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. | 236B | 49B |
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 |
| 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. | 41.8% | 73.58% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 16.8% | — |
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. | 89% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 7.64% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 97.4% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 87.5% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 82.71% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 71.97% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 79.53% |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | Sep 5 2024 | Jul 25 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsClaude Fable 5.2DeepSeek V2.5vsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGPT-6.2 AstraDeepSeek V2.5vsGemini 4 NeonLlama Nemotron Super 49B v1.5vsGemini 4 NeonDeepSeek V2.5vsMuse EmberLlama Nemotron Super 49B v1.5vsMuse EmberDeepSeek V2.5vsGrok 4.7Llama Nemotron Super 49B v1.5vsGrok 4.7DeepSeek V2.5vsMistral Large 4Llama Nemotron Super 49B v1.5vsMistral Large 4Frequently asked questions
Llama Nemotron Super 49B v1.5 leads DeepSeek V2.5 on 1 of the 1 benchmark they both report (LiveCodeBench). DeepSeek V2.5 shipped 323 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.
DeepSeek V2.5 has 236B parameters, while Llama Nemotron Super 49B v1.5 has 49B. Context windows are 128k (DeepSeek V2.5) vs 128k (Llama Nemotron Super 49B v1.5).
On LiveCodeBench, Llama Nemotron Super 49B v1.5 leads at 73.58% vs DeepSeek V2.5 at 41.8%.