Noometry

Model comparison

Claude 3 Sonnet vs Llama 2-13B

Claude 3 Sonnet and Llama 2-13B score almost the same on the Noometry Index (29.0 vs 29.6), so choose on price, context window or the category you care about most.

Last verified . 21 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Llama 2-13B Meta

29.6

Rank #309 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Llama 2-13B in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Llama 2-13B leads 31.1 to 10.7.
  • The biggest single-benchmark swing is DTBench: 53.6% for Claude 3 Sonnet and 42.2% for Llama 2-13B.
  • Llama 2-13B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetLlama 2-13B
ProviderAnthropicMeta
Noometry Index29.029.6
Released2024-02-292023-07-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3032

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

Category by category

Coding Llama 2-13B leads

Claude 3 Sonnet: 29.6 (#302), Llama 2-13B: 30.9 (#291)

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Coding12231062
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 2-13B: 12.8 (#337)

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Hard Prompts11971051
DTBench53.6%42.2%
Epoch Capabilities Index120.7106.17
WinoGrande75.1%72.8%
Chess Puzzles—0%
BIG-Bench Hard—58.2%
HellaSwag—80.7%
LAMBADA—76.5%
PIQA—80.8%

Math Llama 2-13B leads

Claude 3 Sonnet: 10.7 (#310), Llama 2-13B: 31.1 (#229)

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Math12131065
OTIS Mock AIME 2024-20252.5%—
MATH Level 518.2%—
GSM8K—36.9%

Knowledge Llama 2-13B leads

Claude 3 Sonnet: 21.1 (#276), Llama 2-13B: 28.1 (#249)

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Expert11731030
MMLU75.9%55.6%
GPQA Diamond40.6%—
ARC (AI2) Challenge—60.3%
BoolQ—82.4%
OpenBookQA—57%
TriviaQA—79.6%

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Llama 2-13B: —

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Vision984—
ScienceQA—55.8%

Multilingual Claude 3 Sonnet leads

Claude 3 Sonnet: 37.8 (#234), Llama 2-13B: 26.5 (#279)

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Non-English12051024
LMArena Chinese11891001
LMArena French12291044
LMArena German12041009
LMArena Japanese1131894
LMArena Korean1128953
LMArena Russian12271055
LMArena Spanish12041087

Instruction Following Claude 3 Sonnet leads

Claude 3 Sonnet: 62.8 (#235), Llama 2-13B: 53.3 (#287)

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Instruction Following11991045

Long Context Claude 3 Sonnet leads

Claude 3 Sonnet: 36.7 (#228), Llama 2-13B: 32.3 (#269)

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Longer Query12111064

Writing & Preference Claude 3 Sonnet leads

Claude 3 Sonnet: 42.1 (#238), Llama 2-13B: 29.8 (#289)

BenchmarkClaude 3 SonnetLlama 2-13B
LMArena Text12181084
LMArena Creative Writing11861047
LMArena Multi-Turn12271050

Frequently asked questions

Is Claude 3 Sonnet better than Llama 2-13B?

Claude 3 Sonnet and Llama 2-13B score almost the same on the Noometry Index (29.0 vs 29.6), so choose on price, context window or the category you care about most.

Is Claude 3 Sonnet or Llama 2-13B better for coding?

Llama 2-13B scores higher on coding benchmarks: 30.9 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Llama 2-13B share?

21 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Llama 2-13B has 32.

Related comparisons

Go deeper