GPT-5.3-CodexvsQwen3.7-Plus

GPT-5.3-Codex
Qwen3.7-Plus
API pricing
Input price
$1.75$0.40
Output price
$14.00$1.60
Cached input price
$0.175
Cheapest input
$1.75Azure
Cheapest output
$14.00Azure
Benchmarks
SWE-Bench Verified
85%77.7%
OSWorld-Verified
64.7%73.3%
Benchmarks
BullshitBench v2
24%
Next.js Evals
81%
LiveCodeBench
89.6%
Humanity's Last Exam · with tools
34.7%
Overview
CompanyOpenAIQwen
Release dateFeb 5 2026Jun 1 2026
AccessProprietaryProprietary

Other comparisons

GPT-5.3-CodexvsClaude Opus 5Qwen3.7-PlusvsClaude Opus 5GPT-5.3-CodexvsGemini 3.7 FlashQwen3.7-PlusvsGemini 3.7 FlashGPT-5.3-CodexvsMuse GlimmerQwen3.7-PlusvsMuse GlimmerGPT-5.3-CodexvsGrok 4.6Qwen3.7-PlusvsGrok 4.6GPT-5.3-CodexvsDeepSeek-V4-Pro-0813Qwen3.7-PlusvsDeepSeek-V4-Pro-0813GPT-5.3-CodexvsMistral Medium 3.5Qwen3.7-PlusvsMistral Medium 3.5

Frequently asked questions

GPT-5.3-Codex and Qwen3.7-Plus are evenly matched across the 2 benchmarks they both report (SWE-Bench Verified, OSWorld-Verified). Qwen3.7-Plus is cheaper on both input and output: $0.40 vs $1.75 per million input tokens, and $1.60 vs $14.00 per million output tokens. Figures are base-tier rates. GPT-5.3-Codex shipped 116 days before Qwen3.7-Plus, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On SWE-Bench Verified, GPT-5.3-Codex leads at 85% vs Qwen3.7-Plus at 77.7%. On OSWorld-Verified, Qwen3.7-Plus leads at 73.3% vs GPT-5.3-Codex at 64.7%.

GPT-5.3-Codex was released by OpenAI on Feb 5 2026.

Qwen3.7-Plus was released by Qwen on Jun 1 2026.

GPT-5.3-Codex leads on SWE-Bench Verified — GPT-5.3-Codex 85% vs Qwen3.7-Plus 77.7%.

Qwen3.7-Plus is cheaper on both input and output: $0.40 vs $1.75 per million input tokens, and $1.60 vs $14.00 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on August 18, 2026.