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 | 1.5B/7B/8B/14B/32B/70B |
| 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% | 57.5% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 86% | 70% |
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% | 65.2% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 94.5% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 76.3% | — |
| Overview | ||
| Company | DeepSeek | DeepSeek |
| Release date | May 29 2025 | Jan 20 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1-0528 Qwen3 8BvsClaude Fable 5.2DeepSeek R1 DistillvsClaude Fable 5.2DeepSeek R1-0528 Qwen3 8BvsGPT-6.2 AstraDeepSeek R1 DistillvsGPT-6.2 AstraDeepSeek R1-0528 Qwen3 8BvsGemini 4 HydrogenDeepSeek R1 DistillvsGemini 4 HydrogenDeepSeek R1-0528 Qwen3 8BvsMuse EmberDeepSeek R1 DistillvsMuse EmberDeepSeek R1-0528 Qwen3 8BvsGrok 4.7DeepSeek R1 DistillvsGrok 4.7DeepSeek R1-0528 Qwen3 8BvsMistral Large 4DeepSeek R1 DistillvsMistral Large 4Frequently asked questions
DeepSeek R1-0528 Qwen3 8B leads DeepSeek R1 Distill on 2 of the 3 benchmarks they both report (LiveCodeBench, AIME 2024, GPQA Diamond). DeepSeek R1 Distill shipped 129 days before DeepSeek R1-0528 Qwen3 8B, so benchmark comparisons should account for the intervening progress.
DeepSeek R1-0528 Qwen3 8B has 8B parameters, while DeepSeek R1 Distill has 1.5B/7B/8B/14B/32B/70B.
On LiveCodeBench, DeepSeek R1-0528 Qwen3 8B leads at 60.5% vs DeepSeek R1 Distill at 57.5%. On AIME 2024, DeepSeek R1-0528 Qwen3 8B leads at 86% vs DeepSeek R1 Distill at 70%. On GPQA Diamond, DeepSeek R1 Distill leads at 65.2% vs DeepSeek R1-0528 Qwen3 8B at 61.1%.