Kimi K2.5vsQwen3.6
Kimi K2.5 | Qwen3.6 | |
|---|---|---|
| Specifications | ||
Parameters | 1T | 35B |
Context window | 256k | 256k |
| 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. | — | 49.5% |
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%Best | 73.4% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 67.2% |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 31.9% | — |
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% | — |
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% | — |
Agentic terminal coding Terminal-Bench 2.0Can 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. | — | 51.5% |
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. | — | 21.4% |
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%Best | 86% |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 78% |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 75.3% |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | — | 81.7% |
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 | Apr 16 2026 |
| Access | Open Weight | Open Weight |
Which is better: Kimi K2.5 or Qwen3.6?
Kimi K2.5 leads Qwen3.6 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Kimi K2.5 shipped 79 days before Qwen3.6, so benchmark comparisons should account for the intervening progress.
Kimi K2.5 has 1T parameters, while Qwen3.6 has 35B. Context windows are 256k (Kimi K2.5) vs 256k (Qwen3.6).
On SWE-Bench Verified, Kimi K2.5 leads at 76.8% vs Qwen3.6 at 73.4%. On GPQA Diamond, Kimi K2.5 leads at 87.6% vs Qwen3.6 at 86%.
Frequently asked questions
Kimi K2.5 was released by Moonshot AI on Jan 27 2026.
Qwen3.6 was released by Qwen on Apr 16 2026.
Kimi K2.5 leads on SWE-Bench Verified — Kimi K2.5 76.8% vs Qwen3.6 73.4%.
Kimi K2.5 leads on GPQA Diamond — Kimi K2.5 87.6% vs Qwen3.6 86%.
Kimi K2.5 has a 256k context window; Qwen3.6 has 256k.