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 | — |
| 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. | $0.60Novita | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.50Novita | — |
| $245Novita · bf16 | — | |
| Benchmarks | ||
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 61.1% | 73.7% |
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% | — |
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. | — | 57% |
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. | 83.1% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 61.7% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 60.2% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 23.9% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 94.5% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 84.5% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 84.6% | — |
| Overview | ||
| Company | Moonshot AI | SpaceXSI |
| Release date | Nov 6 2025 | Mar 19 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2 ThinkingvsClaude Fable 5.2Composer 2vsClaude Fable 5.2Kimi K2 ThinkingvsGPT-6.2 AstraComposer 2vsGPT-6.2 AstraKimi K2 ThinkingvsGemini 4 HydrogenComposer 2vsGemini 4 HydrogenKimi K2 ThinkingvsMuse EmberComposer 2vsMuse EmberKimi K2 ThinkingvsDeepSeek-V4.1-Flash-1017Composer 2vsDeepSeek-V4.1-Flash-1017Kimi K2 ThinkingvsMistral Large 4Composer 2vsMistral Large 4Frequently asked questions
Composer 2 leads Kimi K2 Thinking on 1 of the 1 benchmark they both report (SWE-Bench Multilingual). Kimi K2 Thinking shipped 133 days before Composer 2, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking is open weight, while Composer 2 is closed.
On SWE-Bench Multilingual, Composer 2 leads at 73.7% vs Kimi K2 Thinking at 61.1%.