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. | 49B | — |
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 | 2M |
| Benchmarks | ||
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. | 73.58% | 80% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 82.71% | 92% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 71.97% | 85.7% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 44.9% |
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. | — | 20% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 7.64% | — |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 97.4% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 87.5% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 79.53% | — |
| Overview | ||
| Company | NVIDIA | SpaceXSI |
| Release date | Jul 25 2025 | Sep 19 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Super 49B v1.5vsClaude Fable 5.2Grok 4 FastvsClaude Fable 5.2Llama Nemotron Super 49B v1.5vsGPT-6.2 AstraGrok 4 FastvsGPT-6.2 AstraLlama Nemotron Super 49B v1.5vsGemini 4 NeonGrok 4 FastvsGemini 4 NeonLlama Nemotron Super 49B v1.5vsMuse EmberGrok 4 FastvsMuse EmberLlama Nemotron Super 49B v1.5vsDeepSeek-V4.1-Flash-1017Grok 4 FastvsDeepSeek-V4.1-Flash-1017Llama Nemotron Super 49B v1.5vsMistral Large 4Grok 4 FastvsMistral Large 4Frequently asked questions
Grok 4 Fast leads Llama Nemotron Super 49B v1.5 on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). Llama Nemotron Super 49B v1.5 shipped 56 days before Grok 4 Fast, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Llama Nemotron Super 49B v1.5) vs 2M (Grok 4 Fast). Llama Nemotron Super 49B v1.5 is open weight, while Grok 4 Fast is closed.
On LiveCodeBench, Grok 4 Fast leads at 80% vs Llama Nemotron Super 49B v1.5 at 73.58%. On AIME 2025, Grok 4 Fast leads at 92% vs Llama Nemotron Super 49B v1.5 at 82.71%. On GPQA Diamond, Grok 4 Fast leads at 85.7% vs Llama Nemotron Super 49B v1.5 at 71.97%.