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. | 9B | — |
| 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. | 5% | 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. | 71.1% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 64% | — |
| Overview | ||
| Company | NVIDIA | OpenAI |
| Release date | Aug 18 2025 | Sep 15 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Nemotron Nano 2vsClaude Haiku 5.5GPT-5-CodexvsClaude Haiku 5.5Nemotron Nano 2vsGemini 4 ArgonGPT-5-CodexvsGemini 4 ArgonNemotron Nano 2vsMuse Spark 1.3GPT-5-CodexvsMuse Spark 1.3Nemotron Nano 2vsGrok 4.7GPT-5-CodexvsGrok 4.7Nemotron Nano 2vsDeepSeek-V4.1-FlashGPT-5-CodexvsDeepSeek-V4.1-FlashNemotron Nano 2vsMistral Large 4GPT-5-CodexvsMistral Large 4Frequently asked questions
GPT-5-Codex leads Nemotron Nano 2 on 1 of the 1 benchmark they both report (BullshitBench v2). Nemotron Nano 2 shipped 28 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.
Nemotron Nano 2 is open weight, while GPT-5-Codex is closed.
On BullshitBench v2, GPT-5-Codex leads at 39% vs Nemotron Nano 2 at 5%.