Noometry

Model comparison

DeepSeek V4.1 Flash vs Magistral Medium

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 35.2 on the Noometry Index.

Last verified . 19 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Magistral Medium Mistral AI

35.2

Rank #227 Confirmed

Summary

  • They share 19 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 8.6.
  • The biggest single-benchmark swing is CritPt: 14.3% for DeepSeek V4.1 Flash and 0.3% for Magistral Medium.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $5 for Magistral Medium.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 262K.

Side by side

DeepSeek V4.1 FlashMagistral Medium
ProviderDeepSeekMistral AI
Noometry Index52.835.2
Released2026-09-092025-03-17
WeightsOpenOpen
Context window1M262K
Max output393K16K
Input $ / M tokens$0.15$2
Output $ / M tokens$0.60$5
Results tracked3722

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), Magistral Medium: 39.1 (#161)

BenchmarkDeepSeek V4.1 FlashMagistral Medium
SciCode51.9%39.2%
LMArena Coding15061319
LMArena WebDev1619—
ALE-Bench1,092—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), Magistral Medium: —

BenchmarkDeepSeek V4.1 FlashMagistral Medium
APEX-Agents39.5%—
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Magistral Medium: 8.6 (#348)

BenchmarkDeepSeek V4.1 FlashMagistral Medium
CritPt14.3%0.3%
LMArena Hard Prompts14831267
ARC-AGI-2—0%
Kagi LLM Benchmark—16.2%
NYT Connections (extended)89.6%—
ARC-AGI-1—6.1%
Mystery Game Puzzles43%—
DTBench89.9%—
LMCA47%—
Surface Evolver Bench46.3%—
Epoch Capabilities Index154.9—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Magistral Medium: 35.1 (#189)

BenchmarkDeepSeek V4.1 FlashMagistral Medium
LMArena Math14771250
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Magistral Medium: 33.5 (#202)

BenchmarkDeepSeek V4.1 FlashMagistral Medium
LMArena Expert15061223
GPQA Diamond89.8%—

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Magistral Medium: —

BenchmarkDeepSeek V4.1 FlashMagistral Medium
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Magistral Medium: 39.6 (#224)

BenchmarkDeepSeek V4.1 FlashMagistral Medium
LMArena Non-English14481232
LMArena Chinese14971227
LMArena French14521267
LMArena German14841248
LMArena Japanese14121175
LMArena Korean14521125
LMArena Russian14711224
LMArena Spanish14591271

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Magistral Medium: 66.0 (#211)

BenchmarkDeepSeek V4.1 FlashMagistral Medium
LMArena Instruction Following14741254

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Magistral Medium: 39.3 (#183)

BenchmarkDeepSeek V4.1 FlashMagistral Medium
LMArena Longer Query14751295

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Magistral Medium: 46.3 (#219)

BenchmarkDeepSeek V4.1 FlashMagistral Medium
LMArena Text14621255
LMArena Creative Writing14351245
LMArena Multi-Turn14571275
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Magistral Medium?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 35.2 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Magistral Medium?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Magistral Medium lists at $2 and $5.

Is DeepSeek V4.1 Flash or Magistral Medium better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 39.1 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 Magistral Medium share?

19 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Magistral Medium has 22.

Related comparisons

Go deeper