Compare AI models

Specifications
Parameters
—110B
Context window
32k32k
Benchmarks
HumanEval
74.4%52.4%
MATH
53.2%49.6%
HellaSwag
87.8%87.5%
MMLU
83.7%80.4%
GSM8K
88.9%85.4%
Overview
CompanyGoogleQwen
Release dateFeb 8 2024Apr 25 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 1.0 Ultra leads Qwen1.5-110B on 5 of the 5 benchmarks they both report. Gemini 1.0 Ultra shipped 77 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Gemini 1.0 Ultra) vs 32k (Qwen1.5-110B). Gemini 1.0 Ultra is closed, while Qwen1.5-110B is open weight.

On HumanEval, Gemini 1.0 Ultra leads at 74.4% vs Qwen1.5-110B at 52.4%. On MATH, Gemini 1.0 Ultra leads at 53.2% vs Qwen1.5-110B at 49.6%. On HellaSwag, Gemini 1.0 Ultra leads at 87.8% vs Qwen1.5-110B at 87.5%. On MMLU, Gemini 1.0 Ultra leads at 83.7% vs Qwen1.5-110B at 80.4%. On GSM8K, Gemini 1.0 Ultra leads at 88.9% vs Qwen1.5-110B at 85.4%.