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 | 1.5B/7B/72B |
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 | 4k |
| 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 | — | 84% |
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% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 96.7% |
| Overview | ||
| Company | DeepSeek | Qwen |
| Release date | Dec 1 2025 | Aug 8 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V3.2-SpecialevsClaude Fable 5.2Qwen2-MathvsClaude Fable 5.2DeepSeek-V3.2-SpecialevsGPT-6.2 AstraQwen2-MathvsGPT-6.2 AstraDeepSeek-V3.2-SpecialevsGemini 4 NeonQwen2-MathvsGemini 4 NeonDeepSeek-V3.2-SpecialevsMuse EmberQwen2-MathvsMuse EmberDeepSeek-V3.2-SpecialevsGrok 4.7Qwen2-MathvsGrok 4.7DeepSeek-V3.2-SpecialevsMistral Large 4Qwen2-MathvsMistral Large 4Frequently asked questions
DeepSeek-V3.2-Speciale and Qwen2-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2-Math shipped 480 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.
DeepSeek-V3.2-Speciale has 671B parameters, while Qwen2-Math has 1.5B/7B/72B. Context windows are 128k (DeepSeek-V3.2-Speciale) vs 4k (Qwen2-Math).
Direct benchmark comparisons are unavailable — DeepSeek-V3.2-Speciale and Qwen2-Math don't publish scores on any of the same benchmarks.