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 | 1.05M |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.95 | $2.00 |
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 | $10.00 |
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 | $0.10 |
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. | $0.4342Baidu | $1.00OpenAI |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.828Baidu | $5.00OpenAI |
| 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% | 65% |
Auto-review circumvention (Internal)Safety-review circumvention — OpenAI's internal safety check on how often a model finds ways around its own automated review — the guardrail that inspects what it is about to do. This one counts failures, so lower is better and zero is the goal. | — | 0% |
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% | — |
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 75.2% |
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% | — |
Terminal-Bench-Science 0.1Agentic scientific computing — The same command-line setup as Terminal-Bench, pointed at scientific work: the AI has to drive research tooling and computational workflows through to a result, rather than administer a machine. Version 0.1 is the first release of the task set, and scores run lower than on the general board. Higher is better. | — | 57.1% |
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% | — |
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 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better. | — | 71.4% |
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% | — |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | — | 36.2% |
GDP.PDFDocument comprehension — Real professional PDFs — filings, reports, technical documents — with questions an expert in that field would ask. Tests whether the AI reads the page as a document, layout and figures included, rather than as loose text. Higher is better. | — | 32% |
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Apr 21 2026 | Sep 29 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2.6vsClaude Sonnet 5.5GPT-6.1 SolvsClaude Sonnet 5.5Kimi K2.6vsGemini 4 ArgonGPT-6.1 SolvsGemini 4 ArgonKimi K2.6vsMuse Spark 1.3GPT-6.1 SolvsMuse Spark 1.3Kimi K2.6vsGrok 4.7GPT-6.1 SolvsGrok 4.7Kimi K2.6vsDeepSeek-V4.1-FlashGPT-6.1 SolvsDeepSeek-V4.1-FlashKimi K2.6vsMistral Medium 3.5GPT-6.1 SolvsMistral Medium 3.5Frequently asked questions
Kimi K2.6 and GPT-6.1 Sol are evenly matched across the 1 benchmark they both report (BullshitBench v2). Kimi K2.6 is cheaper on both input and output: $0.95 vs $2.00 per million input tokens, and $4.00 vs $10.00 per million output tokens. Kimi K2.6 shipped 161 days before GPT-6.1 Sol, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Kimi K2.6) vs 1.05M (GPT-6.1 Sol). Kimi K2.6 is open weight, while GPT-6.1 Sol is closed.
On BullshitBench v2, both models score 65%.