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 | 253B |
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 | 128k |
| 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. | — | 66.3% |
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. | 65.2% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 76% |
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. | 87.1% | — |
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. | 89.3% | — |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | Dec 25 2024 | Apr 8 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3 BasevsClaude Haiku 5.5Llama Nemotron Ultra 253BvsClaude Haiku 5.5DeepSeek V3 BasevsGPT-6.1 SolLlama Nemotron Ultra 253BvsGPT-6.1 SolDeepSeek V3 BasevsGemini 4 ArgonLlama Nemotron Ultra 253BvsGemini 4 ArgonDeepSeek V3 BasevsMuse Spark OpenLlama Nemotron Ultra 253BvsMuse Spark OpenDeepSeek V3 BasevsGrok 4.7Llama Nemotron Ultra 253BvsGrok 4.7DeepSeek V3 BasevsMistral Large 4Llama Nemotron Ultra 253BvsMistral Large 4Frequently asked questions
DeepSeek V3 Base and Llama Nemotron Ultra 253B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V3 Base shipped 104 days before Llama Nemotron Ultra 253B, so benchmark comparisons should account for the intervening progress.
DeepSeek V3 Base has 671B parameters, while Llama Nemotron Ultra 253B has 253B. Context windows are 128k (DeepSeek V3 Base) vs 128k (Llama Nemotron Ultra 253B).
Direct benchmark comparisons are unavailable — DeepSeek V3 Base and Llama Nemotron Ultra 253B don't publish scores on any of the same benchmarks.