Model comparison

Devstral Small 2505 vs Qwen3-VL 235B-A22B

Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 34.3 on the Noometry Index. Devstral Small 2505 costs 8.2× less per token, which makes it the better buy when Qwen3-VL 235B-A22B's lead doesn't matter for your workload.

Last verified October 11, 2026. 0 shared benchmarks.

Devstral Small 2505

Mistral AI

34.3

Rank #233 Reported

Qwen3-VL 235B-A22B

Alibaba (Qwen)

43.2

Rank #95 Confirmed

Summary

The widest gap is in reasoning, where Qwen3-VL 235B-A22B leads 29.3 to 19.7.
Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.70 / $2.80 for Qwen3-VL 235B-A22B.
Qwen3-VL 235B-A22B accepts more context: 131K tokens versus 128K.

Side by side

Devstral Small 2505 and Qwen3-VL 235B-A22B specifications
	Devstral Small 2505	Qwen3-VL 235B-A22B
Provider	Mistral AI	Alibaba (Qwen)
Noometry Index	34.3	43.2
Released	2025-05-07	2025-04
Weights	Open	Open
Context window	128K	131K
Max output	128K	33K
Input $ / M tokens	$0.10	$0.70
Output $ / M tokens	$0.30	$2.80
Results tracked	4	18

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

Category by category

Coding Qwen3-VL 235B-A22B leads

Devstral Small 2505: 38.9 (#166), Qwen3-VL 235B-A22B: 42.4 (#100)

Coding benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
SWE-bench Verified (bash only)	56.4%	—
SciCode	28.8%	—
LMArena Coding	—	1439

Reasoning Qwen3-VL 235B-A22B leads

Devstral Small 2505: 19.7 (#252), Qwen3-VL 235B-A22B: 29.3 (#92)

Reasoning benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
Kagi LLM Benchmark	37.7%	—
CritPt	0%	—
LMArena Hard Prompts	—	1428

Math Not comparable

Devstral Small 2505: —, Qwen3-VL 235B-A22B: 39.0 (#118)

Math benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
LMArena Math	—	1426

Knowledge Not comparable

Devstral Small 2505: —, Qwen3-VL 235B-A22B: 40.3 (#121)

Knowledge benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
LMArena Expert	—	1442

Multimodal Not comparable

Devstral Small 2505: —, Qwen3-VL 235B-A22B: 39.8 (#55)

Multimodal benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
LMArena Vision	—	1247

Multilingual Not comparable

Devstral Small 2505: —, Qwen3-VL 235B-A22B: 51.9 (#97)

Multilingual benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
LMArena Non-English	—	1405
LMArena Chinese	—	1463
LMArena French	—	1452
LMArena German	—	1424
LMArena Japanese	—	1385
LMArena Korean	—	1394
LMArena Russian	—	1408
LMArena Spanish	—	1428

Instruction Following Not comparable

Devstral Small 2505: —, Qwen3-VL 235B-A22B: 74.2 (#101)

Instruction Following benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
LMArena Instruction Following	—	1406

Long Context Not comparable

Devstral Small 2505: —, Qwen3-VL 235B-A22B: 43.4 (#98)

Long Context benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
LMArena Longer Query	—	1420

Writing & Preference Not comparable

Devstral Small 2505: —, Qwen3-VL 235B-A22B: 60.2 (#99)

Writing & Preference benchmarks
Benchmark	Devstral Small 2505	Qwen3-VL 235B-A22B
LMArena Text	—	1420
LMArena Creative Writing	—	1366
LMArena Multi-Turn	—	1428

Frequently asked questions

Is Devstral Small 2505 better than Qwen3-VL 235B-A22B?

Which is cheaper, Devstral Small 2505 or Qwen3-VL 235B-A22B?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3-VL 235B-A22B lists at $0.70 and $2.80.

Is Devstral Small 2505 or Qwen3-VL 235B-A22B better for coding?

Qwen3-VL 235B-A22B scores higher on coding benchmarks: 42.4 versus 38.9 in the Noometry coding category.

Which has the bigger context window?

Qwen3-VL 235B-A22B does, with 131K tokens against 128K.

How many benchmarks do Devstral Small 2505 and Qwen3-VL 235B-A22B share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen3-VL 235B-A22B has 18.