Llama 3.1 70B (Instruct)

Llama 3.1 70B (Instruct)

Llama 3.1 70B offers a dramatically expanded context window and improved performance on mathematical reasoning and general knowledge tasks.

ConversationReasoningCode Generation
Provider
Meta
Release Date
2024-07-23
Size
LARGE
Parameters
70B

Benchmark Performance

Performance metrics on industry standard AI benchmarks that measure capabilities across reasoning, knowledge, and specialized tasks.

MMLU

86.0%
View Source

GSM8K

95.1%
View Source

MATH

68.0%
View Source

HumanEval

80.5%
View Source

GPQA

46.7%
View Source

Model Insights

All Model Responses