BlogLLM Benchmark Scores as Published, Side by Side
RecreationBench: Results as Published
Every result the catalog holds for RecreationBench: 4 models from 1 developer, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Computer UseMaintainer Alibaba (Qwen team)Introduced 2026Data version 2026103001, as of 2026-10-30
RecreationBench is an in-house, long-horizon benchmark of the Qwen team in which an agent recreates an application, exercising hybrid-agent capabilities across five platforms: desktop (Ubuntu, macOS and Windows), mobile (Android) and the web. The card prints one number per model and does not name the metric or the task count.
RecreationBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Qwen3.7-PlusAlibaba, released 2026-06-01 | 30.2% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.6-27BAlibaba, released 2026-04-22 | 29.8% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15 | - |
| Qwen3.8-27BAlibaba | 47.1% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.8-Flash-NextAlibaba | 49.9% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.