GLM-4.5-Air: 36.2 (#170)

Math benchmarks
Benchmark	Devstral Small 2505	GLM-4.5-Air
Omni-MATH	—	39.1%
LMArena Math	—	1396

Knowledge Not comparable

Devstral Small 2505: —, GLM-4.5-Air: 35.0 (#191)

Knowledge benchmarks
Benchmark	Devstral Small 2505	GLM-4.5-Air
Humanity's Last Exam	—	8.1%
MMLU-Pro	—	76.2%
Vectara Hallucination Rate	—	9.3%
GPQA (HELM)	—	59.4%
LMArena Expert	—	1370

Multilingual Not comparable

Devstral Small 2505: —, GLM-4.5-Air: 49.1 (#135)

Multilingual benchmarks
Benchmark	Devstral Small 2505	GLM-4.5-Air
LMArena Non-English	—	1366
LMArena Chinese	—	1426
LMArena French	—	1399
LMArena German	—	1377
LMArena Japanese	—	1348
LMArena Korean	—	1308
LMArena Russian	—	1373
LMArena Spanish	—	1386

Instruction Following Not comparable

Devstral Small 2505: —, GLM-4.5-Air: 69.6 (#171)

Instruction Following benchmarks
Benchmark	Devstral Small 2505	GLM-4.5-Air
IFEval	—	81.2%
LMArena Instruction Following	—	1354

Long Context Not comparable

Devstral Small 2505: —, GLM-4.5-Air: 41.6 (#135)

Long Context benchmarks
Benchmark	Devstral Small 2505	GLM-4.5-Air
LMArena Longer Query	—	1366

Writing & Preference Not comparable

Devstral Small 2505: —, GLM-4.5-Air: 55.9 (#139)

Writing & Preference benchmarks
Benchmark	Devstral Small 2505	GLM-4.5-Air
LMArena Text	—	1384
LMArena Creative Writing	—	1343
WildBench	—	78.9%
LMArena Multi-Turn	—	1371

Frequently asked questions

Is Devstral Small 2505 better than GLM-4.5-Air?

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

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.

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

Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 33.3 in the Noometry coding category.

Which has the bigger context window?

GLM-4.5-Air does, with 131K tokens against 128K.

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

1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GLM-4.5-Air has 27.