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 | 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 |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.25SiliconFlow | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.00SiliconFlow | — |
| $100SiliconFlow · fp8 | — | |
| 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. | 49.2% | 73.58% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 59.4% | 87.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 68.4% | 71.97% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 81.2% | 79.53% |
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 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 82.71% |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | Mar 24 2025 | Jul 25 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3-0324vsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsClaude Fable 5.2DeepSeek V3-0324vsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGPT-6.2 AstraDeepSeek V3-0324vsGemini 4 NeonLlama Nemotron Super 49B v1.5vsGemini 4 NeonDeepSeek V3-0324vsMuse EmberLlama Nemotron Super 49B v1.5vsMuse EmberDeepSeek V3-0324vsGrok 4.7Llama Nemotron Super 49B v1.5vsGrok 4.7DeepSeek V3-0324vsMistral Large 4Llama Nemotron Super 49B v1.5vsMistral Large 4Frequently asked questions
Llama Nemotron Super 49B v1.5 leads DeepSeek V3-0324 on 3 of the 4 benchmarks they both report (LiveCodeBench, AIME 2024, GPQA Diamond, MMLU-Pro). DeepSeek V3-0324 shipped 123 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.
DeepSeek V3-0324 has 671B parameters, while Llama Nemotron Super 49B v1.5 has 49B. Context windows are 128k (DeepSeek V3-0324) vs 128k (Llama Nemotron Super 49B v1.5).
On LiveCodeBench, Llama Nemotron Super 49B v1.5 leads at 73.58% vs DeepSeek V3-0324 at 49.2%. On AIME 2024, Llama Nemotron Super 49B v1.5 leads at 87.5% vs DeepSeek V3-0324 at 59.4%. On GPQA Diamond, Llama Nemotron Super 49B v1.5 leads at 71.97% vs DeepSeek V3-0324 at 68.4%. On MMLU-Pro, DeepSeek V3-0324 leads at 81.2% vs Llama Nemotron Super 49B v1.5 at 79.53%.