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. | — | 1M |
| 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% | 28.9% |
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% | 51.5% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 12.5% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 94.5% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 70% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | — | 21.7% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 71.6% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 68% |
| Overview | ||
| Company | DeepSeek | |
| Release date | Jan 20 2025 | Feb 5 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek R1 DistillvsClaude Fable 5.2Gemini 2.0 Flash-LitevsClaude Fable 5.2DeepSeek R1 DistillvsGPT-6.2 AstraGemini 2.0 Flash-LitevsGPT-6.2 AstraDeepSeek R1 DistillvsMuse EmberGemini 2.0 Flash-LitevsMuse EmberDeepSeek R1 DistillvsGrok 4.7Gemini 2.0 Flash-LitevsGrok 4.7DeepSeek R1 DistillvsMistral Large 4Gemini 2.0 Flash-LitevsMistral Large 4DeepSeek R1 DistillvsKimi K3.1 ProGemini 2.0 Flash-LitevsKimi K3.1 ProFrequently asked questions
DeepSeek R1 Distill leads Gemini 2.0 Flash-Lite on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek R1 Distill shipped 16 days before Gemini 2.0 Flash-Lite, so benchmark comparisons should account for the intervening progress.
DeepSeek R1 Distill is open weight, while Gemini 2.0 Flash-Lite is closed.
On LiveCodeBench, DeepSeek R1 Distill leads at 57.5% vs Gemini 2.0 Flash-Lite at 28.9%. On GPQA Diamond, DeepSeek R1 Distill leads at 65.2% vs Gemini 2.0 Flash-Lite at 51.5%.