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 | 9B |
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. | $0.256DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.712DeepInfra | — |
| — | — | |
| 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. | 40.5% | 71.1% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 59.1% | 64% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 5% |
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. | 42% | — |
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. | 88.5% | — |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | Dec 26 2024 | Aug 18 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3 ChatvsClaude Haiku 5.5Nemotron Nano 2vsClaude Haiku 5.5DeepSeek V3 ChatvsGPT-6.1 SolNemotron Nano 2vsGPT-6.1 SolDeepSeek V3 ChatvsGemini 4 ArgonNemotron Nano 2vsGemini 4 ArgonDeepSeek V3 ChatvsMuse Spark OpenNemotron Nano 2vsMuse Spark OpenDeepSeek V3 ChatvsGrok 4.7Nemotron Nano 2vsGrok 4.7DeepSeek V3 ChatvsMistral Large 4Nemotron Nano 2vsMistral Large 4Frequently asked questions
Nemotron Nano 2 leads DeepSeek V3 Chat on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek V3 Chat shipped 235 days before Nemotron Nano 2, so benchmark comparisons should account for the intervening progress.
DeepSeek V3 Chat has 671B parameters, while Nemotron Nano 2 has 9B. Context windows are 128k (DeepSeek V3 Chat) vs 128k (Nemotron Nano 2).
On LiveCodeBench, Nemotron Nano 2 leads at 71.1% vs DeepSeek V3 Chat at 40.5%. On GPQA Diamond, Nemotron Nano 2 leads at 64% vs DeepSeek V3 Chat at 59.1%.