Noometry

Model comparison

DeepSeek V4 Flash vs Gemini 3.5 Flash Lite

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 41.5 on the Noometry Index.

Last verified . 36 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

Gemini 3.5 Flash Lite Google

41.5

Rank #133 Confirmed

Summary

  • They share 36 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 5 categories and Gemini 3.5 Flash Lite in 3 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4 Flash leads 60.3 to 25.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 61.4% for DeepSeek V4 Flash and 10.3% for Gemini 3.5 Flash Lite.
  • DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $2.50 for Gemini 3.5 Flash Lite.
  • Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 1M.
  • DeepSeek V4 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 FlashGemini 3.5 Flash Lite
ProviderDeepSeekGoogle
Noometry Index53.641.5
Released2026-04-242026-07-21
WeightsOpenProprietary
Context window1M1.05M
Max output393K66K
Input $ / M tokens$0.15$0.30
Output $ / M tokens$0.60$2.50
Results tracked4139

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

Category by category

Coding DeepSeek V4 Flash leads

DeepSeek V4 Flash: 47.9 (#59), Gemini 3.5 Flash Lite: 42.4 (#104)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
LMArena WebDev15821440
SciCode49.9%41.3%
WeirdML63%39%
LMArena Coding14571453
ALE-Bench1,306765.27
FrontierCode18.8%—

Agentic & Tool Use Not comparable

DeepSeek V4 Flash: —, Gemini 3.5 Flash Lite: 25.7 (#107)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
APEX-Agents—29.3%
GDP.pdf—10%

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#30), Gemini 3.5 Flash Lite: 27.8 (#114)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
ARC-AGI-261.4%10.3%
NYT Connections (extended)89.6%60.4%
ARC-AGI-189%53.5%
CritPt16.6%0%
Chess Puzzles33%22%
LMArena Hard Prompts14441441
Mystery Game Puzzles34%19%
DTBench90.9%83.5%
LMCA41.7%37.6%
Epoch Capabilities Index154.49145.13
SimpleBench61.1%—
Kagi LLM Benchmark52.2%—

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.3 (#37), Gemini 3.5 Flash Lite: 25.9 (#264)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
FrontierMath (Tiers 1-3)57.5%26%
FrontierMath Tier 424.4%0%
OTIS Mock AIME 2024-202594.4%71.1%
ProofBench56%13%
LMArena Math14271433
MathArena Final-Answer Competitions76.5%—

Knowledge DeepSeek V4 Flash leads

DeepSeek V4 Flash: 55.4 (#48), Gemini 3.5 Flash Lite: 50.1 (#72)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
GPQA Diamond91%83.3%
LMArena Expert14411435
SimpleQA Verified33.6%—

Multimodal Not comparable

DeepSeek V4 Flash: —, Gemini 3.5 Flash Lite: 41.1 (#40)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
LMArena Vision—1268

Multilingual Too close to call

DeepSeek V4 Flash: 53.0 (#72), Gemini 3.5 Flash Lite: 53.5 (#63)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
LMArena Non-English14201427
LMArena Chinese14681469
LMArena French14391451
LMArena German14181454
LMArena Japanese14061427
LMArena Korean13841407
LMArena Russian14281443
LMArena Spanish14361442

Instruction Following Too close to call

DeepSeek V4 Flash: 74.9 (#81), Gemini 3.5 Flash Lite: 74.8 (#85)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
LMArena Instruction Following14211420

Long Context Too close to call

DeepSeek V4 Flash: 43.8 (#85), Gemini 3.5 Flash Lite: 43.9 (#84)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
LMArena Longer Query14341435

Writing & Preference Too close to call

DeepSeek V4 Flash: 63.8 (#61), Gemini 3.5 Flash Lite: 64.2 (#57)

BenchmarkDeepSeek V4 FlashGemini 3.5 Flash Lite
LMArena Text14321435
LMArena Creative Writing14031420
EQ-Bench Creative Writing15591559
LMArena Multi-Turn14491445

Frequently asked questions

Is DeepSeek V4 Flash better than Gemini 3.5 Flash Lite?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 41.5 on the Noometry Index.

Which is cheaper, DeepSeek V4 Flash or Gemini 3.5 Flash Lite?

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3.5 Flash Lite lists at $0.30 and $2.50.

Is DeepSeek V4 Flash or Gemini 3.5 Flash Lite better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.5 Flash Lite does, with 1.05M tokens against 1M.

How many benchmarks do DeepSeek V4 Flash and Gemini 3.5 Flash Lite share?

36 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Gemini 3.5 Flash Lite has 39.

Related comparisons

Go deeper