Noometry

Model comparison

Codellama 70b Instruct vs Llama 3.1-405B

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.7 on the Noometry Index.

Last verified . 4 shared benchmarks.

Codellama 70b Instruct Meta

33.7

Rank #237 Confirmed

Llama 3.1-405B Meta

30.7

Rank #288 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Llama 3.1-405B in 3 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Llama 3.1-405B leads 40.7 to 24.8.

Side by side

Codellama 70b InstructLlama 3.1-405B
ProviderMetaMeta
Noometry Index33.730.7
Released—2024-07-23
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked742

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

Category by category

Coding Codellama 70b Instruct leads

Codellama 70b Instruct: 37.6 (#193), Llama 3.1-405B: 33.1 (#262)

BenchmarkCodellama 70b InstructLlama 3.1-405B
WeirdML—21.4%
BigCodeBench Instruct40.7%—
LMArena Coding—1291
BigCodeBench Complete49.6%—
HumanEval+65.9%—

Agentic & Tool Use Not comparable

Codellama 70b Instruct: —, Llama 3.1-405B: 21.0 (#140)

BenchmarkCodellama 70b InstructLlama 3.1-405B
TheAgentCompany—7.4%
Cybench—7.5%

Reasoning Codellama 70b Instruct leads

Codellama 70b Instruct: 20.1 (#242), Llama 3.1-405B: 16.8 (#300)

BenchmarkCodellama 70b InstructLlama 3.1-405B
LMArena Hard Prompts10521269
SimpleBench—23%
Kagi LLM Benchmark—45%
DTBench—61.4%
BIG-Bench Hard—82.9%
Epoch Capabilities Index—128.75
ForecastBench—59.9
HellaSwag—89.2%
PIQA—85.9%
WinoGrande—89.2%

Math Not comparable

Codellama 70b Instruct: —, Llama 3.1-405B: 18.4 (#290)

BenchmarkCodellama 70b InstructLlama 3.1-405B
OTIS Mock AIME 2024-2025—9.7%
Omni-MATH—24.9%
LMArena Math—1281
MATH Level 5—49.8%

Knowledge Not comparable

Codellama 70b Instruct: —, Llama 3.1-405B: 30.4 (#227)

BenchmarkCodellama 70b InstructLlama 3.1-405B
GPQA Diamond—50.9%
MMLU-Pro—72.3%
Confabulations—17.6%
GPQA (HELM)—52.2%
LMArena Expert—1243
ARC (AI2) Challenge—95.3%
MMLU—84.5%
TriviaQA—82.7%

Multilingual Llama 3.1-405B leads

Codellama 70b Instruct: 24.8 (#288), Llama 3.1-405B: 40.7 (#214)

BenchmarkCodellama 70b InstructLlama 3.1-405B
LMArena Non-English9921248
LMArena Chinese—1242
LMArena French—1279
LMArena German—1252
LMArena Japanese—1208
LMArena Korean—1184
LMArena Russian—1265
LMArena Spanish—1260

Instruction Following Llama 3.1-405B leads

Codellama 70b Instruct: 51.9 (#293), Llama 3.1-405B: 65.9 (#214)

BenchmarkCodellama 70b InstructLlama 3.1-405B
LMArena Instruction Following10241259
IFEval—81.1%

Long Context Not comparable

Codellama 70b Instruct: —, Llama 3.1-405B: 38.4 (#197)

BenchmarkCodellama 70b InstructLlama 3.1-405B
LMArena Longer Query—1266

Writing & Preference Llama 3.1-405B leads

Codellama 70b Instruct: 33.4 (#277), Llama 3.1-405B: 38.9 (#251)

BenchmarkCodellama 70b InstructLlama 3.1-405B
LMArena Text10571284
LMArena Creative Writing—1262
EQ-Bench Creative Writing—870
WildBench—78.3%
LMArena Multi-Turn—1297

Frequently asked questions

Is Codellama 70b Instruct better than Llama 3.1-405B?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.7 on the Noometry Index.

Is Codellama 70b Instruct or Llama 3.1-405B better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 33.1 in the Noometry coding category.

How many benchmarks do Codellama 70b Instruct and Llama 3.1-405B share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Llama 3.1-405B has 42.

Related comparisons

Go deeper