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 | 7B/13B/70B |
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% | — |
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. | — | 29.9% |
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 | — | 13.5% |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | — | 57.4% |
HellaSwagReasoning — commonsense completion of short scenarios | — | 85.3% |
WinoGrandeReasoning — resolving ambiguous pronouns in context | — | 80.2% |
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. | — | 68.9% |
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. | — | 56.8% |
| Overview | ||
| Company | DeepSeek | Meta |
| Release date | Dec 1 2025 | Jul 18 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V3.2-SpecialevsClaude Fable 5.2LLaMA 2vsClaude Fable 5.2DeepSeek-V3.2-SpecialevsGPT-6.2 AstraLLaMA 2vsGPT-6.2 AstraDeepSeek-V3.2-SpecialevsGemini 4 HydrogenLLaMA 2vsGemini 4 HydrogenDeepSeek-V3.2-SpecialevsGrok 4.7LLaMA 2vsGrok 4.7DeepSeek-V3.2-SpecialevsMistral Large 4LLaMA 2vsMistral Large 4DeepSeek-V3.2-SpecialevsKimi K3.1 ProLLaMA 2vsKimi K3.1 ProFrequently asked questions
DeepSeek-V3.2-Speciale and LLaMA 2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 2 shipped 867 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.
DeepSeek-V3.2-Speciale has 671B parameters, while LLaMA 2 has 7B/13B/70B. Context windows are 128k (DeepSeek-V3.2-Speciale) vs 4k (LLaMA 2).
Direct benchmark comparisons are unavailable — DeepSeek-V3.2-Speciale and LLaMA 2 don't publish scores on any of the same benchmarks.