Compare AI models

Specifications
Parameters
110B314B
Context window
32k8k
Benchmarks
HumanEval
52.4%63.2%
MATH
49.6%23.9%
MMLU
80.4%73%
GSM8K
85.4%62.9%
Overview
CompanyQwenSpaceXSI
Release dateApr 25 2024Nov 3 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads Grok‑1 on 3 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Grok‑1 shipped 174 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Qwen1.5-110B has 110B parameters, while Grok‑1 has 314B. Context windows are 32k (Qwen1.5-110B) vs 8k (Grok‑1).

On HumanEval, Grok‑1 leads at 63.2% vs Qwen1.5-110B at 52.4%. On MATH, Qwen1.5-110B leads at 49.6% vs Grok‑1 at 23.9%. On MMLU, Qwen1.5-110B leads at 80.4% vs Grok‑1 at 73%. On GSM8K, Qwen1.5-110B leads at 85.4% vs Grok‑1 at 62.9%.