Model comparison

DeepSeek-V3.2-Exp vs Magistral Small

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 30.2 on the Noometry Index.

Last verified October 10, 2026. 10 shared benchmarks.

DeepSeek-V3.2-Exp

DeepSeek

44.3

Rank #78 Confirmed

Magistral Small

Mistral AI

30.2

Rank #296 Confirmed

Summary

They share 10 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 4 categories and Magistral Small in 0 categories; 4 gaps are clear of the uncertainty.
The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 30.9.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for DeepSeek-V3.2-Exp and 30% for Magistral Small.
DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 128K.

Side by side

DeepSeek-V3.2-Exp and Magistral Small specifications
	DeepSeek-V3.2-Exp	Magistral Small
Provider	DeepSeek	Mistral AI
Noometry Index	44.3	30.2
Released	2025-09-29	2025-06-10
Weights	Open	Open
Context window	164K	128K
Max output	66K	40K
Input $ / M tokens	$0.26	$0.50
Output $ / M tokens	$0.38	$1.50
Results tracked	49	10

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

Category by category

Coding DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 46.5 (#65), Magistral Small: 38.4 (#176)

Coding benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
SciCode	38.9%	35.2%
SWE-bench Verified (bash only)	70%	—
Aider Polyglot	74.2%	—
LMArena WebDev	1362	—
SWE-bench Multilingual	59%	—
WeirdML	39.5%	—
LMArena Coding	1454	—

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Exp: 32.7 (#59), Magistral Small: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
Terminal-Bench	39.6%	—
APEX-Agents	21.3%	—
Berkeley Function Calling Leaderboard	56.7%	—
TheAgentCompany	42.9%	—
Vending-Bench 2	1,034	—

Reasoning DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 22.1 (#208), Magistral Small: 6.8 (#350)

Reasoning benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
ARC-AGI-2	4%	0%
Kagi LLM Benchmark	52.2%	6.3%
ARC-AGI-1	57%	5%
CritPt	2.9%	0.3%
Chess Puzzles	14%	3%
DTBench	87.7%	61.3%
Epoch Capabilities Index	146.27	133.19
NYT Connections (extended)	36.7%	—
Thematic Generalization	65%	—
LMArena Hard Prompts	1434	—
LMCA	29.1%	—

Math DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 41.7 (#87), Magistral Small: 26.2 (#261)

Math benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
OTIS Mock AIME 2024-2025	87.8%	30%
MathArena Final-Answer Competitions	57.7%	—
ProofBench	8%	—
LMArena Math	1435	—
FrontierMath (Feb 2025 set)	22.1%	—
FrontierMath Tier 4 (v1)	2.1%	—

Knowledge DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 51.7 (#66), Magistral Small: 30.9 (#223)

Knowledge benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
GPQA Diamond	83.4%	56.1%
Vectara Hallucination Rate	5.3%	—
LMArena Expert	1436	—

Multilingual Not comparable

DeepSeek-V3.2-Exp: 52.2 (#90), Magistral Small: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
LMArena Non-English	1409	—
LMArena Chinese	1461	—
LMArena French	1433	—
LMArena German	1440	—
LMArena Japanese	1374	—
LMArena Korean	1371	—
LMArena Russian	1424	—
LMArena Spanish	1440	—

Instruction Following Not comparable

DeepSeek-V3.2-Exp: 74.5 (#93), Magistral Small: —

Instruction Following benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
LMArena Instruction Following	1413	—

Long Context Not comparable

DeepSeek-V3.2-Exp: 47.6 (#16), Magistral Small: —

Long Context benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
Fiction.LiveBench	83.3%	—
CL-bench	13.2%	—
CL-bench Life	9.5%	—
LMArena Longer Query	1428	—

Writing & Preference Not comparable

DeepSeek-V3.2-Exp: 62.4 (#77), Magistral Small: —

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.2-Exp	Magistral Small
LMArena Text	1425	—
LMArena Creative Writing	1403	—
EQ-Bench Creative Writing	1515	—
LMArena Multi-Turn	1427	—

Frequently asked questions

Is DeepSeek-V3.2-Exp better than Magistral Small?

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 30.2 on the Noometry Index.

Which is cheaper, DeepSeek-V3.2-Exp or Magistral Small?

DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Magistral Small lists at $0.50 and $1.50.

Is DeepSeek-V3.2-Exp or Magistral Small better for coding?

DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 38.4 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.2-Exp does, with 164K tokens against 128K.

How many benchmarks do DeepSeek-V3.2-Exp and Magistral Small share?

10 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Magistral Small has 10.