Noometry

Model comparison

DeepSeek-V3.1 vs Gemini 1.5 Flash 8B

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

Gemini 1.5 Flash 8B Google

29.7

Rank #292 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Gemini 1.5 Flash 8B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.0 to 16.0.
  • The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 50% for Gemini 1.5 Flash 8B.
  • DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1Gemini 1.5 Flash 8B
ProviderDeepSeekGoogle
Noometry Index42.229.7
Released2025-08-212024-10-03
WeightsOpenProprietary
Context window164K—
Max output8K—
Input $ / M tokens$0.25—
Output $ / M tokens$0.95—
Results tracked2721

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 39.8 (#140), Gemini 1.5 Flash 8B: 34.9 (#221)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Coding14171218
WeirdML38.4%—

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.3 (#109), Gemini 1.5 Flash 8B: 19.2 (#242)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Hard Prompts14171210
DTBench82.7%50%
SimpleBench40%—
Kagi LLM Benchmark53.2%—
LMCA24.3%—
Epoch Capabilities Index139.92—
ForecastBench58—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.1 (#125), Gemini 1.5 Flash 8B: 13.3 (#296)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Math14201207
OTIS Mock AIME 2024-2025—4.6%

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.0 (#86), Gemini 1.5 Flash 8B: 16.0 (#285)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Expert14031185
GPQA Diamond—33%
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

DeepSeek-V3.1: —, Gemini 1.5 Flash 8B: 27.6 (#110)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Vision—1044

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.8 (#100), Gemini 1.5 Flash 8B: 38.6 (#224)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Non-English14001215
LMArena Chinese14701231
LMArena French14471233
LMArena German14121206
LMArena Japanese13741150
LMArena Korean13371140
LMArena Russian14051236
LMArena Spanish14291212

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 74.1 (#105), Gemini 1.5 Flash 8B: 63.1 (#231)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Instruction Following14001199

Long Context Too close to call

DeepSeek-V3.1: 36.3 (#227), Gemini 1.5 Flash 8B: 36.9 (#220)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Longer Query14221219
Fiction.LiveBench52.8%—

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.5 (#93), Gemini 1.5 Flash 8B: 43.0 (#227)

BenchmarkDeepSeek-V3.1Gemini 1.5 Flash 8B
LMArena Text14201226
LMArena Creative Writing14011218
LMArena Multi-Turn14081185
EQ-Bench Creative Writing1436—

Frequently asked questions

Is DeepSeek-V3.1 better than Gemini 1.5 Flash 8B?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.7 on the Noometry Index.

Is DeepSeek-V3.1 or Gemini 1.5 Flash 8B better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 34.9 in the Noometry coding category.

How many benchmarks do DeepSeek-V3.1 and Gemini 1.5 Flash 8B share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemini 1.5 Flash 8B has 21.

Related comparisons

Go deeper