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 | 0.5B/1.5B/7B/57B/72B |
| 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% | — |
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 | Qwen |
| Release date | Jan 20 2025 | Jun 6 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1 DistillvsClaude Fable 5.2Qwen2vsClaude Fable 5.2DeepSeek R1 DistillvsGPT-6.2 AstraQwen2vsGPT-6.2 AstraDeepSeek R1 DistillvsGemini 4 HydrogenQwen2vsGemini 4 HydrogenDeepSeek R1 DistillvsMuse EmberQwen2vsMuse EmberDeepSeek R1 DistillvsGrok 4.7Qwen2vsGrok 4.7DeepSeek R1 DistillvsMistral Large 4Qwen2vsMistral Large 4Frequently asked questions
DeepSeek R1 Distill and Qwen2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2 shipped 228 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 Qwen2 has 0.5B/1.5B/7B/57B/72B.
Direct benchmark comparisons are unavailable — DeepSeek R1 Distill and Qwen2 don't publish scores on any of the same benchmarks.