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. | 1T | 4B |
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 | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.57Novita | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.30Novita | — |
| $229Novita · fp8 | — | |
| 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. | 65.8% | 59.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 75.1% | 72.41% |
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. | 10% | — |
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. | — | 18.1% |
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. | 4.7% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 77.94% |
| Overview | ||
| Company | Moonshot AI | NVIDIA |
| Release date | Jul 11 2025 | Oct 16 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi K2vsClaude Fable 5.2Nemotron Labs Dory 1.0 4BvsClaude Fable 5.2Kimi K2vsGPT-6.1 TerraNemotron Labs Dory 1.0 4BvsGPT-6.1 TerraKimi K2vsGemini 4 CarbonNemotron Labs Dory 1.0 4BvsGemini 4 CarbonKimi K2vsMuse EmberNemotron Labs Dory 1.0 4BvsMuse EmberKimi K2vsGrok 4.7Nemotron Labs Dory 1.0 4BvsGrok 4.7Kimi K2vsDeepSeek-V4.1-Flash-1017Nemotron Labs Dory 1.0 4BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K2 leads Nemotron Labs Dory 1.0 4B on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Kimi K2 shipped 462 days before Nemotron Labs Dory 1.0 4B, so benchmark comparisons should account for the intervening progress.
Kimi K2 has 1T parameters, while Nemotron Labs Dory 1.0 4B has 4B. Context windows are 128k (Kimi K2) vs 256k (Nemotron Labs Dory 1.0 4B).
On SWE-Bench Verified, Kimi K2 leads at 65.8% vs Nemotron Labs Dory 1.0 4B at 59.5%. On GPQA Diamond, Kimi K2 leads at 75.1% vs Nemotron Labs Dory 1.0 4B at 72.41%.