Kimi K2.5vsQwen3.8-27B
Kimi K2.5 | Qwen3.8-27B | |
|---|---|---|
| Specifications | ||
Parameters | 1T | 27B |
Context window | 256k | 262k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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% | — |
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. | — | 61.7% |
Coding SWE-Bench VerifiedReal 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% | — |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 31.9% | — |
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. | — | 42.2% |
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. | 21% | — |
Repo-level code generation NL2Repo-BenchTests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 42.3% |
Software engineering QwenSWEBenchQwen's in-house coding benchmark for evaluating a model's ability to complete software-engineering work. Higher is better. | — | 79% |
Competitive coding LiveCodeBenchCoding 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% | 90.3%Best |
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. | — | 73% |
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. | — | 33.4% |
Long-horizon office work CoWorkBenchTests long-running office tasks across fields including computer science, finance, law, medicine, and other productivity work. Higher is better. | — | 70.7% |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 30.8% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87.6% | 89.2%Best |
Instruction following IFBenchTests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 79.5% |
Agentic computer use Agent's Last Exam · pass@1A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 20.4% |
Agentic computer use Agent's Last Exam · scoreThe graded score on the same desktop and operating-system tasks in Agent's Last Exam, giving partial credit for progress beyond the strict pass-or-fail result. Higher is better. | — | 42.9% |
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. | 1433 | — |
| Overview | ||
| Company | Moonshot AI | Qwen |
| Release date | Jan 27 2026 | Aug 14 2026 |
| Access | Open Weight | Open Weight |
Which is better: Kimi K2.5 or Qwen3.8-27B?
Qwen3.8-27B leads Kimi K2.5 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Kimi K2.5 shipped 199 days before Qwen3.8-27B, so benchmark comparisons should account for the intervening progress.
Kimi K2.5 has 1T parameters, while Qwen3.8-27B has 27B. Context windows are 256k (Kimi K2.5) vs 262k (Qwen3.8-27B).
On LiveCodeBench, Qwen3.8-27B leads at 90.3% vs Kimi K2.5 at 85%. On GPQA Diamond, Qwen3.8-27B leads at 89.2% vs Kimi K2.5 at 87.6%.
Frequently asked questions
Kimi K2.5 was released by Moonshot AI on Jan 27 2026.
Qwen3.8-27B was released by Qwen on Aug 14 2026.
Qwen3.8-27B leads on LiveCodeBench — Kimi K2.5 85% vs Qwen3.8-27B 90.3%.
Qwen3.8-27B leads on GPQA Diamond — Kimi K2.5 87.6% vs Qwen3.8-27B 89.2%.
Kimi K2.5 has a 256k context window; Qwen3.8-27B has 262k.
Other comparisons
Kimi K2.5vsClaude Opus 5Qwen3.8-27BvsClaude Opus 5Kimi K2.5vsGPT-5.6-CyberQwen3.8-27BvsGPT-5.6-CyberKimi K2.5vsGemini 3.7 FlashQwen3.8-27BvsGemini 3.7 FlashKimi K2.5vsMuse GlimmerQwen3.8-27BvsMuse GlimmerKimi K2.5vsGrok 4.6Qwen3.8-27BvsGrok 4.6Kimi K2.5vsDeepSeek-V4-Pro-0813Qwen3.8-27BvsDeepSeek-V4-Pro-0813