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. | 1T | 550B |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 256k | — |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.60Google | $0.50DeepInfra |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $2.50Google | $2.20DeepInfra |
| Benchmarks | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 71.3% | 71.9% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 49% |
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. | — | 56.4% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 44.4% |
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. | — | 26.7% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 86.7% |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | — | 48 |
| Overview | ||
| Company | Moonshot AI | NVIDIA |
| Release date | Nov 6 2025 | Jun 4 2026 |
| Access | Open Weight | Open Source |
| Model details | View model | View model |
Other comparisons
Kimi K2 ThinkingvsClaude Haiku 5.5Nemotron 3 UltravsClaude Haiku 5.5Kimi K2 ThinkingvsGPT-6.1 SolNemotron 3 UltravsGPT-6.1 SolKimi K2 ThinkingvsGemini 4 ArgonNemotron 3 UltravsGemini 4 ArgonKimi K2 ThinkingvsMuse Spark 1.3Nemotron 3 UltravsMuse Spark 1.3Kimi K2 ThinkingvsGrok 4.7Nemotron 3 UltravsGrok 4.7Kimi K2 ThinkingvsDeepSeek-V4.1-FlashNemotron 3 UltravsDeepSeek-V4.1-FlashFrequently asked questions
Nemotron 3 Ultra leads Kimi K2 Thinking on 1 of the 1 benchmark they both report (SWE-Bench Verified). Kimi K2 Thinking shipped 210 days before Nemotron 3 Ultra, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking has 1T parameters, while Nemotron 3 Ultra has 550B. Kimi K2 Thinking is open weight, while Nemotron 3 Ultra is open source.
On SWE-Bench Verified, Nemotron 3 Ultra leads at 71.9% vs Kimi K2 Thinking at 71.3%.