Model comparison

DeepSeek-V3.2-Speciale vs Mistral Medium

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 36.0 on the Noometry Index.

Last verified October 10, 2026. 1 shared benchmarks.

DeepSeek-V3.2-Speciale

DeepSeek

39.1

Rank #159 Reported

Mistral Medium

Mistral AI

36.0

Rank #211 Confirmed

Summary

They share 1 benchmark with published results for both. DeepSeek-V3.2-Speciale scores higher in 2 categories and Mistral Medium in 1 category; 3 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Mistral Medium leads 60.2 to 46.1.
DeepSeek-V3.2-Speciale is cheaper at $0.58 / $1.68 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Mistral Medium accepts more context: 262K tokens versus 128K.

Side by side

DeepSeek-V3.2-Speciale and Mistral Medium specifications
	DeepSeek-V3.2-Speciale	Mistral Medium
Provider	DeepSeek	Mistral AI
Noometry Index	39.1	36.0
Released	2025-12-01	2023-12-11
Weights	Open	Open
Context window	128K	262K
Max output	128K	262K
Input $ / M tokens	$0.58	$1.50
Output $ / M tokens	$1.68	$7.50
Results tracked	3	36

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

Category by category

Coding DeepSeek-V3.2-Speciale leads

DeepSeek-V3.2-Speciale: 39.9 (#136), Mistral Medium: 33.8 (#241)

Coding benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
WeirdML	46.7%	43.7%
FrontierCode	—	8%
SciCode	—	40.2%
LMArena Coding	—	1434
ALE-Bench	—	763.98

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Speciale: —, Mistral Medium: 28.1 (#84)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
Berkeley Function Calling Leaderboard	—	37.7%

Reasoning DeepSeek-V3.2-Speciale leads

DeepSeek-V3.2-Speciale: 32.1 (#65), Mistral Medium: 23.3 (#165)

Reasoning benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
SimpleBench	52.6%	—
Kagi LLM Benchmark	—	50%
CritPt	—	0%
LMArena Hard Prompts	—	1426
DTBench	—	75.5%
LMCA	—	26.1%
Surface Evolver Bench	—	26.9%

Math Not comparable

DeepSeek-V3.2-Speciale: —, Mistral Medium: 27.2 (#238)

Math benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
OTIS Mock AIME 2024-2025	—	32.2%
ProofBench	—	9%
LMArena Math	—	1409
MATH Level 5	—	81.6%
FrontierMath (Feb 2025 set)	—	0.3%

Knowledge Not comparable

DeepSeek-V3.2-Speciale: —, Mistral Medium: 24.9 (#260)

Knowledge benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
GPQA Diamond	—	59.5%
Humanity's Last Exam	—	4.5%
Vectara Hallucination Rate	—	22.7%
LMArena Expert	—	1408

Multimodal Not comparable

DeepSeek-V3.2-Speciale: —, Mistral Medium: 34.6 (#82)

Multimodal benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
LMArena Vision	—	1172

Multilingual Not comparable

DeepSeek-V3.2-Speciale: —, Mistral Medium: 52.3 (#86)

Multilingual benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
LMArena Non-English	—	1408
LMArena Chinese	—	1448
LMArena French	—	1460
LMArena German	—	1433
LMArena Japanese	—	1378
LMArena Korean	—	1382
LMArena Russian	—	1411
LMArena Spanish	—	1433

Instruction Following Not comparable

DeepSeek-V3.2-Speciale: —, Mistral Medium: 73.9 (#111)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
LMArena Instruction Following	—	1398

Long Context Not comparable

DeepSeek-V3.2-Speciale: —, Mistral Medium: 42.9 (#108)

Long Context benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
LMArena Longer Query	—	1406

Writing & Preference Mistral Medium leads

DeepSeek-V3.2-Speciale: 46.1 (#217), Mistral Medium: 60.2 (#97)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Mistral Medium
LMArena Text	—	1424
LMArena Creative Writing	—	1391
Short-Story Creative Writing	—	77.3%
EQ-Bench Creative Writing	1276	—
LMArena Multi-Turn	—	1418

Frequently asked questions

Is DeepSeek-V3.2-Speciale better than Mistral Medium?

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 36.0 on the Noometry Index.

Which is cheaper, DeepSeek-V3.2-Speciale or Mistral Medium?

DeepSeek-V3.2-Speciale is cheaper. It lists at $0.58 per million input tokens and $1.68 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

Is DeepSeek-V3.2-Speciale or Mistral Medium better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Mistral Medium does, with 262K tokens against 128K.

How many benchmarks do DeepSeek-V3.2-Speciale and Mistral Medium share?

1 benchmark has published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Mistral Medium has 36.