Kimi K2.7 CodevsQwen3.8-Max
Kimi K2.7 Code | Qwen3.8-Max | |
|---|---|---|
| Specifications | ||
Parameters | 1T | 2.4T |
Context window | 256k | 1M |
| Benchmarks | ||
Agentic coding SWE-Bench ProCan 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. | — | 67.7% |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 49.7% | — |
Agentic coding DeepSWE 1.1Artificial 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% | — |
Research reproduction PaperBenchreproducing the results of an ML research paper end to end | — | 93% |
Next.js coding Next.js EvalsVercel'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. | 75% | — |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 86.6% |
Professional tool use JobBenchTests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | — | 53.4% |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 86.1% |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 88.4% |
Visual reasoning BabyVisionTests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | — | 82% |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1469 | — |
| Overview | ||
| Company | Moonshot AI | Qwen |
| Release date | Jun 12 2026 | Aug 3 2026 |
| Access | Open Weight | Proprietary |
Which is better: Kimi K2.7 Code or Qwen3.8-Max?
Kimi K2.7 Code and Qwen3.8-Max don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi K2.7 Code shipped 52 days before Qwen3.8-Max, so benchmark comparisons should account for the intervening progress.
Kimi K2.7 Code has 1T parameters, while Qwen3.8-Max has 2.4T. Context windows are 256k (Kimi K2.7 Code) vs 1M (Qwen3.8-Max). Kimi K2.7 Code is open weight, while Qwen3.8-Max is proprietary.
Direct benchmark comparisons are unavailable — Kimi K2.7 Code and Qwen3.8-Max don't publish scores on any of the same benchmarks.
Frequently asked questions
Kimi K2.7 Code was released by Moonshot AI on Jun 12 2026.
Qwen3.8-Max was released by Qwen on Aug 3 2026.
Kimi K2.7 Code has a 256k context window; Qwen3.8-Max has 1M.
Kimi K2.7 Code is an open weight model released by Moonshot AI. Qwen3.8-Max is a proprietary model released by Qwen.