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. | 72B | 253B |
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 | Moonshot AI | NVIDIA |
| Release date | Jun 17 2025 | Apr 8 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi-DevvsClaude Haiku 5.5Llama Nemotron Ultra 253BvsClaude Haiku 5.5Kimi-DevvsGPT-6.1 SolLlama Nemotron Ultra 253BvsGPT-6.1 SolKimi-DevvsGemini 4 ArgonLlama Nemotron Ultra 253BvsGemini 4 ArgonKimi-DevvsMuse Spark 1.3Llama Nemotron Ultra 253BvsMuse Spark 1.3Kimi-DevvsGrok 4.7Llama Nemotron Ultra 253BvsGrok 4.7Kimi-DevvsDeepSeek-V4.1-FlashLlama Nemotron Ultra 253BvsDeepSeek-V4.1-FlashFrequently asked questions
Kimi-Dev and Llama Nemotron Ultra 253B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Llama Nemotron Ultra 253B shipped 70 days before Kimi-Dev, so benchmark comparisons should account for the intervening progress.
Kimi-Dev has 72B parameters, while Llama Nemotron Ultra 253B has 253B.
Direct benchmark comparisons are unavailable — Kimi-Dev and Llama Nemotron Ultra 253B don't publish scores on any of the same benchmarks.