DeepSeek-V4-ProvsNemotron 3 Super
DeepSeek-V4-Pro | Nemotron 3 Super | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 120B |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.792GMICloud | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.74DigitalOcean | — |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.1% | 79.2% |
| BenchmarksPublished by one model only | ||
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. | 14% | — |
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. | — | 60.5% |
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. | 93.5% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | — | 36 |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | Apr 24 2026 | Mar 11 2026 |
| Access | Open Weight | Open Source |
Other comparisons
DeepSeek-V4-ProvsClaude Opus 5Nemotron 3 SupervsClaude Opus 5DeepSeek-V4-ProvsGPT-5.6 SolNemotron 3 SupervsGPT-5.6 SolDeepSeek-V4-ProvsGemini 3.7 FlashNemotron 3 SupervsGemini 3.7 FlashDeepSeek-V4-ProvsMuse GlimmerNemotron 3 SupervsMuse GlimmerDeepSeek-V4-ProvsGrok 4.6Nemotron 3 SupervsGrok 4.6DeepSeek-V4-ProvsMistral Medium 3.5Nemotron 3 SupervsMistral Medium 3.5
Frequently asked questions
DeepSeek-V4-Pro leads Nemotron 3 Super on 1 of the 1 benchmark they both report (GPQA Diamond). Nemotron 3 Super shipped 44 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro is open weight, while Nemotron 3 Super is open source.
On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs Nemotron 3 Super at 79.2%.
DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.
Nemotron 3 Super was released by NVIDIA on Mar 11 2026.
DeepSeek-V4-Pro leads on GPQA Diamond — DeepSeek-V4-Pro 90.1% vs Nemotron 3 Super 79.2%.
DeepSeek-V4-Pro is an open weight model released by DeepSeek. Nemotron 3 Super is an open source model released by NVIDIA.