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. | 236B | — |
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 | 128k |
| These models have no shared benchmark scores. | ||
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 84.76% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 71.02% | — |
| Overview | ||
| Company | DeepSeek | Moonshot AI |
| Release date | Jun 28 2024 | Jan 20 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2-0628vsClaude Fable 5.2Kimi K1.5vsClaude Fable 5.2DeepSeek V2-0628vsGPT-6.2 AstraKimi K1.5vsGPT-6.2 AstraDeepSeek V2-0628vsGemini 4 HydrogenKimi K1.5vsGemini 4 HydrogenDeepSeek V2-0628vsMuse EmberKimi K1.5vsMuse EmberDeepSeek V2-0628vsGrok 4.7Kimi K1.5vsGrok 4.7DeepSeek V2-0628vsMistral Large 4Kimi K1.5vsMistral Large 4Frequently asked questions
DeepSeek V2-0628 and Kimi K1.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2-0628 shipped 206 days before Kimi K1.5, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek V2-0628) vs 128k (Kimi K1.5). DeepSeek V2-0628 is open weight, while Kimi K1.5 is closed.
Direct benchmark comparisons are unavailable — DeepSeek V2-0628 and Kimi K1.5 don't publish scores on any of the same benchmarks.