Compare AI models

Specifications
Parameters
—14.3B
Context window
128k32k
These models have no shared benchmark scores.
Overview
CompanyOpenAIQwen
Release dateFeb 12 2026Mar 28 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.3-Codex-Spark and Qwen1.5-MoE don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen1.5-MoE shipped 686 days before GPT-5.3-Codex-Spark, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (GPT-5.3-Codex-Spark) vs 32k (Qwen1.5-MoE). GPT-5.3-Codex-Spark is closed, while Qwen1.5-MoE is open weight.

Direct benchmark comparisons are unavailable — GPT-5.3-Codex-Spark and Qwen1.5-MoE don't publish scores on any of the same benchmarks.