Noometry

Model comparison

DeepSeek-V2.5 (Sep 2024) vs Gemma 2 9B

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 25.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

DeepSeek-V2.5 (Sep 2024) DeepSeek

37.6

Rank #200 Confirmed

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Summary

  • They share 19 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 8 categories and Gemma 2 9B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-V2.5 (Sep 2024) leads 35.9 to 9.9.
  • The biggest single-benchmark swing is BigCodeBench Instruct: 48.6% for DeepSeek-V2.5 (Sep 2024) and 34.7% for Gemma 2 9B.

Side by side

DeepSeek-V2.5 (Sep 2024)Gemma 2 9B
ProviderDeepSeekGoogle
Noometry Index37.625.9
Released2024-09-062024-06-24
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2235

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

Category by category

Coding DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Gemma 2 9B: 29.4 (#304)

BenchmarkDeepSeek-V2.5 (Sep 2024)Gemma 2 9B
BigCodeBench Instruct48.6%34.7%
LMArena Coding13091173
BigCodeBench Complete53.2%40.6%
Aider Polyglot17.8%—
LiveBench Coding—22.5%
HumanEval+83.5%—
MBPP+74.1%—

Reasoning DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Gemma 2 9B: 15.9 (#309)

BenchmarkDeepSeek-V2.5 (Sep 2024)Gemma 2 9B
LMArena Hard Prompts12891171
LiveBench Reasoning—15.2%
LiveBench Data Analysis—36.4%
Epoch Capabilities Index—119.83
LiveBench—28.7%
PIQA—83.7%

Math DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Gemma 2 9B: 9.9 (#318)

BenchmarkDeepSeek-V2.5 (Sep 2024)Gemma 2 9B
LMArena Math12881183
OTIS Mock AIME 2024-2025—0.6%
LiveBench Math—19.8%
MATH Level 5—21%
GSM8K—84.9%

Knowledge DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Gemma 2 9B: 9.7 (#305)

BenchmarkDeepSeek-V2.5 (Sep 2024)Gemma 2 9B
LMArena Expert12661147
GPQA Diamond—27.5%
BoolQ—85.7%
MMLU—72.1%

Multilingual DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Gemma 2 9B: 36.6 (#238)

BenchmarkDeepSeek-V2.5 (Sep 2024)Gemma 2 9B
LMArena Non-English12731188
LMArena Chinese13181185
LMArena French12891190
LMArena German12581186
LMArena Japanese12281144
LMArena Korean12091137
LMArena Russian12891200
LMArena Spanish12481200

Instruction Following DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Gemma 2 9B: 57.6 (#269)

BenchmarkDeepSeek-V2.5 (Sep 2024)Gemma 2 9B
LMArena Instruction Following12801178
LiveBench Instruction Following—52.6%

Long Context DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Gemma 2 9B: 36.3 (#233)

BenchmarkDeepSeek-V2.5 (Sep 2024)Gemma 2 9B
LMArena Longer Query13011197

Writing & Preference DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Gemma 2 9B: 32.1 (#281)

BenchmarkDeepSeek-V2.5 (Sep 2024)Gemma 2 9B
LMArena Text12941207
LMArena Creative Writing12851206
LMArena Multi-Turn12971193
EQ-Bench Creative Writing—841
LiveBench Language—25.5%

Frequently asked questions

Is DeepSeek-V2.5 (Sep 2024) better than Gemma 2 9B?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 25.9 on the Noometry Index.

Is DeepSeek-V2.5 (Sep 2024) or Gemma 2 9B better for coding?

DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.7 versus 29.4 in the Noometry coding category.

How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemma 2 9B share?

19 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemma 2 9B has 35.

Related comparisons

Go deeper