Kimi K2.5vsQwen3-Coder-Next
Kimi K2.5 | Qwen3-Coder-Next | |
|---|---|---|
| Specifications | ||
Parameters | 1T | 80B |
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. | — | 44.3% |
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 | 70.6% |
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. | — | 62.8% |
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. | — | 36.2% |
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% | — |
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 | Feb 3 2026 |
| Access | Open Weight | Open Weight |
Which is better: Kimi K2.5 or Qwen3-Coder-Next?
Kimi K2.5 leads Qwen3-Coder-Next on 1 of the 1 benchmark they both report (SWE-Bench Verified). Kimi K2.5 shipped 7 days before Qwen3-Coder-Next, so benchmark comparisons should account for the intervening progress.
Kimi K2.5 has 1T parameters, while Qwen3-Coder-Next has 80B. Context windows are 256k (Kimi K2.5) vs 256k (Qwen3-Coder-Next).
On SWE-Bench Verified, Kimi K2.5 leads at 76.8% vs Qwen3-Coder-Next at 70.6%.
Frequently asked questions
Kimi K2.5 was released by Moonshot AI on Jan 27 2026.
Qwen3-Coder-Next was released by Qwen on Feb 3 2026.
Kimi K2.5 leads on SWE-Bench Verified — Kimi K2.5 76.8% vs Qwen3-Coder-Next 70.6%.
Kimi K2.5 has a 256k context window; Qwen3-Coder-Next has 256k.
Other comparisons
Kimi K2.5vsClaude Opus 5Qwen3-Coder-NextvsClaude Opus 5Kimi K2.5vsGPT-5.6 SolQwen3-Coder-NextvsGPT-5.6 SolKimi K2.5vsGemini 3.6 FlashQwen3-Coder-NextvsGemini 3.6 FlashKimi K2.5vsMuse Spark 1.1Qwen3-Coder-NextvsMuse Spark 1.1Kimi K2.5vsGrok 4.5Qwen3-Coder-NextvsGrok 4.5Kimi K2.5vsDeepSeek-V4-Flash-0731Qwen3-Coder-NextvsDeepSeek-V4-Flash-0731