Model comparison

Codestral vs Grok 4.7

Grok 4.7 is the stronger model overall, scoring 53.1 to 30.6 on the Noometry Index. Codestral costs 6.7× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

Codestral

Mistral AI

30.6

Rank #290 Reported

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Summary

The widest gap is in coding, where Grok 4.7 leads 58.0 to 27.3.
Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $2 / $6 for Grok 4.7.
Grok 4.7 accepts more context: 500K tokens versus 256K.

Side by side

Codestral and Grok 4.7 specifications
	Codestral	Grok 4.7
Provider	Mistral AI	xAI
Noometry Index	30.6	53.1
Released	2024-05-29	2026-09-21
Weights	Proprietary	Proprietary
Context window	256K	500K
Max output	8K	500K
Input $ / M tokens	$0.30	$2
Output $ / M tokens	$0.90	$6
Results tracked	7	39

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

Category by category

Coding Grok 4.7 leads

Codestral: 27.3 (#321), Grok 4.7: 58.0 (#18)

Coding benchmarks
Benchmark	Codestral	Grok 4.7
FrontierCode	—	47.6%
Aider Polyglot	11.1%	—
CursorBench	—	46.3%
LMArena WebDev	—	1639
FrontierSWE	—	29.5%
SciCode	—	57.8%
BigCodeBench Instruct	41.8%	—
LMArena Coding	—	1427
BigCodeBench Complete	52.5%	—
ALE-Bench	137.78	—
HumanEval+	73.8%	—
MBPP+	61.9%	—

Agentic & Tool Use Not comparable

Codestral: —, Grok 4.7: 36.7 (#37)

Agentic & Tool Use benchmarks
Benchmark	Codestral	Grok 4.7
APEX-Agents	—	54.6%
GDP.pdf	—	22.8%
Vending-Bench 2	—	10,537

Reasoning Grok 4.7 leads

Codestral: 19.8 (#251), Grok 4.7: 49.1 (#40)

Reasoning benchmarks
Benchmark	Codestral	Grok 4.7
Kagi LLM Benchmark	32.5%	—
NYT Connections (extended)	—	76.8%
CritPt	—	18%
Chess Puzzles	—	38%
LMArena Hard Prompts	—	1413
Mystery Game Puzzles	—	29%
DTBench	—	96%
LMCA	—	49.4%
Epoch Capabilities Index	—	153.53

Math Not comparable

Codestral: —, Grok 4.7: 57.8 (#39)

Math benchmarks
Benchmark	Codestral	Grok 4.7
FrontierMath (Tiers 1-3)	—	53%
FrontierMath Tier 4	—	17.1%
OTIS Mock AIME 2024-2025	—	98.1%
ProofBench	—	34%
LMArena Math	—	1407

Knowledge Not comparable

Codestral: —, Grok 4.7: 62.8 (#22)

Knowledge benchmarks
Benchmark	Codestral	Grok 4.7
GPQA Diamond	—	92.7%
SimpleQA Verified	—	56%
LMArena Expert	—	1422

Multimodal Not comparable

Codestral: —, Grok 4.7: 35.5 (#87)

Multimodal benchmarks
Benchmark	Codestral	Grok 4.7
LMArena Vision	—	1228
Blueprint-Bench 2	—	32.5%
Furniture Assembly	—	20.8%

Multilingual Not comparable

Codestral: —, Grok 4.7: 50.8 (#116)

Multilingual benchmarks
Benchmark	Codestral	Grok 4.7
LMArena Non-English	—	1389
LMArena Chinese	—	1455
LMArena French	—	1455
LMArena Russian	—	1397
LMArena Spanish	—	1400

Instruction Following Not comparable

Codestral: —, Grok 4.7: 74.1 (#105)

Instruction Following benchmarks
Benchmark	Codestral	Grok 4.7
LMArena Instruction Following	—	1404

Long Context Not comparable

Codestral: —, Grok 4.7: 43.1 (#104)

Long Context benchmarks
Benchmark	Codestral	Grok 4.7
LMArena Longer Query	—	1413

Writing & Preference Not comparable

Codestral: —, Grok 4.7: 70.0 (#24)

Writing & Preference benchmarks
Benchmark	Codestral	Grok 4.7
LMArena Text	—	1399
LMArena Creative Writing	—	1391
EQ-Bench Creative Writing	—	2007
LMArena Multi-Turn	—	1393

Frequently asked questions

Is Codestral better than Grok 4.7?

Which is cheaper, Codestral or Grok 4.7?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Grok 4.7 lists at $2 and $6.

Is Codestral or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 27.3 in the Noometry coding category.

Which has the bigger context window?

Grok 4.7 does, with 500K tokens against 256K.

How many benchmarks do Codestral and Grok 4.7 share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Grok 4.7 has 39.