GPT-5-CodexvsQwen3-Coder
GPT-5-Codex | Qwen3-Coder | |
|---|---|---|
| Specifications | ||
Parameters | — | 480B |
Context window | — | 256k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 39%Best | 20% |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Sep 15 2025 | Jul 22 2025 |
| Access | Proprietary | Open Weight |
Which is better: GPT-5-Codex or Qwen3-Coder?
GPT-5-Codex leads Qwen3-Coder on 1 of the 1 benchmark they both report (BullshitBench v2). Qwen3-Coder shipped 55 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.
GPT-5-Codex is proprietary, while Qwen3-Coder is open weight.
On BullshitBench v2, GPT-5-Codex leads at 39% vs Qwen3-Coder at 20%.
Frequently asked questions
GPT-5-Codex was released by OpenAI on Sep 15 2025.
Qwen3-Coder was released by Qwen on Jul 22 2025.
GPT-5-Codex is a proprietary model released by OpenAI. Qwen3-Coder is an open weight model released by Qwen.
Other comparisons
GPT-5-CodexvsClaude Opus 5Qwen3-CodervsClaude Opus 5GPT-5-CodexvsGemini 3.6 FlashQwen3-CodervsGemini 3.6 FlashGPT-5-CodexvsMuse Spark 1.2Qwen3-CodervsMuse Spark 1.2GPT-5-CodexvsGrok 4.5Qwen3-CodervsGrok 4.5GPT-5-CodexvsDeepSeek-V4-Flash-0731Qwen3-CodervsDeepSeek-V4-Flash-0731GPT-5-CodexvsMistral Medium 3.5Qwen3-CodervsMistral Medium 3.5