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. | 8B | 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. | 128k | 1M |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | Oct 16 2024 | Oct 30 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Ministral 8BvsClaude Haiku 5.5Kimi LinearvsClaude Haiku 5.5Ministral 8BvsGPT-6.1 SolKimi LinearvsGPT-6.1 SolMinistral 8BvsGemini 4 ArgonKimi LinearvsGemini 4 ArgonMinistral 8BvsMuse Spark OpenKimi LinearvsMuse Spark OpenMinistral 8BvsGrok 4.7Kimi LinearvsGrok 4.7Ministral 8BvsDeepSeek-V4.1-Flash-1017Kimi LinearvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Ministral 8B and Kimi Linear don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Ministral 8B shipped 379 days before Kimi Linear, so benchmark comparisons should account for the intervening progress.
Ministral 8B has 8B parameters, while Kimi Linear has 48B. Context windows are 128k (Ministral 8B) vs 1M (Kimi Linear).
Direct benchmark comparisons are unavailable — Ministral 8B and Kimi Linear don't publish scores on any of the same benchmarks.