Compare AI models

Specifications
Parameters
70B110B
Context window
128k32k
Benchmarks
HellaSwag
87.61%87.5%
MMLU
83.8%80.4%
GSM8K
84.7%85.4%
Overview
CompanyNVIDIAQwen
Release dateOct 15 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama 3.1 Nemotron 70B leads Qwen1.5-110B on 2 of the 3 benchmarks they both report (HellaSwag, MMLU, GSM8K). Qwen1.5-110B shipped 173 days before Llama 3.1 Nemotron 70B, so benchmark comparisons should account for the intervening progress.

Llama 3.1 Nemotron 70B has 70B parameters, while Qwen1.5-110B has 110B. Context windows are 128k (Llama 3.1 Nemotron 70B) vs 32k (Qwen1.5-110B).

On HellaSwag, Llama 3.1 Nemotron 70B leads at 87.61% vs Qwen1.5-110B at 87.5%. On MMLU, Llama 3.1 Nemotron 70B leads at 83.8% vs Qwen1.5-110B at 80.4%. On GSM8K, Qwen1.5-110B leads at 85.4% vs Llama 3.1 Nemotron 70B at 84.7%.