Kimi K2.7 CodevsQwen3-Coder-Next
Kimi K2.7 Code | Qwen3-Coder-Next | |
|---|---|---|
| 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 | 80B |
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 | 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 | $0.30 |
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 | $1.50 |
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. | $0.19 | — |
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. | $0.68DeepInfra | $0.12Parasail |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $3.00StreamLake | $0.80Parasail |
| BenchmarksPublished by one model only | ||
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 44.3% |
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. | — | 70.6% |
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. | — | 62.8% |
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. | 31% | — |
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. | 74% | — |
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. | — | 36.2% |
| Overview | ||
| Company | Moonshot AI | Qwen |
| Release date | Jun 12 2026 | Feb 3 2026 |
| Access | Open Weight | Open Weight |
Other comparisons
Kimi K2.7 CodevsClaude Fable 5.1Qwen3-Coder-NextvsClaude Fable 5.1Kimi K2.7 CodevsGPT-6 AstraQwen3-Coder-NextvsGPT-6 AstraKimi K2.7 CodevsGemini 3.8 FlashQwen3-Coder-NextvsGemini 3.8 FlashKimi K2.7 CodevsMuse Spark 1.3Qwen3-Coder-NextvsMuse Spark 1.3Kimi K2.7 CodevsGrok 4.6Qwen3-Coder-NextvsGrok 4.6Kimi K2.7 CodevsDeepSeek-V4.1-FlashQwen3-Coder-NextvsDeepSeek-V4.1-Flash
Frequently asked questions
Kimi K2.7 Code and Qwen3-Coder-Next don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen3-Coder-Next is cheaper on both input and output: $0.30 vs $0.95 per million input tokens, and $1.50 vs $4.00 per million output tokens. Figures are base-tier rates. Qwen3-Coder-Next shipped 129 days before Kimi K2.7 Code, so benchmark comparisons should account for the intervening progress.
Kimi K2.7 Code has 1T parameters, while Qwen3-Coder-Next has 80B. Context windows are 256k (Kimi K2.7 Code) vs 256k (Qwen3-Coder-Next).
Direct benchmark comparisons are unavailable — Kimi K2.7 Code and Qwen3-Coder-Next don't publish scores on any of the same benchmarks.