Model comparison

Codestral vs Mistral Large 3

Mistral Large 3 is the stronger model overall, scoring 38.6 to 30.1 on the Noometry Index.

Last verified October 10, 2026. 1 shared benchmarks.

Codestral

Mistral AI

30.1

Rank #287 Reported

Mistral Large 3

Mistral AI

38.6

Rank #172 Confirmed

Summary

They share 1 benchmark with published results for both. Codestral scores higher in 1 category and Mistral Large 3 in 1 category; 2 gaps are clear of the uncertainty.
The widest gap is in coding, where Mistral Large 3 leads 34.1 to 26.9.
The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 50.9% for Mistral Large 3.
Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $0.90 for Codestral.
Mistral Large 3 accepts more context: 262K tokens versus 256K.

Side by side

Codestral and Mistral Large 3 specifications
	Codestral	Mistral Large 3
Provider	Mistral AI	Mistral AI
Noometry Index	30.1	38.6
Released	2024-05-29	2025-12-02
Weights	Open	Open
Context window	256K	262K
Max output	4K	8K
Input $ / M tokens	$0.30	$0.25
Output $ / M tokens	$0.90	$0.75
Results tracked	7	24

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

Category by category

Coding Mistral Large 3 leads

Codestral: 26.9 (#316), Mistral Large 3: 34.1 (#230)

Coding benchmarks
Benchmark	Codestral	Mistral Large 3
Aider Polyglot	11.1%	—
LMArena WebDev	—	1230
BigCodeBench Instruct	41.8%	—
LMArena Coding	—	1447
BigCodeBench Complete	52.5%	—
ALE-Bench	137.78	—
HumanEval+	73.8%	—
MBPP+	61.9%	—

Reasoning Codestral leads

Codestral: 19.1 (#244), Mistral Large 3: 14.6 (#314)

Reasoning benchmarks
Benchmark	Codestral	Mistral Large 3
Kagi LLM Benchmark	32.5%	50.9%
NYT Connections (extended)	—	7.5%
Thematic Generalization	—	23%
LMArena Hard Prompts	—	1429

Math Not comparable

Codestral: —, Mistral Large 3: 36.0 (#131)

Math benchmarks
Benchmark	Codestral	Mistral Large 3
LMArena Math	—	1415

Knowledge Not comparable

Codestral: —, Mistral Large 3: 35.5 (#173)

Knowledge benchmarks
Benchmark	Codestral	Mistral Large 3
Vectara Hallucination Rate	—	14.5%
LMArena Expert	—	1421

Multimodal Not comparable

Codestral: —, Mistral Large 3: 37.6 (#65)

Multimodal benchmarks
Benchmark	Codestral	Mistral Large 3
LMArena Vision	—	1222

Multilingual Not comparable

Codestral: —, Mistral Large 3: 52.6 (#79)

Multilingual benchmarks
Benchmark	Codestral	Mistral Large 3
LMArena Non-English	—	1412
LMArena Chinese	—	1448
LMArena French	—	1456
LMArena German	—	1438
LMArena Japanese	—	1399
LMArena Korean	—	1384
LMArena Russian	—	1412
LMArena Spanish	—	1437

Instruction Following Not comparable

Codestral: —, Mistral Large 3: 74.1 (#104)

Instruction Following benchmarks
Benchmark	Codestral	Mistral Large 3
LMArena Instruction Following	—	1402

Long Context Not comparable

Codestral: —, Mistral Large 3: 43.1 (#102)

Long Context benchmarks
Benchmark	Codestral	Mistral Large 3
LMArena Longer Query	—	1413

Writing & Preference Not comparable

Codestral: —, Mistral Large 3: 60.2 (#100)

Writing & Preference benchmarks
Benchmark	Codestral	Mistral Large 3
LMArena Text	—	1427
LMArena Creative Writing	—	1385
EQ-Bench Creative Writing	—	1412
LMArena Multi-Turn	—	1429

Frequently asked questions

Is Codestral better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 30.1 on the Noometry Index.

Which is cheaper, Codestral or Mistral Large 3?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Codestral lists at $0.30 and $0.90.

Is Codestral or Mistral Large 3 better for coding?

Mistral Large 3 scores higher on coding benchmarks: 34.1 versus 26.9 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 256K.

How many benchmarks do Codestral and Mistral Large 3 share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Mistral Large 3 has 24.