Noometry

Model comparison

DeepSeek LLM 67B vs Gemini 1.5 Flash 8B

Gemini 1.5 Flash 8B is the stronger model overall, scoring 29.9 to 24.9 on the Noometry Index.

Last verified . 12 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Gemini 1.5 Flash 8B Google

29.9

Rank #301 Confirmed

Summary

  • They share 12 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Gemini 1.5 Flash 8B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemini 1.5 Flash 8B leads 42.8 to 31.6.
  • The biggest single-benchmark swing is GPQA Diamond: 24.6% for DeepSeek LLM 67B and 33% for Gemini 1.5 Flash 8B.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BGemini 1.5 Flash 8B
ProviderDeepSeekGoogle
Noometry Index24.929.9
Released2023-11-292024-10-03
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1521

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

Category by category

Coding Gemini 1.5 Flash 8B leads

DeepSeek LLM 67B: 31.9 (#278), Gemini 1.5 Flash 8B: 35.5 (#225)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
LMArena Coding10961218

Reasoning Gemini 1.5 Flash 8B leads

DeepSeek LLM 67B: 16.5 (#304), Gemini 1.5 Flash 8B: 20.0 (#244)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
LMArena Hard Prompts10701209
Chess Puzzles0%—
DTBench—50%
Epoch Capabilities Index110.5—

Math Gemini 1.5 Flash 8B leads

DeepSeek LLM 67B: 8.7 (#324), Gemini 1.5 Flash 8B: 14.2 (#302)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
OTIS Mock AIME 2024-20250.8%4.6%
LMArena Math11081207
MATH Level 56.4%—

Knowledge Gemini 1.5 Flash 8B leads

DeepSeek LLM 67B: 7.0 (#313), Gemini 1.5 Flash 8B: 16.0 (#289)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
GPQA Diamond24.6%33%
LMArena Expert—1185

Multimodal Not comparable

DeepSeek LLM 67B: —, Gemini 1.5 Flash 8B: 28.2 (#115)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
LMArena Vision—1044

Multilingual Gemini 1.5 Flash 8B leads

DeepSeek LLM 67B: 29.4 (#267), Gemini 1.5 Flash 8B: 38.5 (#229)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
LMArena Non-English10731215
LMArena Chinese11321231
LMArena French—1234
LMArena German—1206
LMArena Japanese—1150
LMArena Korean—1140
LMArena Russian—1236
LMArena Spanish—1212

Instruction Following Gemini 1.5 Flash 8B leads

DeepSeek LLM 67B: 55.4 (#277), Gemini 1.5 Flash 8B: 62.8 (#236)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
LMArena Instruction Following10791199

Long Context Gemini 1.5 Flash 8B leads

DeepSeek LLM 67B: 33.1 (#265), Gemini 1.5 Flash 8B: 37.0 (#225)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
LMArena Longer Query10921219

Writing & Preference Gemini 1.5 Flash 8B leads

DeepSeek LLM 67B: 31.6 (#282), Gemini 1.5 Flash 8B: 42.8 (#232)

BenchmarkDeepSeek LLM 67BGemini 1.5 Flash 8B
LMArena Text11051226
LMArena Creative Writing10671218
LMArena Multi-Turn10821185

Frequently asked questions

Is DeepSeek LLM 67B better than Gemini 1.5 Flash 8B?

Gemini 1.5 Flash 8B is the stronger model overall, scoring 29.9 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or Gemini 1.5 Flash 8B better for coding?

Gemini 1.5 Flash 8B scores higher on coding benchmarks: 35.5 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Gemini 1.5 Flash 8B share?

12 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Gemini 1.5 Flash 8B has 21.

Related comparisons

Go deeper