Model comparison

Devstral Small 2505 vs Qwen3-4B

Devstral Small 2505 is the stronger model overall, scoring 33.9 to 31.5 on the Noometry Index.

Last verified . 0 shared benchmarks.

Devstral Small 2505 Mistral AI

33.9

Rank #228 Reported

Qwen3-4B Alibaba (Qwen)

31.5

Rank #261 Confirmed

Side by side

Devstral Small 2505 and Qwen3-4B specifications
Devstral Small 2505Qwen3-4B
ProviderMistral AIAlibaba (Qwen)
Noometry Index33.931.5
Released2025-05-072025-04-29
WeightsOpenOpen
Context window128K—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.30—
Results tracked46

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

Category by category

Coding Not comparable

Devstral Small 2505: 38.6 (#160), Qwen3-4B: —

Coding benchmarks
BenchmarkDevstral Small 2505Qwen3-4B
SWE-bench Verified (bash only)56.4%—
SciCode28.8%—

Agentic & Tool Use Not comparable

Devstral Small 2505: —, Qwen3-4B: 27.3 (#94)

Agentic & Tool Use benchmarks
BenchmarkDevstral Small 2505Qwen3-4B
Berkeley Function Calling Leaderboard—35.7%

Reasoning Too close to call

Devstral Small 2505: 19.1 (#243), Qwen3-4B: 18.5 (#264)

Reasoning benchmarks
BenchmarkDevstral Small 2505Qwen3-4B
Kagi LLM Benchmark37.7%—
CritPt0%—
Chess Puzzles—4%

Math Not comparable

Devstral Small 2505: —, Qwen3-4B: 28.5 (#228)

Math benchmarks
BenchmarkDevstral Small 2505Qwen3-4B
MathArena Final-Answer Competitions—38.5%
OTIS Mock AIME 2024-2025—52.2%

Knowledge Not comparable

Devstral Small 2505: —, Qwen3-4B: 33.0 (#198)

Knowledge benchmarks
BenchmarkDevstral Small 2505Qwen3-4B
GPQA Diamond—52.3%
Vectara Hallucination Rate—5.7%

Frequently asked questions

Is Devstral Small 2505 better than Qwen3-4B?

Devstral Small 2505 is the stronger model overall, scoring 33.9 to 31.5 on the Noometry Index.

How many benchmarks do Devstral Small 2505 and Qwen3-4B share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper