all the models — AI benchmark observatory
← Models

Llama 3.1 405B Instruct

Meta · open weight · llama-3.1-405b-instruct

Llama 3.1 405B Instruct is a large language model optimized for multilingual dialogue use cases. It outperforms many available open source and closed chat models on common industry benchmarks. The model supports 8 languages and has a 128K token context length.

ARC-CGSM8kMultilingualHumanEvalIFEvalMMLU (CoT)

Benchmark scores

BenchmarkScore
ARC-C0.97
GSM8k0.97
Multilingual MGSM (CoT)0.92
HumanEval0.89
IFEval0.89
MMLU (CoT)0.89
BFCL0.89
MMLU0.87
MATH0.74
MMLU-Pro0.73
GPQA0.51

Pricing

  • No provider pricing.

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.