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. | 1.3B/5.7B/6.7B/33B | 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. | 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. | — | 60.5% |
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. | 79.3% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 86% |
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 | DeepSeek |
| Release date | Nov 2 2023 | May 29 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek CodervsClaude Fable 5.2DeepSeek R1-0528 Qwen3 8BvsClaude Fable 5.2DeepSeek CodervsGPT-6.2 AstraDeepSeek R1-0528 Qwen3 8BvsGPT-6.2 AstraDeepSeek CodervsGemini 4 HydrogenDeepSeek R1-0528 Qwen3 8BvsGemini 4 HydrogenDeepSeek CodervsMuse EmberDeepSeek R1-0528 Qwen3 8BvsMuse EmberDeepSeek CodervsGrok 4.7DeepSeek R1-0528 Qwen3 8BvsGrok 4.7DeepSeek CodervsMistral Large 4DeepSeek R1-0528 Qwen3 8BvsMistral Large 4Frequently asked questions
DeepSeek Coder and DeepSeek R1-0528 Qwen3 8B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek Coder shipped 574 days before DeepSeek R1-0528 Qwen3 8B, so benchmark comparisons should account for the intervening progress.
DeepSeek Coder has 1.3B/5.7B/6.7B/33B parameters, while DeepSeek R1-0528 Qwen3 8B has 8B.
Direct benchmark comparisons are unavailable — DeepSeek Coder and DeepSeek R1-0528 Qwen3 8B don't publish scores on any of the same benchmarks.