Kimi K2.5 vs GPT-5.2-Codex
Kimi K2.5 is cheaper on output tokens, while GPT-5.2-Codex offers a larger context window. Choose Kimi K2.5 or GPT-5.2-Codex based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Kimi K2.5 | GPT-5.2-Codex |
|---|---|---|
| Provider | MoonshotAI | OpenAI |
| Input / 1M tokens | $0.50 | $1.75 |
| Output / 1M tokens | $2.50 | $14.00 |
| Context window | 262K | 400K |
| Parameters | 1T | — |
| Open weights | Yes | No |
| Released | Jan 2026 | Dec 2025 |
| LiveBench score | 69.2 | 74.3 |
| LMArena (Chatbot Arena) Elo score | 1445 | — |
| LMArena WebDev Elo score | 1437 | 1339 |
| LMArena Vision Elo score | 1269 | — |
| Epoch Capabilities Index score | 148 | — |
| SWE-bench Multilingual score | 67.3 | 66.3 |
| SWE-bench Verified score | 70.8 | 72.8 |
FAQ
Is Kimi K2.5 or GPT-5.2-Codex cheaper?
Kimi K2.5 is cheaper on output tokens ($2.50 vs $14.00 per 1M).
Which has the larger context window, Kimi K2.5 or GPT-5.2-Codex?
GPT-5.2-Codex has the larger context window (400K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.