Model comparison

Codestral vs Qwen3-4B

Qwen3-4B is the stronger model overall, scoring 31.9 to 30.6 on the Noometry Index.

Last verified . 0 shared benchmarks.

Codestral Mistral AI

30.6

Rank #290 Reported

Qwen3-4B Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

  • Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

Codestral and Qwen3-4B specifications
CodestralQwen3-4B
ProviderMistral AIAlibaba (Qwen)
Noometry Index30.631.9
Released2024-05-292025-04-29
WeightsProprietaryOpen
Context window256K—
Max output8K—
Input $ / M tokens$0.30—
Output $ / M tokens$0.90—
Results tracked76

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

Category by category

Coding Not comparable

Codestral: 27.3 (#321), Qwen3-4B: —

Coding benchmarks
BenchmarkCodestralQwen3-4B
Aider Polyglot11.1%—
BigCodeBench Instruct41.8%—
BigCodeBench Complete52.5%—
ALE-Bench137.78—
HumanEval+73.8%—
MBPP+61.9%—

Agentic & Tool Use Not comparable

Codestral: —, Qwen3-4B: 27.6 (#100)

Agentic & Tool Use benchmarks
BenchmarkCodestralQwen3-4B
Berkeley Function Calling Leaderboard—35.7%

Reasoning Too close to call

Codestral: 19.8 (#251), Qwen3-4B: 19.2 (#268)

Reasoning benchmarks
BenchmarkCodestralQwen3-4B
Kagi LLM Benchmark32.5%—
Chess Puzzles—4%

Math Not comparable

Codestral: —, Qwen3-4B: 29.7 (#240)

Math benchmarks
BenchmarkCodestralQwen3-4B
MathArena Final-Answer Competitions—38.5%
OTIS Mock AIME 2024-2025—52.2%

Knowledge Not comparable

Codestral: —, Qwen3-4B: 33.0 (#208)

Knowledge benchmarks
BenchmarkCodestralQwen3-4B
GPQA Diamond—52.3%
Vectara Hallucination Rate—5.7%

Frequently asked questions

Is Codestral better than Qwen3-4B?

Qwen3-4B is the stronger model overall, scoring 31.9 to 30.6 on the Noometry Index.

How many benchmarks do Codestral and Qwen3-4B share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper