Noometry

Model comparison

Claude 3 Sonnet vs Llama 3.1-405B

Llama 3.1-405B is the stronger model overall, scoring 30.4 to 28.8 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude 3 Sonnet Anthropic

28.8

Rank #311 Confirmed

Llama 3.1-405B Meta

30.4

Rank #279 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Sonnet scores higher in 2 categories and Llama 3.1-405B in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 21.1.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 49.8% for Llama 3.1-405B.
  • Llama 3.1-405B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetLlama 3.1-405B
ProviderAnthropicMeta
Noometry Index28.830.4
Released2024-02-292024-07-23
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3042

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

Category by category

Coding Llama 3.1-405B leads

Claude 3 Sonnet: 29.2 (#296), Llama 3.1-405B: 32.7 (#257)

BenchmarkClaude 3 SonnetLlama 3.1-405B
WeirdML10.2%21.4%
LMArena Coding12231291
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Llama 3.1-405B: 20.9 (#131)

BenchmarkClaude 3 SonnetLlama 3.1-405B
TheAgentCompany—7.4%
Cybench—7.5%

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 19.7 (#232), Llama 3.1-405B: 16.4 (#293)

BenchmarkClaude 3 SonnetLlama 3.1-405B
LMArena Hard Prompts11971270
DTBench53.6%61.4%
Epoch Capabilities Index120.69128.76
WinoGrande75.1%89.2%
SimpleBench—23%
Kagi LLM Benchmark—45%
BIG-Bench Hard—82.9%
ForecastBench—59.9
HellaSwag—89.2%
PIQA—85.9%

Math Llama 3.1-405B leads

Claude 3 Sonnet: 10.0 (#305), Llama 3.1-405B: 17.3 (#283)

BenchmarkClaude 3 SonnetLlama 3.1-405B
OTIS Mock AIME 2024-20252.5%9.7%
LMArena Math12131281
MATH Level 518.2%49.8%
Omni-MATH—24.9%

Knowledge Llama 3.1-405B leads

Claude 3 Sonnet: 21.1 (#271), Llama 3.1-405B: 30.4 (#221)

BenchmarkClaude 3 SonnetLlama 3.1-405B
GPQA Diamond40.6%50.9%
LMArena Expert11731243
MMLU75.9%84.5%
MMLU-Pro—72.3%
Confabulations—17.6%
GPQA (HELM)—52.2%
ARC (AI2) Challenge—95.3%
TriviaQA—82.7%

Multimodal Not comparable

Claude 3 Sonnet: 24.7 (#120), Llama 3.1-405B: —

BenchmarkClaude 3 SonnetLlama 3.1-405B
LMArena Vision984—

Multilingual Llama 3.1-405B leads

Claude 3 Sonnet: 38.0 (#229), Llama 3.1-405B: 40.9 (#209)

BenchmarkClaude 3 SonnetLlama 3.1-405B
LMArena Non-English12051248
LMArena Chinese11881242
LMArena French12281278
LMArena German12041252
LMArena Japanese11311208
LMArena Korean11281184
LMArena Russian12271265
LMArena Spanish12041259

Instruction Following Llama 3.1-405B leads

Claude 3 Sonnet: 63.1 (#230), Llama 3.1-405B: 66.1 (#209)

BenchmarkClaude 3 SonnetLlama 3.1-405B
LMArena Instruction Following12001259
IFEval—81.1%

Long Context Llama 3.1-405B leads

Claude 3 Sonnet: 36.7 (#223), Llama 3.1-405B: 38.4 (#192)

BenchmarkClaude 3 SonnetLlama 3.1-405B
LMArena Longer Query12111266

Writing & Preference Claude 3 Sonnet leads

Claude 3 Sonnet: 42.3 (#233), Llama 3.1-405B: 39.1 (#246)

BenchmarkClaude 3 SonnetLlama 3.1-405B
LMArena Text12181284
LMArena Creative Writing11861262
LMArena Multi-Turn12271297
EQ-Bench Creative Writing—870
WildBench—78.3%

Frequently asked questions

Is Claude 3 Sonnet better than Llama 3.1-405B?

Llama 3.1-405B is the stronger model overall, scoring 30.4 to 28.8 on the Noometry Index.

Is Claude 3 Sonnet or Llama 3.1-405B better for coding?

Llama 3.1-405B scores higher on coding benchmarks: 32.7 versus 29.2 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Llama 3.1-405B share?

25 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Llama 3.1-405B has 42.

Related comparisons

Go deeper