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. | 4B | — |
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 | 256k |
| Benchmarks | ||
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 46.3% | 91.7% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 55.1% | 87.5% |
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. | — | 79% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 75.5% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 43% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 25.4% |
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. | — | 38.6% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 96.2% | — |
| Overview | ||
| Company | NVIDIA | SpaceXSI |
| Release date | May 20 2025 | Jul 9 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Nano 4B v1.1vsClaude Fable 5.2Grok 4vsClaude Fable 5.2Llama Nemotron Nano 4B v1.1vsGPT-6.2 AstraGrok 4vsGPT-6.2 AstraLlama Nemotron Nano 4B v1.1vsGemini 4 NeonGrok 4vsGemini 4 NeonLlama Nemotron Nano 4B v1.1vsMuse EmberGrok 4vsMuse EmberLlama Nemotron Nano 4B v1.1vsDeepSeek-V4.1-Flash-1017Grok 4vsDeepSeek-V4.1-Flash-1017Llama Nemotron Nano 4B v1.1vsMistral Large 4Grok 4vsMistral Large 4Frequently asked questions
Grok 4 leads Llama Nemotron Nano 4B v1.1 on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Llama Nemotron Nano 4B v1.1 shipped 50 days before Grok 4, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Llama Nemotron Nano 4B v1.1) vs 256k (Grok 4). Llama Nemotron Nano 4B v1.1 is open weight, while Grok 4 is closed.
On AIME 2025, Grok 4 leads at 91.7% vs Llama Nemotron Nano 4B v1.1 at 46.3%. On GPQA Diamond, Grok 4 leads at 87.5% vs Llama Nemotron Nano 4B v1.1 at 55.1%.