Compare AI models
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 128k | 128k |
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Jan 20 2025 | Feb 12 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K1.5vsClaude Haiku 5.5GPT-5.3-Codex-SparkvsClaude Haiku 5.5Kimi K1.5vsGemini 4 ArgonGPT-5.3-Codex-SparkvsGemini 4 ArgonKimi K1.5vsMuse WonderGPT-5.3-Codex-SparkvsMuse WonderKimi K1.5vsGrok 4.7GPT-5.3-Codex-SparkvsGrok 4.7Kimi K1.5vsDeepSeek-V4.1-FlashGPT-5.3-Codex-SparkvsDeepSeek-V4.1-FlashKimi K1.5vsMistral Large 4GPT-5.3-Codex-SparkvsMistral Large 4Frequently asked questions
Kimi K1.5 and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi K1.5 shipped 388 days before GPT-5.3-Codex-Spark, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Kimi K1.5) vs 128k (GPT-5.3-Codex-Spark).
Direct benchmark comparisons are unavailable — Kimi K1.5 and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks.