BlogLLM Benchmark Scores as Published, Side by Side
QwenClawBench: Results as Published
Every result the catalog holds for QwenClawBench: 8 models from 3 developers, 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 Tool Use and WorkflowsMaintainer Alibaba (Qwen team)Introduced 2026Data version 2026103001, as of 2026-10-30
QwenClawBench is an in-house benchmark of the Qwen team for Claw-style agents, built from a real-user task distribution: the agent works through multi-step tool tasks and the card prints one score per model. The Qwen3.6-35B-A3B card says the set will be open-sourced; the metric is not named.
QwenClawBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Opus 4.5Anthropic, released 2025-11-24 | 52.3 | Alibaba, Qwen3.6-27B model cardchecked 2026-10-15 | Context: 256000 |
| Gemma 4 26B A4BGoogle, released 2026-04-02 | 38.7 | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | Context: 256000 |
| Gemma 4 31BGoogle, released 2026-04-02 | 41.7 | Alibaba, Qwen3.6-27B model cardchecked 2026-10-15; printed on 1 more page | Context: 256000 |
| Qwen3.6-27BAlibaba, released 2026-04-22 | 53.4 | Alibaba, Qwen3.6-27B model cardchecked 2026-10-15 | Context: 256000 |
| Qwen3.6-35B-A3BAlibaba, released 2026-04-16 | 52.6 | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15; printed on 1 more page | Context: 256000 |
| Qwen3.5-27BAlibaba, released 2026-02-24 | 52.2 | Alibaba, Qwen3.6-27B model cardchecked 2026-10-15; printed on 1 more page | Context: 256000 |
| Qwen3.5-35B-A3BAlibaba, released 2026-02-24 | 47.7 | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | Context: 256000 |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 51.8 | Alibaba, Qwen3.6-27B model cardchecked 2026-10-15 | Context: 256000 |
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.