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 | 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. | — | 16k |
| These models have no shared benchmark scores. | ||
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% | — |
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. | — | 53% |
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% | — |
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 | Meta |
| Release date | Jan 20 2025 | Jan 29 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1 DistillvsClaude Fable 5.2Code Llama 70BvsClaude Fable 5.2DeepSeek R1 DistillvsGPT-6.2 AstraCode Llama 70BvsGPT-6.2 AstraDeepSeek R1 DistillvsGemini 4 HydrogenCode Llama 70BvsGemini 4 HydrogenDeepSeek R1 DistillvsGrok 4.7Code Llama 70BvsGrok 4.7DeepSeek R1 DistillvsMistral Large 4Code Llama 70BvsMistral Large 4DeepSeek R1 DistillvsKimi K3.1 ProCode Llama 70BvsKimi K3.1 ProFrequently asked questions
DeepSeek R1 Distill and Code Llama 70B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Code Llama 70B shipped 357 days before DeepSeek R1 Distill, so benchmark comparisons should account for the intervening progress.
DeepSeek R1 Distill has 1.5B/7B/8B/14B/32B/70B parameters, while Code Llama 70B has 70B.
Direct benchmark comparisons are unavailable — DeepSeek R1 Distill and Code Llama 70B don't publish scores on any of the same benchmarks.