Compare AI models
| 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 |
| 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. | — | $0.50DeepInfra |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $2.20DeepInfra |
| Benchmarks | ||
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. | 48% | 49% |
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. | 76.2% | 71.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.9% | 86.7% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 52% | — |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 56.4% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 44.4% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 26.7% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 31.1% | — |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | — | 48 |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 81% | — |
| Overview | ||
| Company | NVIDIA | |
| Release date | Nov 18 2025 | Jun 4 2026 |
| Access | Closed | Open Source |
| Model details | View model | View model |
Other comparisons
Gemini 3.0 ProvsClaude Haiku 5.5Nemotron 3 UltravsClaude Haiku 5.5Gemini 3.0 ProvsGPT-6.1 SolNemotron 3 UltravsGPT-6.1 SolGemini 3.0 ProvsMuse Spark 1.3Nemotron 3 UltravsMuse Spark 1.3Gemini 3.0 ProvsGrok 4.7Nemotron 3 UltravsGrok 4.7Gemini 3.0 ProvsDeepSeek-V4.1-FlashNemotron 3 UltravsDeepSeek-V4.1-FlashGemini 3.0 ProvsMistral Large 4Nemotron 3 UltravsMistral Large 4Frequently asked questions
Gemini 3.0 Pro leads Nemotron 3 Ultra on 2 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Gemini 3.0 Pro shipped 198 days before Nemotron 3 Ultra, so benchmark comparisons should account for the intervening progress.
Gemini 3.0 Pro is closed, while Nemotron 3 Ultra is open source.
On BullshitBench v2, Nemotron 3 Ultra leads at 49% vs Gemini 3.0 Pro at 48%. On SWE-Bench Verified, Gemini 3.0 Pro leads at 76.2% vs Nemotron 3 Ultra at 71.9%. On GPQA Diamond, Gemini 3.0 Pro leads at 91.9% vs Nemotron 3 Ultra at 86.7%.