Noometry

Model comparison

DeepSeek V4.1 Flash vs Gemini 3 Flash Preview

DeepSeek V4.1 Flash and Gemini 3 Flash Preview score almost the same on the Noometry Index (52.8 vs 52.3), so choose on price, context window or the category you care about most.

Last verified . 31 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 31 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 5 categories and Gemini 3 Flash Preview in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 51.7.
  • The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 Flash and 15% for Gemini 3 Flash Preview.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1M.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 FlashGemini 3 Flash Preview
ProviderDeepSeekGoogle
Noometry Index52.852.3
Released2026-09-092025-12-17
WeightsOpenProprietary
Context window1M1.05M
Max output393K66K
Input $ / M tokens$0.15$0.50
Output $ / M tokens$0.60$3
Results tracked3759

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), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
LMArena WebDev16191439
LMArena Coding15061460
ALE-Bench1,0921,367
SWE-bench Verified—75.4%
SWE-bench Verified (bash only)—75.8%
SWE-bench Multilingual—72.7%
SciCode51.9%—
GSO—9.8%
WeirdML—61.6%

Agentic & Tool Use Gemini 3 Flash Preview leads

DeepSeek V4.1 Flash: 31.2 (#69), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
GDP.pdf19.8%10%
Terminal-Bench—64.3%
APEX-Agents39.5%—
τ²-bench Airline—82.5%
τ²-bench Banking—27.3%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
DeepResearch Bench—49.8%
BALROG—48.1%
LMArena Search—1198
Vending-Bench 2—3,635

Reasoning Too close to call

DeepSeek V4.1 Flash: 50.2 (#36), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
NYT Connections (extended)89.6%83.1%
LMArena Hard Prompts14831465
Mystery Game Puzzles43%26%
DTBench89.9%89.1%
LMCA47%43.1%
Epoch Capabilities Index154.9151.8
ARC-AGI-2—33.6%
SimpleBench—61.1%
ARC-AGI-1—84.7%
CritPt14.3%—
Chess Puzzles—40%
Surface Evolver Bench46.3%—
ForecastBench—58.5

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
FrontierMath (Tiers 1-3)67.4%51.2%
FrontierMath Tier 426.8%17.1%
OTIS Mock AIME 2024-202598.3%95.6%
ProofBench54%15%
LMArena Math14771473
MathArena Final-Answer Competitions—67.6%
FrontierMath (Feb 2025 set)—35.6%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Too close to call

DeepSeek V4.1 Flash: 57.9 (#38), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
GPQA Diamond89.8%89.4%
LMArena Expert15061462
SimpleQA Verified—66.8%
Vectara Hallucination Rate—13.5%

Multimodal Gemini 3 Flash Preview leads

DeepSeek V4.1 Flash: 39.1 (#61), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
LMArena Vision12771285
GeoBench—88%
VPCT—72.6%
Blueprint-Bench 2—0%
Furniture Assembly34.2%—
LMArena Document—1413

Multilingual Too close to call

DeepSeek V4.1 Flash: 55.0 (#35), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
LMArena Non-English14481458
LMArena Chinese14971511
LMArena French14521477
LMArena German14841497
LMArena Japanese14121489
LMArena Korean14521443
LMArena Russian14711480
LMArena Spanish14591469

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
LMArena Instruction Following14741437

Long Context Too close to call

DeepSeek V4.1 Flash: 45.2 (#47), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
LMArena Longer Query14751452

Writing & Preference Too close to call

DeepSeek V4.1 Flash: 65.4 (#48), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkDeepSeek V4.1 FlashGemini 3 Flash Preview
LMArena Text14621466
LMArena Creative Writing14351457
LMArena Multi-Turn14571471
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Gemini 3 Flash Preview?

DeepSeek V4.1 Flash and Gemini 3 Flash Preview score almost the same on the Noometry Index (52.8 vs 52.3), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek V4.1 Flash or Gemini 3 Flash Preview?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

Is DeepSeek V4.1 Flash or Gemini 3 Flash Preview better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 50.9 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 1M.

How many benchmarks do DeepSeek V4.1 Flash and Gemini 3 Flash Preview share?

31 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper