Noometry

Model comparison

DeepSeek-V3.1 vs Gemini 3.5 Flash Lite

DeepSeek-V3.1 and Gemini 3.5 Flash Lite score almost the same on the Noometry Index (42.2 vs 41.8), so choose on price, context window or the category you care about most.

Last verified . 22 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

Gemini 3.5 Flash Lite Google

41.8

Rank #113 Confirmed

Summary

  • They share 22 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 1 category and Gemini 3.5 Flash Lite in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-V3.1 leads 36.1 to 25.7.
  • The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 37.6% for Gemini 3.5 Flash Lite.
  • DeepSeek-V3.1 is cheaper at $0.25 / $0.95 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 164K.
  • DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1Gemini 3.5 Flash Lite
ProviderDeepSeekGoogle
Noometry Index42.241.8
Released2025-08-212026-07-21
WeightsOpenProprietary
Context window164K1.05M
Max output8K66K
Input $ / M tokens$0.25$0.30
Output $ / M tokens$0.95$2.50
Results tracked2738

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

Category by category

Coding Gemini 3.5 Flash Lite leads

DeepSeek-V3.1: 39.8 (#140), Gemini 3.5 Flash Lite: 42.1 (#96)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
WeirdML38.4%39%
LMArena Coding14171455
LMArena WebDev—1440
SciCode—41.3%
ALE-Bench—765.27

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, Gemini 3.5 Flash Lite: 28.6 (#82)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
GDP.pdf—10%

Reasoning Too close to call

DeepSeek-V3.1: 27.3 (#109), Gemini 3.5 Flash Lite: 27.8 (#95)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
LMArena Hard Prompts14171441
DTBench82.7%83.5%
LMCA24.3%37.6%
Epoch Capabilities Index139.92145.12
ARC-AGI-2—10.3%
SimpleBench40%—
Kagi LLM Benchmark53.2%—
NYT Connections (extended)—60.4%
ARC-AGI-1—53.5%
CritPt—0%
Chess Puzzles—22%
Mystery Game Puzzles—19%
ForecastBench58—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.1 (#125), Gemini 3.5 Flash Lite: 25.7 (#245)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
LMArena Math14201431
FrontierMath (Tiers 1-3)—26%
FrontierMath Tier 4—0%
OTIS Mock AIME 2024-2025—71.1%
ProofBench—13%

Knowledge Gemini 3.5 Flash Lite leads

DeepSeek-V3.1: 43.0 (#86), Gemini 3.5 Flash Lite: 50.0 (#66)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
LMArena Expert14031430
GPQA Diamond—83.3%
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

DeepSeek-V3.1: —, Gemini 3.5 Flash Lite: 40.3 (#38)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
LMArena Vision—1266

Multilingual Gemini 3.5 Flash Lite leads

DeepSeek-V3.1: 51.8 (#100), Gemini 3.5 Flash Lite: 53.8 (#59)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
LMArena Non-English14001428
LMArena Chinese14701467
LMArena French14471452
LMArena German14121454
LMArena Japanese13741428
LMArena Korean13371406
LMArena Russian14051443
LMArena Spanish14291440

Instruction Following Too close to call

DeepSeek-V3.1: 74.1 (#105), Gemini 3.5 Flash Lite: 75.0 (#77)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
LMArena Instruction Following14001420

Long Context Gemini 3.5 Flash Lite leads

DeepSeek-V3.1: 36.3 (#227), Gemini 3.5 Flash Lite: 43.8 (#80)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
LMArena Longer Query14221435
Fiction.LiveBench52.8%—

Writing & Preference Gemini 3.5 Flash Lite leads

DeepSeek-V3.1: 60.5 (#93), Gemini 3.5 Flash Lite: 64.4 (#55)

BenchmarkDeepSeek-V3.1Gemini 3.5 Flash Lite
LMArena Text14201436
LMArena Creative Writing14011419
EQ-Bench Creative Writing14361559
LMArena Multi-Turn14081445

Frequently asked questions

Is DeepSeek-V3.1 better than Gemini 3.5 Flash Lite?

DeepSeek-V3.1 and Gemini 3.5 Flash Lite score almost the same on the Noometry Index (42.2 vs 41.8), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek-V3.1 or Gemini 3.5 Flash Lite?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Gemini 3.5 Flash Lite lists at $0.30 and $2.50.

Is DeepSeek-V3.1 or Gemini 3.5 Flash Lite better for coding?

Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.1 versus 39.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.5 Flash Lite does, with 1.05M tokens against 164K.

How many benchmarks do DeepSeek-V3.1 and Gemini 3.5 Flash Lite share?

22 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemini 3.5 Flash Lite has 38.

Related comparisons

Go deeper