Noometry

Model comparison

Claude 3 Opus vs Llama 2-70B

Claude 3 Opus is the stronger model overall, scoring 29.5 to 24.4 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Opus scores higher in 8 categories and Llama 2-70B in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude 3 Opus leads 24.5 to 7.4.
  • The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 3.3% for Llama 2-70B.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusLlama 2-70B
ProviderAnthropicMeta
Noometry Index29.524.4
Released2024-02-292023-07-18
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), Llama 2-70B: 31.4 (#286)

BenchmarkClaude 3 OpusLlama 2-70B
LMArena Coding12641079
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Llama 2-70B: —

BenchmarkClaude 3 OpusLlama 2-70B
Cybench10%—
METR Time Horizons29.5%—

Reasoning Too close to call

Claude 3 Opus: 14.6 (#324), Llama 2-70B: 14.4 (#325)

BenchmarkClaude 3 OpusLlama 2-70B
LMArena Hard Prompts12451073
DTBench61.6%41.6%
Epoch Capabilities Index126.91113.79
ForecastBench58.451.4
WinoGrande88.5%80.2%
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
HellaSwag—85.3%
LAMBADA—78.9%
LiveBench49.2%—
PIQA—82.8%

Math Claude 3 Opus leads

Claude 3 Opus: 14.8 (#299), Llama 2-70B: 8.1 (#326)

BenchmarkClaude 3 OpusLlama 2-70B
OTIS Mock AIME 2024-20254.7%0%
LMArena Math12731091
MATH Level 537.5%3.3%
LiveBench Math43.6%—
GSM8K—69.6%

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Llama 2-70B: 7.4 (#310)

BenchmarkClaude 3 OpusLlama 2-70B
GPQA Diamond47.2%26.3%
LMArena Expert12231039
MMLU84.6%69.9%
SimpleQA Verified12.6%—
Confabulations22.7%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
OpenBookQA—60.2%
TriviaQA—87.6%

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Llama 2-70B: —

BenchmarkClaude 3 OpusLlama 2-70B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Llama 2-70B: 27.7 (#274)

BenchmarkClaude 3 OpusLlama 2-70B
LMArena Non-English12581045
LMArena Chinese1248995
LMArena French12751090
LMArena German12581041
LMArena Japanese1204927
LMArena Korean1187964
LMArena Russian12801083
LMArena Spanish12461143

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Llama 2-70B: 54.9 (#278)

BenchmarkClaude 3 OpusLlama 2-70B
LMArena Instruction Following12481071
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Llama 2-70B: 32.3 (#270)

BenchmarkClaude 3 OpusLlama 2-70B
LMArena Longer Query12591062

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Llama 2-70B: 32.3 (#279)

BenchmarkClaude 3 OpusLlama 2-70B
LMArena Text12621115
LMArena Creative Writing12351075
LMArena Multi-Turn12751088
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Llama 2-70B?

Claude 3 Opus is the stronger model overall, scoring 29.5 to 24.4 on the Noometry Index.

Is Claude 3 Opus or Llama 2-70B better for coding?

Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 31.4 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Llama 2-70B share?

25 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper