Compare AI models

Specifications
Parameters
7B/14B—
Context window
1M128k
Benchmarks
HumanEval
88.4%74.1%
MATH
79.5%50.6%
MMLU-Pro
63.3%51%
GSM8K
94.8%90%
Overview
CompanyQwenSpaceXSI
Release dateJan 27 2025Mar 28 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads Grok‑1.5 on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU-Pro, GSM8K). Grok‑1.5 shipped 305 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Qwen2.5-1M) vs 128k (Grok‑1.5). Qwen2.5-1M is open weight, while Grok‑1.5 is closed.

On HumanEval, Qwen2.5-1M leads at 88.4% vs Grok‑1.5 at 74.1%. On MATH, Qwen2.5-1M leads at 79.5% vs Grok‑1.5 at 50.6%. On MMLU-Pro, Qwen2.5-1M leads at 63.3% vs Grok‑1.5 at 51%. On GSM8K, Qwen2.5-1M leads at 94.8% vs Grok‑1.5 at 90%.