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 | 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. | 128k | 1M |
| 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. | 88.7% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 30.6% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 35.9% |
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% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | — | 68.1% |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | — | 70.5% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 50.3% |
| Overview | ||
| Company | DeepSeek | |
| Release date | Dec 1 2025 | Oct 3 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-V3.2-SpecialevsClaude Fable 5.2Gemini 1.5 Flash-8BvsClaude Fable 5.2DeepSeek-V3.2-SpecialevsGPT-6.2 AstraGemini 1.5 Flash-8BvsGPT-6.2 AstraDeepSeek-V3.2-SpecialevsMuse EmberGemini 1.5 Flash-8BvsMuse EmberDeepSeek-V3.2-SpecialevsGrok 4.7Gemini 1.5 Flash-8BvsGrok 4.7DeepSeek-V3.2-SpecialevsMistral Large 4Gemini 1.5 Flash-8BvsMistral Large 4DeepSeek-V3.2-SpecialevsKimi K3.1 ProGemini 1.5 Flash-8BvsKimi K3.1 ProFrequently asked questions
DeepSeek-V3.2-Speciale and Gemini 1.5 Flash-8B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemini 1.5 Flash-8B shipped 424 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.
DeepSeek-V3.2-Speciale has 671B parameters, while Gemini 1.5 Flash-8B has 8B. Context windows are 128k (DeepSeek-V3.2-Speciale) vs 1M (Gemini 1.5 Flash-8B). DeepSeek-V3.2-Speciale is open weight, while Gemini 1.5 Flash-8B is closed.
Direct benchmark comparisons are unavailable — DeepSeek-V3.2-Speciale and Gemini 1.5 Flash-8B don't publish scores on any of the same benchmarks.