BlogLLM Benchmark Scores as Published, Side by Side
CoWorkBench: Results as Published
Every result the catalog holds for CoWorkBench: 11 models from 4 developers, read from 3 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 Knowledge WorkMaintainer Alibaba GroupIntroduced 2026Data version 2026103001, as of 2026-10-30
CoWorkBench is an in-house Qwen benchmark for long-horizon professional work across computer science, finance, law, medicine and other productivity domains. Its grading method is not published.
CoWorkBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.6 SolOpenAI, released 2026-07-09 | 71.5 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | Effort: max |
| Claude Fable 5Anthropic, released 2026-06-09 | 75.9 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Claude Opus 4.8Anthropic, released 2026-05-28 | 72.3 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Claude Opus 4.6Anthropic, released 2026-02-05 | 68.2 | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page | Effort: max |
| DeepSeek-V4-Flash-0731DeepSeek | 45.1 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| Qwen3.8-MaxAlibaba, released 2026-08-03 | 74.8 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Qwen3.7-PlusAlibaba, released 2026-06-01 | 65.1 | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.6-27BAlibaba, released 2026-04-22 | 61 | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15 | - |
| Qwen3.7-MaxAlibaba | 64.6 | Alibaba, Qwen3.8-Max comparisonchecked 2026-10-14 | - |
| Qwen3.8-27BAlibaba | 70.7 | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.8-Flash-NextAlibaba | 73.9 | 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.