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. | — | 253B |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $1.25 | — |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $10.00 | — |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.125 | — |
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. | $0.625Google AI Studio | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $5.00Google AI Studio | — |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 86.4% | 76% |
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. | 20% | — |
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. | 59.6% | — |
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. | — | 66.3% |
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. | 18.8% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 68% | — |
| Overview | ||
| Company | NVIDIA | |
| Release date | Mar 25 2025 | Apr 8 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 2.5 ProvsClaude Haiku 5.5Llama Nemotron Ultra 253BvsClaude Haiku 5.5Gemini 2.5 ProvsGPT-6.1 SolLlama Nemotron Ultra 253BvsGPT-6.1 SolGemini 2.5 ProvsMuse Spark 1.3Llama Nemotron Ultra 253BvsMuse Spark 1.3Gemini 2.5 ProvsGrok 4.7Llama Nemotron Ultra 253BvsGrok 4.7Gemini 2.5 ProvsDeepSeek-V4.1-FlashLlama Nemotron Ultra 253BvsDeepSeek-V4.1-FlashGemini 2.5 ProvsMistral Large 4Llama Nemotron Ultra 253BvsMistral Large 4Frequently asked questions
Gemini 2.5 Pro leads Llama Nemotron Ultra 253B on 1 of the 1 benchmark they both report (GPQA Diamond). Only Gemini 2.5 Pro has a verified first-party API price: $1.25 per million input tokens and $10.00 per million output tokens. No pay-as-you-go API rate is tracked for Llama Nemotron Ultra 253B. Gemini 2.5 Pro shipped 14 days before Llama Nemotron Ultra 253B, so benchmark comparisons should account for the intervening progress.
Gemini 2.5 Pro is closed, while Llama Nemotron Ultra 253B is open weight.
On GPQA Diamond, Gemini 2.5 Pro leads at 86.4% vs Llama Nemotron Ultra 253B at 76%.