Llama Nemotron Ultra 253BvsGPT-5.2
Llama Nemotron Ultra 253B | GPT-5.2 | |
|---|---|---|
| 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 | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $1.75 |
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. | — | $14.00 |
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. | — | $0.175 |
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. | — | $1.75Azure |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $14.00Azure |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 76% | 92.4% |
| 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. | — | 38% |
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. | — | 80% |
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% | — |
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. | — | 52.9% |
| Overview | ||
| Company | NVIDIA | OpenAI |
| Release date | Apr 8 2025 | Dec 11 2025 |
| Access | Open Weight | Proprietary |
Other comparisons
Frequently asked questions
GPT-5.2 leads Llama Nemotron Ultra 253B on 1 of the 1 benchmark they both report (GPQA Diamond). Only GPT-5.2 has a verified first-party API price: $1.75 per million input tokens and $14.00 per million output tokens. No pay-as-you-go API rate is tracked for Llama Nemotron Ultra 253B. Llama Nemotron Ultra 253B shipped 247 days before GPT-5.2, so benchmark comparisons should account for the intervening progress.
Llama Nemotron Ultra 253B is open weight, while GPT-5.2 is proprietary.
On GPQA Diamond, GPT-5.2 leads at 92.4% vs Llama Nemotron Ultra 253B at 76%.
Llama Nemotron Ultra 253B was released by NVIDIA on Apr 8 2025.
GPT-5.2 was released by OpenAI on Dec 11 2025.
GPT-5.2 leads on GPQA Diamond — Llama Nemotron Ultra 253B 76% vs GPT-5.2 92.4%.
Only GPT-5.2 has a verified first-party API price: $1.75 per million input tokens and $14.00 per million output tokens. No pay-as-you-go API rate is tracked for Llama Nemotron Ultra 253B. Rates are pay-as-you-go API prices verified on August 18, 2026.
Llama Nemotron Ultra 253B is an open weight model released by NVIDIA. GPT-5.2 is a proprietary model released by OpenAI.