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. | 48B | 74B |
| These models have no shared benchmark scores. | ||
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 50.98% |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | — | 52.2% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 66.75% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 86.43% |
| Overview | ||
| Company | Moonshot AI | NVIDIA |
| Release date | Oct 30 2025 | Oct 15 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi LinearvsClaude Haiku 5.5Nemotron 3.5 Bolt 74BvsClaude Haiku 5.5Kimi LinearvsGPT-6.1 SolNemotron 3.5 Bolt 74BvsGPT-6.1 SolKimi LinearvsGemini 4 ArgonNemotron 3.5 Bolt 74BvsGemini 4 ArgonKimi LinearvsMuse Spark OpenNemotron 3.5 Bolt 74BvsMuse Spark OpenKimi LinearvsGrok 4.7Nemotron 3.5 Bolt 74BvsGrok 4.7Kimi LinearvsDeepSeek-V4.1-FlashNemotron 3.5 Bolt 74BvsDeepSeek-V4.1-FlashFrequently asked questions
Kimi Linear and Nemotron 3.5 Bolt 74B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi Linear shipped 350 days before Nemotron 3.5 Bolt 74B, so benchmark comparisons should account for the intervening progress.
Kimi Linear has 48B parameters, while Nemotron 3.5 Bolt 74B has 74B.
Direct benchmark comparisons are unavailable — Kimi Linear and Nemotron 3.5 Bolt 74B don't publish scores on any of the same benchmarks.