Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 253B | — |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 400k |
| These models have no shared benchmark scores. | ||
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. | — | 39% |
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% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 76% | — |
| Overview | ||
| Company | NVIDIA | OpenAI |
| Release date | Apr 8 2025 | Sep 15 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Ultra 253BvsClaude Haiku 5.5GPT-5-CodexvsClaude Haiku 5.5Llama Nemotron Ultra 253BvsGemini 4 ArgonGPT-5-CodexvsGemini 4 ArgonLlama Nemotron Ultra 253BvsMuse Spark OpenGPT-5-CodexvsMuse Spark OpenLlama Nemotron Ultra 253BvsGrok 4.7GPT-5-CodexvsGrok 4.7Llama Nemotron Ultra 253BvsDeepSeek-V4.1-Flash-1017GPT-5-CodexvsDeepSeek-V4.1-Flash-1017Llama Nemotron Ultra 253BvsMistral Large 4GPT-5-CodexvsMistral Large 4Frequently asked questions
Llama Nemotron Ultra 253B and GPT-5-Codex don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Llama Nemotron Ultra 253B shipped 160 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Llama Nemotron Ultra 253B) vs 400k (GPT-5-Codex). Llama Nemotron Ultra 253B is open weight, while GPT-5-Codex is closed.
Direct benchmark comparisons are unavailable — Llama Nemotron Ultra 253B and GPT-5-Codex don't publish scores on any of the same benchmarks.