Noometry

Model comparison

Claude 3 Opus vs Gemma 2 9B

Claude 3 Opus is the stronger model overall, scoring 29.5 to 25.9 on the Noometry Index.

Last verified . 31 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Claude 3 Opus scores higher in 7 categories and Gemma 2 9B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude 3 Opus leads 47.2 to 32.1.
  • The biggest single-benchmark swing is LiveBench Reasoning: 40.6% for Claude 3 Opus and 15.2% for Gemma 2 9B.
  • Gemma 2 9B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusGemma 2 9B
ProviderAnthropicGoogle
Noometry Index29.525.9
Released2024-02-292024-06-24
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4635

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

Category by category

Coding Claude 3 Opus leads

Claude 3 Opus: 32.9 (#267), Gemma 2 9B: 29.4 (#304)

BenchmarkClaude 3 OpusGemma 2 9B
BigCodeBench Instruct45.5%34.7%
LiveBench Coding38.6%22.5%
LMArena Coding12641173
BigCodeBench Complete57.4%40.6%
WeirdML19.2%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Gemma 2 9B: —

BenchmarkClaude 3 OpusGemma 2 9B
Cybench10%—
METR Time Horizons29.5%—

Reasoning Gemma 2 9B leads

Claude 3 Opus: 14.6 (#324), Gemma 2 9B: 15.9 (#309)

BenchmarkClaude 3 OpusGemma 2 9B
LiveBench Reasoning40.6%15.2%
LMArena Hard Prompts12451171
LiveBench Data Analysis57.9%36.4%
Epoch Capabilities Index126.91119.83
LiveBench49.2%28.7%
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
DTBench61.6%—
LMCA17%—
ForecastBench58.4—
PIQA—83.7%
WinoGrande88.5%—

Math Claude 3 Opus leads

Claude 3 Opus: 14.8 (#299), Gemma 2 9B: 9.9 (#318)

BenchmarkClaude 3 OpusGemma 2 9B
OTIS Mock AIME 2024-20254.7%0.6%
LiveBench Math43.6%19.8%
LMArena Math12731183
MATH Level 537.5%21%
GSM8K—84.9%

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Gemma 2 9B: 9.7 (#305)

BenchmarkClaude 3 OpusGemma 2 9B
GPQA Diamond47.2%27.5%
LMArena Expert12231147
MMLU84.6%72.1%
SimpleQA Verified12.6%—
Confabulations22.7%—
BoolQ—85.7%

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Gemma 2 9B: —

BenchmarkClaude 3 OpusGemma 2 9B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Gemma 2 9B: 36.6 (#238)

BenchmarkClaude 3 OpusGemma 2 9B
LMArena Non-English12581188
LMArena Chinese12481185
LMArena French12751190
LMArena German12581186
LMArena Japanese12041144
LMArena Korean11871137
LMArena Russian12801200
LMArena Spanish12461200

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Gemma 2 9B: 57.6 (#269)

BenchmarkClaude 3 OpusGemma 2 9B
LiveBench Instruction Following63.9%52.6%
LMArena Instruction Following12481178

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Gemma 2 9B: 36.3 (#233)

BenchmarkClaude 3 OpusGemma 2 9B
LMArena Longer Query12591197

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Gemma 2 9B: 32.1 (#281)

BenchmarkClaude 3 OpusGemma 2 9B
LMArena Text12621207
LMArena Creative Writing12351206
LMArena Multi-Turn12751193
LiveBench Language50.4%25.5%
EQ-Bench Creative Writing—841

Frequently asked questions

Is Claude 3 Opus better than Gemma 2 9B?

Claude 3 Opus is the stronger model overall, scoring 29.5 to 25.9 on the Noometry Index.

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

Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 29.4 in the Noometry coding category.

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

31 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemma 2 9B has 35.

Related comparisons

Go deeper