Model comparison

Mistral Small 3.2 vs Qwen3.8 27B

Qwen3.8 27B is the stronger model overall, scoring 45.3 to 30.8 on the Noometry Index. Mistral Small 3.2 costs 8.4× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.

Last verified October 10, 2026. 2 shared benchmarks.

Mistral Small 3.2

Mistral AI

30.8

Rank #271 Confirmed

Qwen3.8 27B

Alibaba (Qwen)

45.3

Rank #64 Confirmed

Summary

They share 2 benchmarks with published results for both. Mistral Small 3.2 scores higher in 0 categories and Qwen3.8 27B in 4 categories; 4 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Qwen3.8 27B leads 65.9 to 45.1.
Mistral Small 3.2 is cheaper at $0.0938 / $0.25 per million input/output tokens, against $0.99 / $1.49 for Qwen3.8 27B.
Qwen3.8 27B accepts more context: 262K tokens versus 256K.

Side by side

Mistral Small 3.2 and Qwen3.8 27B specifications
	Mistral Small 3.2	Qwen3.8 27B
Provider	Mistral AI	Alibaba (Qwen)
Noometry Index	30.8	45.3
Released	2025-06-20	2026-08-14
Weights	Open	Open
Context window	256K	262K
Max output	16K	33K
Input $ / M tokens	$0.0938	$0.99
Output $ / M tokens	$0.25	$1.49
Results tracked	6	28

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

Category by category

Coding Not comparable

Mistral Small 3.2: —, Qwen3.8 27B: 50.3 (#42)

Coding benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
LMArena WebDev	—	1592
SciCode	—	46.6%
LMArena Coding	—	1487

Reasoning Qwen3.8 27B leads

Mistral Small 3.2: 17.5 (#282), Qwen3.8 27B: 31.5 (#71)

Reasoning benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
Epoch Capabilities Index	131.73	149.38
Kagi LLM Benchmark	40.4%	—
NYT Connections (extended)	—	54.5%
CritPt	—	5.4%
Chess Puzzles	1%	—
LMArena Hard Prompts	—	1459
DTBench	—	88%
LMCA	—	41.4%
Surface Evolver Bench	—	45%

Math Qwen3.8 27B leads

Mistral Small 3.2: 24.9 (#251), Qwen3.8 27B: 35.7 (#139)

Math benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
OTIS Mock AIME 2024-2025	30.3%	—
ProofBench	—	16%
LMArena Math	—	1453

Knowledge Qwen3.8 27B leads

Mistral Small 3.2: 26.8 (#249), Qwen3.8 27B: 40.9 (#105)

Knowledge benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
GPQA Diamond	49.1%	—
LMArena Expert	—	1482

Multimodal Not comparable

Mistral Small 3.2: —, Qwen3.8 27B: 40.5 (#36)

Multimodal benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
LMArena Vision	—	1270

Multilingual Not comparable

Mistral Small 3.2: —, Qwen3.8 27B: 54.0 (#54)

Multilingual benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
LMArena Non-English	—	1431
LMArena Chinese	—	1504
LMArena French	—	1468
LMArena German	—	1435
LMArena Japanese	—	1392
LMArena Korean	—	1389
LMArena Russian	—	1421
LMArena Spanish	—	1444

Instruction Following Not comparable

Mistral Small 3.2: —, Qwen3.8 27B: 75.8 (#54)

Instruction Following benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
LMArena Instruction Following	—	1436

Long Context Not comparable

Mistral Small 3.2: —, Qwen3.8 27B: 44.3 (#66)

Long Context benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
LMArena Longer Query	—	1448

Writing & Preference Qwen3.8 27B leads

Mistral Small 3.2: 45.1 (#219), Qwen3.8 27B: 65.9 (#41)

Writing & Preference benchmarks
Benchmark	Mistral Small 3.2	Qwen3.8 27B
EQ-Bench Creative Writing	1255	1671
LMArena Text	—	1441
LMArena Creative Writing	—	1382
LMArena Multi-Turn	—	1443

Frequently asked questions

Is Mistral Small 3.2 better than Qwen3.8 27B?

Which is cheaper, Mistral Small 3.2 or Qwen3.8 27B?

Mistral Small 3.2 is cheaper. It lists at $0.0938 per million input tokens and $0.25 per million output tokens; Qwen3.8 27B lists at $0.99 and $1.49.

Which has the bigger context window?

Qwen3.8 27B does, with 262K tokens against 256K.

How many benchmarks do Mistral Small 3.2 and Qwen3.8 27B share?

2 benchmarks have published results for both models. Mistral Small 3.2 has 6 scored results on Noometry and Qwen3.8 27B has 28.