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 | 24B |
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. | — | 128k |
| 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% | 70.88% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 86% | 86.14% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 76.3% | 77.34% |
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% | 70.07% |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | May 29 2025 | Sep 17 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1-0528 Qwen3 8BvsClaude Fable 5.2Magistral Small 1.2vsClaude Fable 5.2DeepSeek R1-0528 Qwen3 8BvsGPT-6.2 AstraMagistral Small 1.2vsGPT-6.2 AstraDeepSeek R1-0528 Qwen3 8BvsGemini 4 HydrogenMagistral Small 1.2vsGemini 4 HydrogenDeepSeek R1-0528 Qwen3 8BvsMuse EmberMagistral Small 1.2vsMuse EmberDeepSeek R1-0528 Qwen3 8BvsGrok 4.7Magistral Small 1.2vsGrok 4.7DeepSeek R1-0528 Qwen3 8BvsKimi K3.1 ProMagistral Small 1.2vsKimi K3.1 ProFrequently asked questions
Magistral Small 1.2 leads DeepSeek R1-0528 Qwen3 8B on 4 of the 4 benchmarks they both report (LiveCodeBench, AIME 2024, AIME 2025, GPQA Diamond). DeepSeek R1-0528 Qwen3 8B shipped 111 days before Magistral Small 1.2, so benchmark comparisons should account for the intervening progress.
DeepSeek R1-0528 Qwen3 8B has 8B parameters, while Magistral Small 1.2 has 24B.
On LiveCodeBench, Magistral Small 1.2 leads at 70.88% vs DeepSeek R1-0528 Qwen3 8B at 60.5%. On AIME 2024, Magistral Small 1.2 leads at 86.14% vs DeepSeek R1-0528 Qwen3 8B at 86%. On AIME 2025, Magistral Small 1.2 leads at 77.34% vs DeepSeek R1-0528 Qwen3 8B at 76.3%. On GPQA Diamond, Magistral Small 1.2 leads at 70.07% vs DeepSeek R1-0528 Qwen3 8B at 61.1%.