Noometry

Model comparison

DeepSeek V4.1 Flash vs Ministral 8B

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 28.2 on the Noometry Index. Ministral 8B costs 1.7× less per token, which makes it the better buy when DeepSeek V4.1 Flash's lead doesn't matter for your workload.

Last verified . 14 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Ministral 8B Mistral AI

28.2

Rank #325 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek V4.1 Flash 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 V4.1 Flash leads 57.9 to 12.6.
  • The biggest single-benchmark swing is GPQA Diamond: 89.8% for DeepSeek V4.1 Flash and 27.1% for Ministral 8B.
  • Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4.1 Flash.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 262K.

Side by side

DeepSeek V4.1 FlashMinistral 8B
ProviderDeepSeekMistral AI
Noometry Index52.828.2
Released2026-09-092024-10-01
WeightsOpenOpen
Context window1M262K
Max output393K262K
Input $ / M tokens$0.15$0.15
Output $ / M tokens$0.60$0.15
Results tracked3717

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Ministral 8B: 35.0 (#230)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
LMArena Coding15061202
LMArena WebDev1619—
SciCode51.9%—
ALE-Bench1,092—

Agentic & Tool Use DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 31.2 (#69), Ministral 8B: 16.4 (#148)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
APEX-Agents39.5%—
Berkeley Function Calling Leaderboard—11.1%
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Ministral 8B: 18.4 (#281)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
LMArena Hard Prompts14831191
DTBench89.9%45.7%
NYT Connections (extended)89.6%—
CritPt14.3%—
Mystery Game Puzzles43%—
LMCA47%—
Surface Evolver Bench46.3%—
Epoch Capabilities Index154.9—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Ministral 8B: 25.7 (#267)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
LMArena Math14771188
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—
MATH Level 5—14.9%

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Ministral 8B: 12.6 (#297)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
GPQA Diamond89.8%27.1%
LMArena Expert15061170
Vectara Hallucination Rate—7.4%

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Ministral 8B: —

BenchmarkDeepSeek V4.1 FlashMinistral 8B
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Ministral 8B: 35.1 (#247)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
LMArena Non-English14481165
LMArena Chinese14971193
LMArena Russian14711195
LMArena French1452—
LMArena German1484—
LMArena Japanese1412—
LMArena Korean1452—
LMArena Spanish1459—

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Ministral 8B: 60.5 (#250)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
LMArena Instruction Following14741161

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Ministral 8B: 36.7 (#227)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
LMArena Longer Query14751212

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Ministral 8B: 39.6 (#246)

BenchmarkDeepSeek V4.1 FlashMinistral 8B
LMArena Text14621191
LMArena Creative Writing14351175
LMArena Multi-Turn14571166
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Ministral 8B?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 28.2 on the Noometry Index. Ministral 8B costs 1.7× less per token, which makes it the better buy when DeepSeek V4.1 Flash's lead doesn't matter for your workload.

Which is cheaper, DeepSeek V4.1 Flash or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.

Is DeepSeek V4.1 Flash or Ministral 8B better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 35.0 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 262K.

How many benchmarks do DeepSeek V4.1 Flash and Ministral 8B share?

14 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Ministral 8B has 17.

Related comparisons

Go deeper