Noometry

Model comparison

Claude 3 Opus vs Gemma 2 27B

Claude 3 Opus and Gemma 2 27B score almost the same on the Noometry Index (29.5 vs 29.4), so choose on price, context window or the category you care about most.

Last verified . 34 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Gemma 2 27B Google

29.4

Rank #312 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude 3 Opus scores higher in 6 categories and Gemma 2 27B in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude 3 Opus leads 24.5 to 19.0.
  • The biggest single-benchmark swing is LiveBench Language: 50.4% for Claude 3 Opus and 32.6% for Gemma 2 27B.
  • Gemma 2 27B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusGemma 2 27B
ProviderAnthropicGoogle
Noometry Index29.529.4
Released2024-02-292024-06-24
WeightsProprietaryOpen
Context window—8K
Max output—2K
Input $ / M tokens—$0.65
Output $ / M tokens—$0.65
Results tracked4634

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

Category by category

Coding Gemma 2 27B leads

Claude 3 Opus: 32.9 (#267), Gemma 2 27B: 34.1 (#246)

BenchmarkClaude 3 OpusGemma 2 27B
BigCodeBench Instruct45.5%42.8%
LiveBench Coding38.6%36%
LMArena Coding12641211
BigCodeBench Complete57.4%52.5%
WeirdML19.2%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Gemma 2 27B: —

BenchmarkClaude 3 OpusGemma 2 27B
Cybench10%—
METR Time Horizons29.5%—

Reasoning Too close to call

Claude 3 Opus: 14.6 (#324), Gemma 2 27B: 15.3 (#315)

BenchmarkClaude 3 OpusGemma 2 27B
LiveBench Reasoning40.6%28.1%
LMArena Hard Prompts12451198
DTBench61.6%48%
LiveBench Data Analysis57.9%47.9%
LMCA17%7.1%
Epoch Capabilities Index126.91122.08
LiveBench49.2%38.2%
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
ForecastBench58.4—
WinoGrande88.5%—

Math Claude 3 Opus leads

Claude 3 Opus: 14.8 (#299), Gemma 2 27B: 10.7 (#311)

BenchmarkClaude 3 OpusGemma 2 27B
OTIS Mock AIME 2024-20254.7%1.4%
LiveBench Math43.6%26.5%
LMArena Math12731212
MATH Level 537.5%27.9%

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Gemma 2 27B: 19.0 (#280)

BenchmarkClaude 3 OpusGemma 2 27B
GPQA Diamond47.2%36.5%
Confabulations22.7%27.1%
LMArena Expert12231172
MMLU84.6%75.7%
SimpleQA Verified12.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Gemma 2 27B: —

BenchmarkClaude 3 OpusGemma 2 27B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Gemma 2 27B: 38.6 (#226)

BenchmarkClaude 3 OpusGemma 2 27B
LMArena Non-English12581217
LMArena Chinese12481221
LMArena French12751247
LMArena German12581209
LMArena Japanese12041175
LMArena Korean11871174
LMArena Russian12801234
LMArena Spanish12461228

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Gemma 2 27B: 60.5 (#249)

BenchmarkClaude 3 OpusGemma 2 27B
LiveBench Instruction Following63.9%58.1%
LMArena Instruction Following12481206

Long Context Too close to call

Claude 3 Opus: 38.2 (#202), Gemma 2 27B: 37.3 (#218)

BenchmarkClaude 3 OpusGemma 2 27B
LMArena Longer Query12591231

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Gemma 2 27B: 44.2 (#225)

BenchmarkClaude 3 OpusGemma 2 27B
LMArena Text12621231
LMArena Creative Writing12351241
LMArena Multi-Turn12751224
LiveBench Language50.4%32.6%

Frequently asked questions

Is Claude 3 Opus better than Gemma 2 27B?

Claude 3 Opus and Gemma 2 27B score almost the same on the Noometry Index (29.5 vs 29.4), so choose on price, context window or the category you care about most.

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

Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 32.9 in the Noometry coding category.

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

34 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemma 2 27B has 34.

Related comparisons

Go deeper