Model comparison

DeepSeek-V3.2-Exp vs Ministral 3B

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 25.6 on the Noometry Index. Ministral 3B costs 7.3× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.

Last verified October 10, 2026. 5 shared benchmarks.

DeepSeek-V3.2-Exp

DeepSeek

44.9

Rank #68 Confirmed

Ministral 3B

Mistral AI

25.6

Rank #336 Confirmed

Summary

They share 5 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 3 categories and Ministral 3B in 0 categories; 3 gaps are clear of the uncertainty.
The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 10.4.
The biggest single-benchmark swing is GPQA Diamond: 83.4% for DeepSeek-V3.2-Exp and 25.3% for Ministral 3B.
Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 128K.

Side by side

DeepSeek-V3.2-Exp and Ministral 3B specifications
	DeepSeek-V3.2-Exp	Ministral 3B
Provider	DeepSeek	Mistral AI
Noometry Index	44.9	25.6
Released	2025-09-29	2024-10-01
Weights	Open	Open
Context window	164K	128K
Max output	66K	128K
Input $ / M tokens	$0.26	$0.04
Output $ / M tokens	$0.38	$0.04
Results tracked	48	6

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

Category by category

Coding Not comparable

DeepSeek-V3.2-Exp: 46.4 (#61), Ministral 3B: —

Coding benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
SWE-bench Verified (bash only)	70%	—
Aider Polyglot	74.2%	—
LMArena WebDev	1362	—
SWE-bench Multilingual	59%	—
SciCode	38.9%	—
WeirdML	39.5%	—
LMArena Coding	1454	—

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Exp: 37.9 (#31), Ministral 3B: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
Terminal-Bench	39.6%	—
Berkeley Function Calling Leaderboard	56.7%	—
TheAgentCompany	42.9%	—
Vending-Bench 2	1,034	—

Reasoning DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 22.0 (#185), Ministral 3B: 17.7 (#278)

Reasoning benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
DTBench	87.7%	51.7%
LMCA	29.1%	5.5%
Epoch Capabilities Index	146.28	118.08
ARC-AGI-2	4%	—
Kagi LLM Benchmark	52.2%	—
NYT Connections (extended)	36.7%	—
ARC-AGI-1	57%	—
CritPt	2.9%	—
Chess Puzzles	14%	—
Thematic Generalization	65%	—
LMArena Hard Prompts	1433	—

Math DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 40.8 (#75), Ministral 3B: 24.5 (#257)

Math benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
MathArena Final-Answer Competitions	57.7%	—
OTIS Mock AIME 2024-2025	87.8%	—
ProofBench	8%	—
LMArena Math	1435	—
MATH Level 5	—	14.4%
FrontierMath (Feb 2025 set)	22.1%	—
FrontierMath Tier 4 (v1)	2.1%	—

Knowledge DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 51.6 (#61), Ministral 3B: 10.4 (#297)

Knowledge benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
GPQA Diamond	83.4%	25.3%
Vectara Hallucination Rate	5.3%	7.3%
LMArena Expert	1436	—

Multilingual Not comparable

DeepSeek-V3.2-Exp: 52.4 (#85), Ministral 3B: —

Multilingual benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
LMArena Non-English	1409	—
LMArena Chinese	1461	—
LMArena French	1435	—
LMArena German	1440	—
LMArena Japanese	1377	—
LMArena Korean	1372	—
LMArena Russian	1423	—
LMArena Spanish	1441	—

Instruction Following Not comparable

DeepSeek-V3.2-Exp: 74.7 (#89), Ministral 3B: —

Instruction Following benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
LMArena Instruction Following	1413	—

Long Context Not comparable

DeepSeek-V3.2-Exp: 47.6 (#15), Ministral 3B: —

Long Context benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
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: 62.5 (#73), Ministral 3B: —

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 3B
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 Ministral 3B?

Which is cheaper, DeepSeek-V3.2-Exp or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.

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 Ministral 3B share?

5 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Ministral 3B has 6.