Claude 3.5 SonnetvsNemotron 3 Ultra
Claude 3.5 Sonnet | Nemotron 3 Ultra | |
|---|---|---|
| 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. | — | 550B |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 59.4% | 86.7% |
| 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. | 45% | — |
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. | 33.4% | — |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | — | 48 |
| Overview | ||
| Company | Anthropic | NVIDIA |
| Release date | Jun 20 2024 | Jun 4 2026 |
| Access | Proprietary | Open Source |
Other comparisons
Claude 3.5 SonnetvsGPT-5.6 SolNemotron 3 UltravsGPT-5.6 SolClaude 3.5 SonnetvsGemini 3.7 FlashNemotron 3 UltravsGemini 3.7 FlashClaude 3.5 SonnetvsMuse GlimmerNemotron 3 UltravsMuse GlimmerClaude 3.5 SonnetvsGrok 4.6Nemotron 3 UltravsGrok 4.6Claude 3.5 SonnetvsDeepSeek-V4-Pro-0813Nemotron 3 UltravsDeepSeek-V4-Pro-0813Claude 3.5 SonnetvsMistral Medium 3.5Nemotron 3 UltravsMistral Medium 3.5
Frequently asked questions
Nemotron 3 Ultra leads Claude 3.5 Sonnet on 1 of the 1 benchmark they both report (GPQA Diamond). Claude 3.5 Sonnet shipped 714 days before Nemotron 3 Ultra, so benchmark comparisons should account for the intervening progress.
Claude 3.5 Sonnet is proprietary, while Nemotron 3 Ultra is open source.
On GPQA Diamond, Nemotron 3 Ultra leads at 86.7% vs Claude 3.5 Sonnet at 59.4%.
Claude 3.5 Sonnet was released by Anthropic on Jun 20 2024.
Nemotron 3 Ultra was released by NVIDIA on Jun 4 2026.
Nemotron 3 Ultra leads on GPQA Diamond — Claude 3.5 Sonnet 59.4% vs Nemotron 3 Ultra 86.7%.
Claude 3.5 Sonnet is a proprietary model released by Anthropic. Nemotron 3 Ultra is an open source model released by NVIDIA.