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 | 22B |
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. | — | 32k |
| 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% | 31.5% |
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. | — | 81.1% |
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 | Mistral |
| Release date | May 29 2025 | May 29 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1-0528 Qwen3 8BvsClaude Fable 5.2Codestral 22BvsClaude Fable 5.2DeepSeek R1-0528 Qwen3 8BvsGPT-6.2 AstraCodestral 22BvsGPT-6.2 AstraDeepSeek R1-0528 Qwen3 8BvsGemini 4 HydrogenCodestral 22BvsGemini 4 HydrogenDeepSeek R1-0528 Qwen3 8BvsMuse EmberCodestral 22BvsMuse EmberDeepSeek R1-0528 Qwen3 8BvsGrok 4.7Codestral 22BvsGrok 4.7DeepSeek R1-0528 Qwen3 8BvsKimi K3.1 ProCodestral 22BvsKimi K3.1 ProFrequently asked questions
DeepSeek R1-0528 Qwen3 8B leads Codestral 22B on 1 of the 1 benchmark they both report (LiveCodeBench). Codestral 22B shipped 365 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 Codestral 22B has 22B.
On LiveCodeBench, DeepSeek R1-0528 Qwen3 8B leads at 60.5% vs Codestral 22B at 31.5%.