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. | 1.5B/7B/8B/14B/32B/70B | — |
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 |
| Benchmarks | ||
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 57.5% | 62.5% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 94.5% | 96.2% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 70% | 77.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 65.2% | — |
| Overview | ||
| Company | DeepSeek | Moonshot AI |
| Release date | Jan 20 2025 | Jan 20 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek R1 DistillvsClaude Fable 5.2Kimi K1.5vsClaude Fable 5.2DeepSeek R1 DistillvsGPT-6.2 AstraKimi K1.5vsGPT-6.2 AstraDeepSeek R1 DistillvsGemini 4 HydrogenKimi K1.5vsGemini 4 HydrogenDeepSeek R1 DistillvsMuse EmberKimi K1.5vsMuse EmberDeepSeek R1 DistillvsGrok 4.7Kimi K1.5vsGrok 4.7DeepSeek R1 DistillvsMistral Large 4Kimi K1.5vsMistral Large 4Frequently asked questions
Kimi K1.5 leads DeepSeek R1 Distill on 3 of the 3 benchmarks they both report (LiveCodeBench, MATH-500, AIME 2024). Both models were released on the same day — Jan 20 2025.
DeepSeek R1 Distill is open weight, while Kimi K1.5 is closed.
On LiveCodeBench, Kimi K1.5 leads at 62.5% vs DeepSeek R1 Distill at 57.5%. On MATH-500, Kimi K1.5 leads at 96.2% vs DeepSeek R1 Distill at 94.5%. On AIME 2024, Kimi K1.5 leads at 77.5% vs DeepSeek R1 Distill at 70%.