{"slug": "opus-and-qwen-do-a-sokoban", "title": "Opus and Qwen do a Sokoban", "summary": "In a head-to-head coding test, Claude Opus 5.5 scored 77% and locally run Qwen3.8-Flash-Next scored 70% across 30 implementation aspects of a single-file HTML/JS/CSS Sokoban game, according to blogger Senko's vibecode benchmarks. Opus finished the one-line prompt in about 4 minutes, while Qwen — quantized to 4 bits on an AMD Strix Halo machine with 128GB of unified RAM — took about 31 minutes and 64k tokens, roughly 80% of it reasoning at extra-high effort. GPT-6 Astra, used as an unbiased judge, concluded Opus held \"a modest but meaningful advantage in correctness and maintainability,\" and Senko noted the local setup costs $3.5k to $6k, comparable to a few years of Claude Max.", "body_md": "## Opus and Qwen do a Sokoban\n\nComparing Claude Opus 5.5 vs Qwen3.8-Flash-Next, running locally, on the same coding task: [Sokoban](https://en.wikipedia.org/wiki/Sokoban)!\n\nIn a slightly different setup than usual, I ran Claude Opus 5.5 and Qwen3.8-Flash-Next through the chatbot interface (not a coding agent); Qwen I ran via [llama.app](https://llama.app/) (quantized to [4 bits](https://unsloth.ai/docs/models/qwen3.8-next) on an AMD Strix Halo machine with 128GB of unified RAM).\n\nThe prompt was a one-liner: “*Create a simple but beautiful Sokoban game clone in HTML/JS/CSS (all in one file, no frameworks or 3rd-party libraries).*“\n\nOpus (high reasoning effort) took ~4 minutes (I don't have a token count because this was from a web chatbot interface). Qwen took ~31 minutes and 64k tokens. 80% of this was for reasoning (at extra-high effort). Qwen thinks a lot more than Opus!\n\nBoth are available at [my vibecode benchmarks page](https://senko.net/vibecode-bench/). Here's also a side-by-side playthrough of both:\n\nI then had GPT-6 Astra compare the quality of the implementations. I chose Astra so as to not have any bias towards a solution (in case models really do prefer their own).\n\nAcross 30 different areas/aspects of each solution, Opus scored 77% and Qwen 70% (100% would be a perfect implementation without downsides or bugs).\n\nAstra concluded the code review with: “*Claude’s implementation has a modest but meaningful advantage in correctness and maintainability, with simpler state management, stronger movement safeguards, and fewer consequential bugs.*“\n\nNote that this test compared the best frontier model for coding against something I ran completely locally, on a machine sitting next to me. As I wrote earlier this year, [open-weights models have become good enough](https://blog.senko.net/open-weights-ai-models-have-become-good-enough), but it's hard (and expensive) to run a very capable model locally.\n\nFor this test I chose Sokoban because, frankly, my usual “frontier” tests, RTS/Warcraft, Minecraft and a flying simulator, were beyond Qwen's reach for a zero-shot. When trying to build an RTS, the model took hours and produced an unusable mess.\n\nThe hardware cost for this setup can vary between $3.5k and $6k, depending on luck, availability, and other system components. Not cheap, but not beyond the budget for a small business or affluent techies.\n\nThe same amount of money does buy you a few years of Claude Max subscription—purely on that level, it's not easy to justify.\n\nBut while I will not be canceling my Claude subscription any time soon, I'd say that for smaller tasks and with more guided steering, this is a usable alternative for those who would prefer to—or must—use local models.", "url": "https://wpnews.pro/news/opus-and-qwen-do-a-sokoban", "canonical_source": "https://blog.senko.net/opus-and-qwen-do-a-sokoban?pk_campaign=rss-feed", "published_at": "2026-11-07 15:56:20+00:00", "updated_at": "2026-11-09 01:25:23.289301+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "ai-tools"], "entities": ["Claude Opus 5.5", "Qwen3.8-Flash-Next", "GPT-6 Astra", "Senko", "AMD Strix Halo", "llama.app", "Claude Max"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/opus-and-qwen-do-a-sokoban", "markdown": "https://wpnews.pro/news/opus-and-qwen-do-a-sokoban.md", "text": "https://wpnews.pro/news/opus-and-qwen-do-a-sokoban.txt", "jsonld": "https://wpnews.pro/news/opus-and-qwen-do-a-sokoban.jsonld"}}