Noometry

Model comparison

Claude 3 Sonnet vs Gemma 2 9B

Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 25.9 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 8 categories and Gemma 2 9B in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude 3 Sonnet leads 21.1 to 9.7.
  • The biggest single-benchmark swing is BigCodeBench Complete: 53.8% for Claude 3 Sonnet and 40.6% for Gemma 2 9B.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetGemma 2 9B
ProviderAnthropicGoogle
Noometry Index29.025.9
Released2024-02-292024-06-24
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3035

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

Category by category

Coding Too close to call

Claude 3 Sonnet: 29.6 (#302), Gemma 2 9B: 29.4 (#304)

BenchmarkClaude 3 SonnetGemma 2 9B
BigCodeBench Instruct42.7%34.7%
LMArena Coding12231173
BigCodeBench Complete53.8%40.6%
WeirdML10.2%—
LiveBench Coding—22.5%
HumanEval+64%—
MBPP+69.3%—

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 20.5 (#237), Gemma 2 9B: 15.9 (#309)

BenchmarkClaude 3 SonnetGemma 2 9B
LMArena Hard Prompts11971171
Epoch Capabilities Index120.7119.83
LiveBench Reasoning—15.2%
DTBench53.6%—
LiveBench Data Analysis—36.4%
LiveBench—28.7%
PIQA—83.7%
WinoGrande75.1%—

Math Too close to call

Claude 3 Sonnet: 10.7 (#310), Gemma 2 9B: 9.9 (#318)

BenchmarkClaude 3 SonnetGemma 2 9B
OTIS Mock AIME 2024-20252.5%0.6%
LMArena Math12131183
MATH Level 518.2%21%
LiveBench Math—19.8%
GSM8K—84.9%

Knowledge Claude 3 Sonnet leads

Claude 3 Sonnet: 21.1 (#276), Gemma 2 9B: 9.7 (#305)

BenchmarkClaude 3 SonnetGemma 2 9B
GPQA Diamond40.6%27.5%
LMArena Expert11731147
MMLU75.9%72.1%
BoolQ—85.7%

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Gemma 2 9B: —

BenchmarkClaude 3 SonnetGemma 2 9B
LMArena Vision984—

Multilingual Claude 3 Sonnet leads

Claude 3 Sonnet: 37.8 (#234), Gemma 2 9B: 36.6 (#238)

BenchmarkClaude 3 SonnetGemma 2 9B
LMArena Non-English12051188
LMArena Chinese11891185
LMArena French12291190
LMArena German12041186
LMArena Japanese11311144
LMArena Korean11281137
LMArena Russian12271200
LMArena Spanish12041200

Instruction Following Claude 3 Sonnet leads

Claude 3 Sonnet: 62.8 (#235), Gemma 2 9B: 57.6 (#269)

BenchmarkClaude 3 SonnetGemma 2 9B
LMArena Instruction Following11991178
LiveBench Instruction Following—52.6%

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#228), Gemma 2 9B: 36.3 (#233)

BenchmarkClaude 3 SonnetGemma 2 9B
LMArena Longer Query12111197

Writing & Preference Claude 3 Sonnet leads

Claude 3 Sonnet: 42.1 (#238), Gemma 2 9B: 32.1 (#281)

BenchmarkClaude 3 SonnetGemma 2 9B
LMArena Text12181207
LMArena Creative Writing11861206
LMArena Multi-Turn12271193
EQ-Bench Creative Writing—841
LiveBench Language—25.5%

Frequently asked questions

Is Claude 3 Sonnet better than Gemma 2 9B?

Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 25.9 on the Noometry Index.

Is Claude 3 Sonnet or Gemma 2 9B better for coding?

They score almost the same on coding (29.6 vs 29.4); test both on your own repository before choosing.

How many benchmarks do Claude 3 Sonnet and Gemma 2 9B share?

24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemma 2 9B has 35.

Related comparisons

Go deeper