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 | — |
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. | 256k | 400k |
| 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. | $0.49AtlasCloud | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.50AtlasCloud | — |
| $223AtlasCloud · int4 | — | |
| 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. | 52% | 45% |
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. | 18% | 46% |
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. | 76.8% | — |
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. | 85% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 60.6% | — |
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. | 30.1% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87.6% | — |
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. | 63.3% | — |
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Jan 27 2026 | Dec 18 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2.5vsClaude Fable 5.2GPT-5.2-CodexvsClaude Fable 5.2Kimi K2.5vsGemini 4 CarbonGPT-5.2-CodexvsGemini 4 CarbonKimi K2.5vsMuse EmberGPT-5.2-CodexvsMuse EmberKimi K2.5vsGrok 4.7GPT-5.2-CodexvsGrok 4.7Kimi K2.5vsDeepSeek-V4.1-Flash-1017GPT-5.2-CodexvsDeepSeek-V4.1-Flash-1017Kimi K2.5vsMistral Large 4GPT-5.2-CodexvsMistral Large 4Frequently asked questions
Kimi K2.5 and GPT-5.2-Codex are evenly matched across the 2 benchmarks they both report (BullshitBench v2, Next.js Evals). GPT-5.2-Codex shipped 40 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Kimi K2.5) vs 400k (GPT-5.2-Codex). Kimi K2.5 is open weight, while GPT-5.2-Codex is closed.
On BullshitBench v2, Kimi K2.5 leads at 52% vs GPT-5.2-Codex at 45%. On Next.js Evals, GPT-5.2-Codex leads at 46% vs Kimi K2.5 at 18%.