Compare AI models

Specifications
Parameters
—8B
Context window
200k8k
Benchmarks
HumanEval
73%36.22%
MMLU
81.5%69.51%
GSM8K
92.3%58.45%
Overview
CompanyAnthropicNVIDIA
Release dateMar 4 2024Aug 21 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3 Sonnet leads Mistral NeMo Minitron 8B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Claude 3 Sonnet shipped 170 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Sonnet) vs 8k (Mistral NeMo Minitron 8B). Claude 3 Sonnet is closed, while Mistral NeMo Minitron 8B is open weight.

On HumanEval, Claude 3 Sonnet leads at 73% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, Claude 3 Sonnet leads at 81.5% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, Claude 3 Sonnet leads at 92.3% vs Mistral NeMo Minitron 8B at 58.45%.