Noometry

Model comparison

DeepSeek V4.1 Flash vs Gemini 4 Argon

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 52.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 2 categories and Gemini 4 Argon in 8 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Gemini 4 Argon leads 49.2 to 31.2.
  • The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 Flash and 99% for Gemini 4 Argon.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 FlashGemini 4 Argon
ProviderDeepSeekGoogle
Noometry Index52.856.5
Released2026-09-092026-09-30
WeightsOpenProprietary
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3721

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

Category by category

Coding Gemini 4 Argon leads

DeepSeek V4.1 Flash: 52.9 (#32), Gemini 4 Argon: 62.0 (#9)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
LMArena WebDev16191678
SciCode51.9%61.8%
LMArena Coding15061550
FrontierSWE—55%
ALE-Bench1,092—

Agentic & Tool Use Gemini 4 Argon leads

DeepSeek V4.1 Flash: 31.2 (#69), Gemini 4 Argon: 49.2 (#8)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
APEX-Agents39.5%82.2%
GDP.pdf19.8%—
Vending-Bench 2—13,718

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Gemini 4 Argon: 44.2 (#47)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
CritPt14.3%27.1%
LMArena Hard Prompts14831548
NYT Connections (extended)89.6%—
Mystery Game Puzzles43%—
DTBench89.9%—
LMCA47%—
Surface Evolver Bench46.3%—
Epoch Capabilities Index154.9—

Math Gemini 4 Argon leads

DeepSeek V4.1 Flash: 66.7 (#25), Gemini 4 Argon: 73.9 (#17)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
ProofBench54%99%
LMArena Math14771536
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Gemini 4 Argon: 43.9 (#89)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
LMArena Expert15061553
GPQA Diamond89.8%—

Multimodal Gemini 4 Argon leads

DeepSeek V4.1 Flash: 39.1 (#61), Gemini 4 Argon: 46.5 (#14)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
LMArena Vision1277—
Blueprint-Bench 2—54.4%
Furniture Assembly34.2%—

Multilingual Gemini 4 Argon leads

DeepSeek V4.1 Flash: 55.0 (#35), Gemini 4 Argon: 60.3 (#1)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
LMArena Non-English14481523
LMArena Chinese14971610
LMArena Russian14711537
LMArena Spanish14591497
LMArena French1452—
LMArena German1484—
LMArena Japanese1412—
LMArena Korean1452—

Instruction Following Gemini 4 Argon leads

DeepSeek V4.1 Flash: 77.3 (#26), Gemini 4 Argon: 80.1 (#2)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
LMArena Instruction Following14741538

Long Context Gemini 4 Argon leads

DeepSeek V4.1 Flash: 45.2 (#47), Gemini 4 Argon: 47.6 (#15)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
LMArena Longer Query14751549

Writing & Preference Gemini 4 Argon leads

DeepSeek V4.1 Flash: 65.4 (#48), Gemini 4 Argon: 71.4 (#19)

BenchmarkDeepSeek V4.1 FlashGemini 4 Argon
LMArena Text14621534
LMArena Creative Writing14351531
LMArena Multi-Turn14571557
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Gemini 4 Argon?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 52.8 on the Noometry Index.

Is DeepSeek V4.1 Flash or Gemini 4 Argon better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 52.9 in the Noometry coding category.

How many benchmarks do DeepSeek V4.1 Flash and Gemini 4 Argon share?

18 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Gemini 4 Argon has 21.

Related comparisons

Go deeper