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. | 671B | — |
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 | 256k |
| 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. | 88.7% | 37.9% |
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. | — | 86.6% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 30.6% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 96% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 85.7% | — |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Dec 1 2025 | Jan 13 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-V3.2-SpecialevsClaude Fable 5.2Codestral 25.01vsClaude Fable 5.2DeepSeek-V3.2-SpecialevsGPT-6.2 AstraCodestral 25.01vsGPT-6.2 AstraDeepSeek-V3.2-SpecialevsGemini 4 HydrogenCodestral 25.01vsGemini 4 HydrogenDeepSeek-V3.2-SpecialevsMuse EmberCodestral 25.01vsMuse EmberDeepSeek-V3.2-SpecialevsGrok 4.7Codestral 25.01vsGrok 4.7DeepSeek-V3.2-SpecialevsKimi K3.1 ProCodestral 25.01vsKimi K3.1 ProFrequently asked questions
DeepSeek-V3.2-Speciale leads Codestral 25.01 on 1 of the 1 benchmark they both report (LiveCodeBench). Codestral 25.01 shipped 322 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek-V3.2-Speciale) vs 256k (Codestral 25.01). DeepSeek-V3.2-Speciale is open weight, while Codestral 25.01 is closed.
On LiveCodeBench, DeepSeek-V3.2-Speciale leads at 88.7% vs Codestral 25.01 at 37.9%.