Compare AI models

Specifications
Parameters
—1.5B/7B/72B
Context window
200k4k
These models have no shared benchmark scores.
Overview
CompanyOpenAIQwen
Release dateMay 16 2025Aug 8 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

codex-mini-latest and Qwen2-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2-Math shipped 281 days before codex-mini-latest, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (codex-mini-latest) vs 4k (Qwen2-Math). codex-mini-latest is closed, while Qwen2-Math is open weight.

Direct benchmark comparisons are unavailable — codex-mini-latest and Qwen2-Math don't publish scores on any of the same benchmarks.