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 | — |
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. | 60.5% | 62.5% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 86% | 77.5% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 96.2% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 76.3% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 61.1% | — |
| Overview | ||
| Company | DeepSeek | Moonshot AI |
| Release date | May 29 2025 | Jan 20 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek R1-0528 Qwen3 8BvsClaude Fable 5.2Kimi K1.5vsClaude Fable 5.2DeepSeek R1-0528 Qwen3 8BvsGPT-6.2 AstraKimi K1.5vsGPT-6.2 AstraDeepSeek R1-0528 Qwen3 8BvsGemini 4 HydrogenKimi K1.5vsGemini 4 HydrogenDeepSeek R1-0528 Qwen3 8BvsMuse EmberKimi K1.5vsMuse EmberDeepSeek R1-0528 Qwen3 8BvsGrok 4.7Kimi K1.5vsGrok 4.7DeepSeek R1-0528 Qwen3 8BvsMistral Large 4Kimi K1.5vsMistral Large 4Frequently asked questions
DeepSeek R1-0528 Qwen3 8B and Kimi K1.5 are evenly matched across the 2 benchmarks they both report (LiveCodeBench, AIME 2024). Kimi K1.5 shipped 129 days before DeepSeek R1-0528 Qwen3 8B, so benchmark comparisons should account for the intervening progress.
DeepSeek R1-0528 Qwen3 8B is open weight, while Kimi K1.5 is closed.
On LiveCodeBench, Kimi K1.5 leads at 62.5% vs DeepSeek R1-0528 Qwen3 8B at 60.5%. On AIME 2024, DeepSeek R1-0528 Qwen3 8B leads at 86% vs Kimi K1.5 at 77.5%.