Kimi K2 vs GPT-5-Codex
Moonshot AI Kimi K2 | OpenAI GPT-5-Codex | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Jul 11 2025 | Sep 15 2025 |
| Access | Open Weight | Proprietary |
| Specifications | ||
Parameters | 1T | — |
Context window | 128k | — |
| 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. | 10% | 39%Best |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 65.8% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 75.1% | — |
| Timeline | ||
| Release gap | Kimi K2 shipped 66 days before GPT-5-Codex | |
Which is better: Kimi K2 or GPT-5-Codex?
GPT-5-Codex leads Kimi K2 on 1 of the 1 benchmark they both report (BullshitBench v2). Kimi K2 shipped 66 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.
Kimi K2 is open weight, while GPT-5-Codex is proprietary.
On BullshitBench v2, GPT-5-Codex leads at 39% vs Kimi K2 at 10%.
Frequently asked questions
Kimi K2 was released by Moonshot AI on Jul 11 2025.
GPT-5-Codex was released by OpenAI on Sep 15 2025.
Kimi K2 is an open weight model released by Moonshot AI. GPT-5-Codex is a proprietary model released by OpenAI.
Other comparisons
Kimi K2 vs Claude Sonnet 5GPT-5-Codex vs Claude Sonnet 5Kimi K2 vs Gemini OmniGPT-5-Codex vs Gemini OmniKimi K2 vs Muse Spark 1.1GPT-5-Codex vs Muse Spark 1.1Kimi K2 vs Grok 4.5GPT-5-Codex vs Grok 4.5Kimi K2 vs DeepSeek-V4-ProGPT-5-Codex vs DeepSeek-V4-ProKimi K2 vs Mistral Medium 3.5GPT-5-Codex vs Mistral Medium 3.5