Model comparison

DeepSeek-V3.2-Exp vs Ministral 8B

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 28.2 on the Noometry Index. Ministral 8B costs 1.9× 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. 16 shared benchmarks.

DeepSeek-V3.2-Exp

DeepSeek

44.3

Rank #78 Confirmed

Ministral 8B

Mistral AI

28.2

Rank #325 Confirmed

Summary

They share 16 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 9 categories and Ministral 8B in 0 categories; 9 gaps are clear of the uncertainty.
The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 12.6.
The biggest single-benchmark swing is GPQA Diamond: 83.4% for DeepSeek-V3.2-Exp and 27.1% for Ministral 8B.
Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
Ministral 8B accepts more context: 262K tokens versus 164K.

Side by side

DeepSeek-V3.2-Exp and Ministral 8B specifications
	DeepSeek-V3.2-Exp	Ministral 8B
Provider	DeepSeek	Mistral AI
Noometry Index	44.3	28.2
Released	2025-09-29	2024-10-01
Weights	Open	Open
Context window	164K	262K
Max output	66K	262K
Input $ / M tokens	$0.26	$0.15
Output $ / M tokens	$0.38	$0.15
Results tracked	49	17

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), Ministral 8B: 35.0 (#230)

Coding benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
LMArena Coding	1454	1202
SWE-bench Verified (bash only)	70%	—
Aider Polyglot	74.2%	—
LMArena WebDev	1362	—
SWE-bench Multilingual	59%	—
SciCode	38.9%	—
WeirdML	39.5%	—

Agentic & Tool Use DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 32.7 (#59), Ministral 8B: 16.4 (#148)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
Berkeley Function Calling Leaderboard	56.7%	11.1%
Terminal-Bench	39.6%	—
APEX-Agents	21.3%	—
TheAgentCompany	42.9%	—
Vending-Bench 2	1,034	—

Reasoning DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 22.1 (#208), Ministral 8B: 18.4 (#281)

Reasoning benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
LMArena Hard Prompts	1434	1191
DTBench	87.7%	45.7%
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%	—
LMCA	29.1%	—
Epoch Capabilities Index	146.27	—

Math DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 41.7 (#87), Ministral 8B: 25.7 (#267)

Math benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
LMArena Math	1435	1188
MathArena Final-Answer Competitions	57.7%	—
OTIS Mock AIME 2024-2025	87.8%	—
ProofBench	8%	—
MATH Level 5	—	14.9%
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), Ministral 8B: 12.6 (#297)

Knowledge benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
GPQA Diamond	83.4%	27.1%
Vectara Hallucination Rate	5.3%	7.4%
LMArena Expert	1436	1170

Multilingual DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 52.2 (#90), Ministral 8B: 35.1 (#247)

Multilingual benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
LMArena Non-English	1409	1165
LMArena Chinese	1461	1193
LMArena Russian	1424	1195
LMArena French	1433	—
LMArena German	1440	—
LMArena Japanese	1374	—
LMArena Korean	1371	—
LMArena Spanish	1440	—

Instruction Following DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 74.5 (#93), Ministral 8B: 60.5 (#250)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
LMArena Instruction Following	1413	1161

Long Context DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 47.6 (#16), Ministral 8B: 36.7 (#227)

Long Context benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
LMArena Longer Query	1428	1212
Fiction.LiveBench	83.3%	—
CL-bench	13.2%	—
CL-bench Life	9.5%	—

Writing & Preference DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 62.4 (#77), Ministral 8B: 39.6 (#246)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.2-Exp	Ministral 8B
LMArena Text	1425	1191
LMArena Creative Writing	1403	1175
LMArena Multi-Turn	1427	1166
EQ-Bench Creative Writing	1515	—

Frequently asked questions

Is DeepSeek-V3.2-Exp better than Ministral 8B?

Which is cheaper, DeepSeek-V3.2-Exp or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.

Is DeepSeek-V3.2-Exp or Ministral 8B better for coding?

DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 35.0 in the Noometry coding category.

Which has the bigger context window?

Ministral 8B does, with 262K tokens against 164K.

How many benchmarks do DeepSeek-V3.2-Exp and Ministral 8B share?

16 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Ministral 8B has 17.