Model comparison

Devstral Small 2505 vs GLM-4.7-Flash

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 34.3 on the Noometry Index.

Last verified October 11, 2026. 0 shared benchmarks.

Devstral Small 2505

Mistral AI

34.3

Rank #233 Reported

GLM-4.7-Flash Z.ai (Zhipu)

38.8

Rank #180 Confirmed

Summary

Both cost about the same: $0.10 input and $0.30 output per million tokens.
GLM-4.7-Flash accepts more context: 200K tokens versus 128K.

Side by side

Devstral Small 2505 and GLM-4.7-Flash specifications
	Devstral Small 2505	GLM-4.7-Flash
Provider	Mistral AI	Z.ai (Zhipu)
Noometry Index	34.3	38.8
Released	2025-05-07	2026-01-19
Weights	Open	Open
Context window	128K	200K
Max output	128K	131K
Input $ / M tokens	$0.10	$0.06
Output $ / M tokens	$0.30	$0.40
Results tracked	4	21

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

Category by category

Coding GLM-4.7-Flash leads

Devstral Small 2505: 38.9 (#166), GLM-4.7-Flash: 40.6 (#135)

Coding benchmarks
Benchmark	Devstral Small 2505	GLM-4.7-Flash
SWE-bench Verified (bash only)	56.4%	—
SciCode	28.8%	—
LMArena Coding	—	1383

Reasoning GLM-4.7-Flash leads

Devstral Small 2505: 19.7 (#252), GLM-4.7-Flash: 20.9 (#229)

Reasoning benchmarks
Benchmark	Devstral Small 2505	GLM-4.7-Flash
Kagi LLM Benchmark	37.7%	—
CritPt	0%	—
Chess Puzzles	—	0%
LMArena Hard Prompts	—	1356

Math Not comparable

Devstral Small 2505: —, GLM-4.7-Flash: 36.1 (#173)

Math benchmarks
Benchmark	Devstral Small 2505	GLM-4.7-Flash
OTIS Mock AIME 2024-2025	—	58.3%
LMArena Math	—	1355

Knowledge Not comparable

Devstral Small 2505: —, GLM-4.7-Flash: 35.5 (#184)

Knowledge benchmarks
Benchmark	Devstral Small 2505	GLM-4.7-Flash
GPQA Diamond	—	60.5%
Vectara Hallucination Rate	—	9.3%
LMArena Expert	—	1357

Multilingual Not comparable

Devstral Small 2505: —, GLM-4.7-Flash: 46.5 (#158)

Multilingual benchmarks
Benchmark	Devstral Small 2505	GLM-4.7-Flash
LMArena Non-English	—	1330
LMArena Chinese	—	1403
LMArena French	—	1332
LMArena German	—	1337
LMArena Korean	—	1283
LMArena Russian	—	1332
LMArena Spanish	—	1350

Instruction Following Not comparable

Devstral Small 2505: —, GLM-4.7-Flash: 70.1 (#167)

Instruction Following benchmarks
Benchmark	Devstral Small 2505	GLM-4.7-Flash
LMArena Instruction Following	—	1327

Long Context Not comparable

Devstral Small 2505: —, GLM-4.7-Flash: 40.9 (#148)

Long Context benchmarks
Benchmark	Devstral Small 2505	GLM-4.7-Flash
LMArena Longer Query	—	1345

Writing & Preference Not comparable

Devstral Small 2505: —, GLM-4.7-Flash: 47.4 (#210)

Writing & Preference benchmarks
Benchmark	Devstral Small 2505	GLM-4.7-Flash
LMArena Text	—	1351
LMArena Creative Writing	—	1297
EQ-Bench Creative Writing	—	1125
LMArena Multi-Turn	—	1342

Frequently asked questions

Is Devstral Small 2505 better than GLM-4.7-Flash?

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 34.3 on the Noometry Index.

Which is cheaper, Devstral Small 2505 or GLM-4.7-Flash?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; Devstral Small 2505 lists at $0.10 and $0.30.

Is Devstral Small 2505 or GLM-4.7-Flash better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 38.9 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 128K.

How many benchmarks do Devstral Small 2505 and GLM-4.7-Flash share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and GLM-4.7-Flash has 21.