Model comparison

Codestral vs GLM-4.7

GLM-4.7 is the stronger model overall, scoring 42.0 to 30.6 on the Noometry Index. Codestral costs 2.2× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Last verified October 11, 2026. 1 shared benchmarks.

Codestral

Mistral AI

30.6

Rank #290 Reported

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Summary

They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and GLM-4.7 in 2 categories; 2 gaps are clear of the uncertainty.
The widest gap is in coding, where GLM-4.7 leads 44.0 to 27.3.
Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
Codestral accepts more context: 256K tokens versus 205K.
GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

Codestral and GLM-4.7 specifications
	Codestral	GLM-4.7
Provider	Mistral AI	Z.ai (Zhipu)
Noometry Index	30.6	42.0
Released	2024-05-29	2025-12-22
Weights	Proprietary	Open
Context window	256K	205K
Max output	8K	131K
Input $ / M tokens	$0.30	$0.60
Output $ / M tokens	$0.90	$2.20
Results tracked	7	36

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

Category by category

Coding GLM-4.7 leads

Codestral: 27.3 (#321), GLM-4.7: 44.0 (#79)

Coding benchmarks
Benchmark	Codestral	GLM-4.7
ALE-Bench	137.78	399.48
Aider Polyglot	11.1%	—
LMArena WebDev	—	1435
SciCode	—	45.1%
BigCodeBench Instruct	41.8%	—
LMArena Coding	—	1454
BigCodeBench Complete	52.5%	—
HumanEval+	73.8%	—
MBPP+	61.9%	—

Agentic & Tool Use Not comparable

Codestral: —, GLM-4.7: 26.5 (#103)

Agentic & Tool Use benchmarks
Benchmark	Codestral	GLM-4.7
Terminal-Bench	—	33.4%
Vending-Bench 2	—	2,377

Reasoning GLM-4.7 leads

Codestral: 19.8 (#251), GLM-4.7: 24.3 (#164)

Reasoning benchmarks
Benchmark	Codestral	GLM-4.7
SimpleBench	—	47.7%
Kagi LLM Benchmark	32.5%	—
CritPt	—	1.7%
Chess Puzzles	—	6%
LMArena Hard Prompts	—	1443
Epoch Capabilities Index	—	143.51

Math Not comparable

Codestral: —, GLM-4.7: 38.6 (#135)

Math benchmarks
Benchmark	Codestral	GLM-4.7
OTIS Mock AIME 2024-2025	—	83.3%
ProofBench	—	6%
LMArena Math	—	1423
FrontierMath (Feb 2025 set)	—	2.4%
FrontierMath Tier 4 (v1)	—	0%

Knowledge Not comparable

Codestral: —, GLM-4.7: 47.0 (#80)

Knowledge benchmarks
Benchmark	Codestral	GLM-4.7
GPQA Diamond	—	83.3%
SimpleQA Verified	—	32.2%
Vectara Hallucination Rate	—	11.7%
LMArena Expert	—	1424

Multilingual Not comparable

Codestral: —, GLM-4.7: 52.8 (#79)

Multilingual benchmarks
Benchmark	Codestral	GLM-4.7
LMArena Non-English	—	1417
LMArena Chinese	—	1495
LMArena French	—	1432
LMArena German	—	1424
LMArena Japanese	—	1439
LMArena Korean	—	1399
LMArena Russian	—	1423
LMArena Spanish	—	1434

Instruction Following Not comparable

Codestral: —, GLM-4.7: 74.4 (#95)

Instruction Following benchmarks
Benchmark	Codestral	GLM-4.7
LMArena Instruction Following	—	1411

Long Context Not comparable

Codestral: —, GLM-4.7: 42.8 (#116)

Long Context benchmarks
Benchmark	Codestral	GLM-4.7
CL-bench	—	15.9%
CL-bench Life	—	10.9%
LMArena Longer Query	—	1432

Writing & Preference Not comparable

Codestral: —, GLM-4.7: 60.9 (#93)

Writing & Preference benchmarks
Benchmark	Codestral	GLM-4.7
LMArena Text	—	1435
LMArena Creative Writing	—	1401
EQ-Bench Creative Writing	—	1413
LMArena Multi-Turn	—	1446

Frequently asked questions

Is Codestral better than GLM-4.7?

Which is cheaper, Codestral or GLM-4.7?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Is Codestral or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 27.3 in the Noometry coding category.

Which has the bigger context window?

Codestral does, with 256K tokens against 205K.

How many benchmarks do Codestral and GLM-4.7 share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and GLM-4.7 has 36.