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 | — |
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 · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.95 | $1.25 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $4.00 | $2.50 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.16 | $0.20 |
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. | $0.465Inceptron | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $2.40DigitalOcean | — |
| Benchmarks | ||
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. | 65% | 56% |
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. | 80.2% | 76.7% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 52% | — |
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. | 89.6% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.2% | — |
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. | 34.7% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 53.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.5% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 73.1% | — |
| Overview | ||
| Company | Moonshot AI | SpaceXAI |
| Release date | Apr 21 2026 | Feb 17 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2.6vsClaude Sonnet 5.5Grok 4.20 BetavsClaude Sonnet 5.5Kimi K2.6vsGPT-6.1 SolGrok 4.20 BetavsGPT-6.1 SolKimi K2.6vsGemini 4 ArgonGrok 4.20 BetavsGemini 4 ArgonKimi K2.6vsMuse Spark 1.3Grok 4.20 BetavsMuse Spark 1.3Kimi K2.6vsDeepSeek-V4.1-FlashGrok 4.20 BetavsDeepSeek-V4.1-FlashKimi K2.6vsMistral Large 4Grok 4.20 BetavsMistral Large 4Frequently asked questions
Kimi K2.6 leads Grok 4.20 Beta on 2 of the 2 benchmarks they both report (BullshitBench v2, SWE-Bench Verified). Kimi K2.6 is cheaper on input: $0.95 vs $1.25 per million tokens. Grok 4.20 Beta is cheaper on output: $2.50 vs $4.00 per million tokens. Figures are base-tier rates. Grok 4.20 Beta shipped 63 days before Kimi K2.6, so benchmark comparisons should account for the intervening progress.
Kimi K2.6 is open weight, while Grok 4.20 Beta is closed.
On BullshitBench v2, Kimi K2.6 leads at 65% vs Grok 4.20 Beta at 56%. On SWE-Bench Verified, Kimi K2.6 leads at 80.2% vs Grok 4.20 Beta at 76.7%.