GPT-4vsQwen2

GPT-4
Qwen2
Specifications
Parameters
72B
Context window
8k
128k
Benchmarks
Function synthesis
HumanEval
67%
General knowledge
MMLU
86.4%
Grade-school math
GSM8K
92%
Overview
CompanyOpenAIQwen
Release dateMar 14 2023Jun 6 2024
AccessProprietaryOpen Weight

Which is better: GPT-4 or Qwen2?

GPT-4 and Qwen2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-4 shipped 450 days before Qwen2, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (GPT-4) vs 128k (Qwen2). GPT-4 is proprietary, while Qwen2 is open weight.

Direct benchmark comparisons are unavailable — GPT-4 and Qwen2 don't publish scores on any of the same benchmarks.

Frequently asked questions

GPT-4 was released by OpenAI on Mar 14 2023.

Qwen2 was released by Qwen on Jun 6 2024.

GPT-4 has a 8k context window; Qwen2 has 128k.

GPT-4 is a proprietary model released by OpenAI. Qwen2 is an open weight model released by Qwen.

Other comparisons