Noometry

Model comparison

Devstral Small 2505 vs Qwen3-30B-A3B

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 34.3 on the Noometry Index.

Last verified . 3 shared benchmarks.

Devstral Small 2505 Mistral AI

34.3

Rank #233 Reported

Qwen3-30B-A3B Alibaba (Qwen)

38.9

Rank #179 Confirmed

Summary

  • They share 3 benchmarks with published results for both. Devstral Small 2505 scores higher in 1 category and Qwen3-30B-A3B in 1 category; 2 gaps are clear of the uncertainty.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 54.9% for Qwen3-30B-A3B.
  • Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
  • Devstral Small 2505 accepts more context: 128K tokens versus 41K.

Side by side

Devstral Small 2505Qwen3-30B-A3B
ProviderMistral AIAlibaba (Qwen)
Noometry Index34.338.9
Released2025-05-072025-04-28
WeightsOpenOpen
Context window128K41K
Max output128K16K
Input $ / M tokens$0.10$0.12
Output $ / M tokens$0.30$0.50
Results tracked432

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

Category by category

Coding Devstral Small 2505 leads

Devstral Small 2505: 38.9 (#166), Qwen3-30B-A3B: 37.5 (#194)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
SciCode28.8%33.3%
SWE-bench Verified (bash only)56.4%—
WeirdML—29.8%
LMArena Coding—1416

Agentic & Tool Use Not comparable

Devstral Small 2505: —, Qwen3-30B-A3B: 29.8 (#82)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
Berkeley Function Calling Leaderboard—41.4%

Reasoning Qwen3-30B-A3B leads

Devstral Small 2505: 19.7 (#252), Qwen3-30B-A3B: 22.2 (#204)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
Kagi LLM Benchmark37.7%54.9%
CritPt0%0.3%
Chess Puzzles—8%
LMArena Hard Prompts—1398
DTBench—69.3%
LMCA—22.4%
Epoch Capabilities Index—139.63

Math Not comparable

Devstral Small 2505: —, Qwen3-30B-A3B: 37.4 (#157)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
MathArena Final-Answer Competitions—47.8%
OTIS Mock AIME 2024-2025—70.3%
LMArena Math—1394

Knowledge Not comparable

Devstral Small 2505: —, Qwen3-30B-A3B: 41.8 (#105)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
GPQA Diamond—70.1%
Confabulations—12.3%
LMArena Expert—1396

Multilingual Not comparable

Devstral Small 2505: —, Qwen3-30B-A3B: 49.5 (#132)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
LMArena Non-English—1372
LMArena Chinese—1433
LMArena French—1418
LMArena German—1380
LMArena Japanese—1337
LMArena Korean—1331
LMArena Russian—1370
LMArena Spanish—1404

Instruction Following Not comparable

Devstral Small 2505: —, Qwen3-30B-A3B: 72.0 (#142)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
LMArena Instruction Following—1363

Long Context Not comparable

Devstral Small 2505: —, Qwen3-30B-A3B: 31.0 (#283)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
Fiction.LiveBench—40.6%
LMArena Longer Query—1379

Writing & Preference Not comparable

Devstral Small 2505: —, Qwen3-30B-A3B: 55.6 (#143)

BenchmarkDevstral Small 2505Qwen3-30B-A3B
LMArena Text—1384
LMArena Creative Writing—1317
Short-Story Creative Writing—75.3%
LMArena Multi-Turn—1378

Frequently asked questions

Is Devstral Small 2505 better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 34.3 on the Noometry Index.

Which is cheaper, Devstral Small 2505 or Qwen3-30B-A3B?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.

Is Devstral Small 2505 or Qwen3-30B-A3B better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 37.5 in the Noometry coding category.

Which has the bigger context window?

Devstral Small 2505 does, with 128K tokens against 41K.

How many benchmarks do Devstral Small 2505 and Qwen3-30B-A3B share?

3 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper