Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 1.8B/3.25B | 48B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 32k | 1M |
| Overview | ||
| Company | Moonshot AI | |
| Release date | Dec 6 2023 | Oct 30 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 1.0 NanovsClaude Haiku 5.5Kimi LinearvsClaude Haiku 5.5Gemini 1.0 NanovsGPT-6.1 SolKimi LinearvsGPT-6.1 SolGemini 1.0 NanovsMuse Spark OpenKimi LinearvsMuse Spark OpenGemini 1.0 NanovsGrok 4.7Kimi LinearvsGrok 4.7Gemini 1.0 NanovsDeepSeek-V4.1-Flash-1017Kimi LinearvsDeepSeek-V4.1-Flash-1017Gemini 1.0 NanovsMistral Large 4Kimi LinearvsMistral Large 4Frequently asked questions
Gemini 1.0 Nano and Kimi Linear don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemini 1.0 Nano shipped 694 days before Kimi Linear, so benchmark comparisons should account for the intervening progress.
Gemini 1.0 Nano has 1.8B/3.25B parameters, while Kimi Linear has 48B. Context windows are 32k (Gemini 1.0 Nano) vs 1M (Kimi Linear). Gemini 1.0 Nano is closed, while Kimi Linear is open weight.
Direct benchmark comparisons are unavailable — Gemini 1.0 Nano and Kimi Linear don't publish scores on any of the same benchmarks.