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. | 253B | 9B |
These models have no shared benchmark scores. | ||
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 | Z.ai |
| Release date | Apr 8 2025 | Jun 5 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Llama Nemotron Ultra 253BvsClaude Haiku 5.5GLM-4-9BvsClaude Haiku 5.5Llama Nemotron Ultra 253BvsGPT-6.1 SolGLM-4-9BvsGPT-6.1 SolLlama Nemotron Ultra 253BvsGemini 4 ArgonGLM-4-9BvsGemini 4 ArgonLlama Nemotron Ultra 253BvsMuse Spark 1.3GLM-4-9BvsMuse Spark 1.3Llama Nemotron Ultra 253BvsGrok 4.7GLM-4-9BvsGrok 4.7Llama Nemotron Ultra 253BvsDeepSeek-V4.1-FlashGLM-4-9BvsDeepSeek-V4.1-FlashFrequently asked questions
Llama Nemotron Ultra 253B and GLM-4-9B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-4-9B shipped 307 days before Llama Nemotron Ultra 253B, so benchmark comparisons should account for the intervening progress.
Llama Nemotron Ultra 253B has 253B parameters, while GLM-4-9B has 9B.
Direct benchmark comparisons are unavailable — Llama Nemotron Ultra 253B and GLM-4-9B don't publish scores on any of the same benchmarks.