Noometry

Model comparison

Claude 3 Sonnet vs Llama 2-70B

Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 24.4 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 7 categories and Llama 2-70B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude 3 Sonnet leads 21.1 to 7.4.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 3.3% for Llama 2-70B.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetLlama 2-70B
ProviderAnthropicMeta
Noometry Index29.024.4
Released2024-02-292023-07-18
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 Llama 2-70B leads

Claude 3 Sonnet: 29.6 (#302), Llama 2-70B: 31.4 (#286)

BenchmarkClaude 3 SonnetLlama 2-70B
LMArena Coding12231079
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 20.5 (#237), Llama 2-70B: 14.4 (#325)

BenchmarkClaude 3 SonnetLlama 2-70B
LMArena Hard Prompts11971073
DTBench53.6%41.6%
Epoch Capabilities Index120.7113.79
WinoGrande75.1%80.2%
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
PIQA—82.8%

Math Claude 3 Sonnet leads

Claude 3 Sonnet: 10.7 (#310), Llama 2-70B: 8.1 (#326)

BenchmarkClaude 3 SonnetLlama 2-70B
OTIS Mock AIME 2024-20252.5%0%
LMArena Math12131091
MATH Level 518.2%3.3%
GSM8K—69.6%

Knowledge Claude 3 Sonnet leads

Claude 3 Sonnet: 21.1 (#276), Llama 2-70B: 7.4 (#310)

BenchmarkClaude 3 SonnetLlama 2-70B
GPQA Diamond40.6%26.3%
LMArena Expert11731039
MMLU75.9%69.9%
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
OpenBookQA—60.2%
TriviaQA—87.6%

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Llama 2-70B: —

BenchmarkClaude 3 SonnetLlama 2-70B
LMArena Vision984—

Multilingual Claude 3 Sonnet leads

Claude 3 Sonnet: 37.8 (#234), Llama 2-70B: 27.7 (#274)

BenchmarkClaude 3 SonnetLlama 2-70B
LMArena Non-English12051045
LMArena Chinese1189995
LMArena French12291090
LMArena German12041041
LMArena Japanese1131927
LMArena Korean1128964
LMArena Russian12271083
LMArena Spanish12041143

Instruction Following Claude 3 Sonnet leads

Claude 3 Sonnet: 62.8 (#235), Llama 2-70B: 54.9 (#278)

BenchmarkClaude 3 SonnetLlama 2-70B
LMArena Instruction Following11991071

Long Context Claude 3 Sonnet leads

Claude 3 Sonnet: 36.7 (#228), Llama 2-70B: 32.3 (#270)

BenchmarkClaude 3 SonnetLlama 2-70B
LMArena Longer Query12111062

Writing & Preference Claude 3 Sonnet leads

Claude 3 Sonnet: 42.1 (#238), Llama 2-70B: 32.3 (#279)

BenchmarkClaude 3 SonnetLlama 2-70B
LMArena Text12181115
LMArena Creative Writing11861075
LMArena Multi-Turn12271088

Frequently asked questions

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

Claude 3 Sonnet is the stronger model overall, scoring 29.0 to 24.4 on the Noometry Index.

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

Llama 2-70B scores higher on coding benchmarks: 31.4 versus 29.6 in the Noometry coding category.

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

24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper