Noometry

Model comparison

Claude 3 Sonnet vs Gemma 2 27B

Claude 3 Sonnet and Gemma 2 27B score almost the same on the Noometry Index (29.0 vs 29.4), so choose on price, context window or the category you care about most.

Last verified . 25 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Gemma 2 27B Google

29.4

Rank #312 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Sonnet scores higher in 4 categories and Gemma 2 27B in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude 3 Sonnet leads 20.5 to 15.3.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 27.9% for Gemma 2 27B.
  • Gemma 2 27B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetGemma 2 27B
ProviderAnthropicGoogle
Noometry Index29.029.4
Released2024-02-292024-06-24
WeightsProprietaryOpen
Context window—8K
Max output—2K
Input $ / M tokens—$0.65
Output $ / M tokens—$0.65
Results tracked3034

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

Category by category

Coding Gemma 2 27B leads

Claude 3 Sonnet: 29.6 (#302), Gemma 2 27B: 34.1 (#246)

BenchmarkClaude 3 SonnetGemma 2 27B
BigCodeBench Instruct42.7%42.8%
LMArena Coding12231211
BigCodeBench Complete53.8%52.5%
WeirdML10.2%—
LiveBench Coding—36%
HumanEval+64%—
MBPP+69.3%—

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 20.5 (#237), Gemma 2 27B: 15.3 (#315)

BenchmarkClaude 3 SonnetGemma 2 27B
LMArena Hard Prompts11971198
DTBench53.6%48%
Epoch Capabilities Index120.7122.08
LiveBench Reasoning—28.1%
LiveBench Data Analysis—47.9%
LMCA—7.1%
LiveBench—38.2%
WinoGrande75.1%—

Math Too close to call

Claude 3 Sonnet: 10.7 (#310), Gemma 2 27B: 10.7 (#311)

BenchmarkClaude 3 SonnetGemma 2 27B
OTIS Mock AIME 2024-20252.5%1.4%
LMArena Math12131212
MATH Level 518.2%27.9%
LiveBench Math—26.5%

Knowledge Claude 3 Sonnet leads

Claude 3 Sonnet: 21.1 (#276), Gemma 2 27B: 19.0 (#280)

BenchmarkClaude 3 SonnetGemma 2 27B
GPQA Diamond40.6%36.5%
LMArena Expert11731172
MMLU75.9%75.7%
Confabulations—27.1%

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Gemma 2 27B: —

BenchmarkClaude 3 SonnetGemma 2 27B
LMArena Vision984—

Multilingual Too close to call

Claude 3 Sonnet: 37.8 (#234), Gemma 2 27B: 38.6 (#226)

BenchmarkClaude 3 SonnetGemma 2 27B
LMArena Non-English12051217
LMArena Chinese11891221
LMArena French12291247
LMArena German12041209
LMArena Japanese11311175
LMArena Korean11281174
LMArena Russian12271234
LMArena Spanish12041228

Instruction Following Claude 3 Sonnet leads

Claude 3 Sonnet: 62.8 (#235), Gemma 2 27B: 60.5 (#249)

BenchmarkClaude 3 SonnetGemma 2 27B
LMArena Instruction Following11991206
LiveBench Instruction Following—58.1%

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#228), Gemma 2 27B: 37.3 (#218)

BenchmarkClaude 3 SonnetGemma 2 27B
LMArena Longer Query12111231

Writing & Preference Gemma 2 27B leads

Claude 3 Sonnet: 42.1 (#238), Gemma 2 27B: 44.2 (#225)

BenchmarkClaude 3 SonnetGemma 2 27B
LMArena Text12181231
LMArena Creative Writing11861241
LMArena Multi-Turn12271224
LiveBench Language—32.6%

Frequently asked questions

Is Claude 3 Sonnet better than Gemma 2 27B?

Claude 3 Sonnet and Gemma 2 27B score almost the same on the Noometry Index (29.0 vs 29.4), so choose on price, context window or the category you care about most.

Is Claude 3 Sonnet or Gemma 2 27B better for coding?

Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Gemma 2 27B share?

25 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemma 2 27B has 34.

Related comparisons

Go deeper