Noometry

Model comparison

Deepseek Coder v2 vs Gemini 1.5 Flash 8B

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 29.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Gemini 1.5 Flash 8B Google

29.9

Rank #301 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 5 categories and Gemini 1.5 Flash 8B in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 14.2.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2Gemini 1.5 Flash 8B
ProviderDeepSeekGoogle
Noometry Index35.929.9
Released2024-06-172024-10-03
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2421

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

Category by category

Coding Deepseek Coder v2 leads

Deepseek Coder v2: 38.1 (#183), Gemini 1.5 Flash 8B: 35.5 (#225)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Coding12511218
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
HumanEval+82.3%—
MBPP+75.1%—

Reasoning Deepseek Coder v2 leads

Deepseek Coder v2: 23.6 (#176), Gemini 1.5 Flash 8B: 20.0 (#244)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Hard Prompts12071209
DTBench—50%
WinoGrande83.7%—

Math Deepseek Coder v2 leads

Deepseek Coder v2: 34.9 (#190), Gemini 1.5 Flash 8B: 14.2 (#302)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Math12411207
OTIS Mock AIME 2024-2025—4.6%
GSM8K94.5%—

Knowledge Deepseek Coder v2 leads

Deepseek Coder v2: 32.3 (#212), Gemini 1.5 Flash 8B: 16.0 (#289)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Expert11811185
GPQA Diamond—33%
ARC (AI2) Challenge64.3%—

Multimodal Not comparable

Deepseek Coder v2: —, Gemini 1.5 Flash 8B: 28.2 (#115)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Vision—1044

Multilingual Gemini 1.5 Flash 8B leads

Deepseek Coder v2: 36.3 (#240), Gemini 1.5 Flash 8B: 38.5 (#229)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Non-English11821215
LMArena Chinese12011231
LMArena French11851234
LMArena German11641206
LMArena Japanese11261150
LMArena Korean11041140
LMArena Russian11881236
LMArena Spanish11531212

Instruction Following Gemini 1.5 Flash 8B leads

Deepseek Coder v2: 61.7 (#242), Gemini 1.5 Flash 8B: 62.8 (#236)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Instruction Following11801199

Long Context Too close to call

Deepseek Coder v2: 37.0 (#224), Gemini 1.5 Flash 8B: 37.0 (#225)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Longer Query12191219

Writing & Preference Gemini 1.5 Flash 8B leads

Deepseek Coder v2: 38.2 (#253), Gemini 1.5 Flash 8B: 42.8 (#232)

BenchmarkDeepseek Coder v2Gemini 1.5 Flash 8B
LMArena Text11911226
LMArena Creative Writing11201218
LMArena Multi-Turn11771185

Frequently asked questions

Is Deepseek Coder v2 better than Gemini 1.5 Flash 8B?

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 29.9 on the Noometry Index.

Is Deepseek Coder v2 or Gemini 1.5 Flash 8B better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 35.5 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and Gemini 1.5 Flash 8B share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemini 1.5 Flash 8B has 21.

Related comparisons

Go deeper