QwenClawBench
We show this table for reference; we do not rank on it.
Qwen's internal OpenClaw-style benchmark for measuring broad real-world agent performance across practical productivity and research tasks.
Benchmark score on QwenClawBench — November 13, 2026
We compile the QwenClawBench rows from provider self-reports and secondary reports. Qwen3.7 Max leads the table at 64.3%, followed by Qwen3.7 Plus (61.8%) and Qwen 3.6 Max (preview) (59.0%). We do not use these results to rank models overall.
Qwen3.7 Max
Alibaba
Reported by AlibabaQwen3.7 Plus
Alibaba
Reported by AlibabaQwen 3.6 Max (preview)
Alibaba
Reported by Alibaba10 modelsAgenticCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (10 models)
None of the 10 results on this page has a documented run by the benchmark or an independent evaluator: 7 reported by the labs that built the models and 3 reported in another publisher’s document.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Qwen3.7 MaxAlibabaReported by Alibaba | 64.3% | Reported by Alibaba | Not reported | Closed |
| 2 | Qwen3.7 PlusAlibabaReported by Alibaba | 61.8% | Reported by Alibaba | Not reported | Closed |
| 3 | Qwen 3.6 Max (preview)AlibabaReported by Alibaba | 59.0% | Reported by Alibaba | Not reported | Closed |
| 4 | Qwen3.6 PlusAlibabaReported by Alibaba | 57.2% | Reported by Alibaba | Not reported | Closed |
| 5 | Kimi K2.5Moonshot AIAnother lab’s comparison table | 54.3% | Another lab’s comparison table | Not reported | Open |
| 6 | GLM-5Z.AIAnother lab’s comparison table | 54.1% | Another lab’s comparison table | Not reported | Open |
| 7 | Qwen3.6-27BAlibabaReported by Alibaba | 53.4% | Reported by Alibaba | Not reported | Open |
| 8 | Qwen3.6-35B-A3BAlibabaReported by Alibaba | 52.6% | Reported by Alibaba | Not reported | Open |
| 9 | Claude Opus 4.5AnthropicAnother lab’s comparison table | 52.3% | Another lab’s comparison table | Not reported | Closed |
| 10 | Qwen3.5 397BAlibabaReported by Alibaba | 51.8% | Reported by Alibaba | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
Among the reported QwenClawBench rows, Qwen3.7 Max is first at 64.3%. The third row is 5.3 points behind. The broader top-10 range is 12.5 points, so the table still separates the published systems.
10 models have been evaluated on QwenClawBench. The benchmark falls in the Agentic category. QwenClawBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About QwenClawBench
Year
2026
Tasks
Real-world agent workflows
Format
End-to-end agent evaluation
Difficulty
Broad real-world agentic execution
QwenClawBench appears in the Qwen3.6 launch comparisons as an internal real-world agent benchmark. BenchLM tracks it separately rather than merging it into other Claw-style benchmarks because the task mix and exact protocol are Qwen-specific.
Freshness and provenance
Version
QwenClawBench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does QwenClawBench measure?
Qwen's internal OpenClaw-style benchmark for measuring broad real-world agent performance across practical productivity and research tasks.
Which model scores highest on QwenClawBench?
Qwen3.7 Max by Alibaba currently leads with a score of 64.3% on QwenClawBench.
How many models are evaluated on QwenClawBench?
10 AI models have published results on QwenClawBench in the BenchLM catalog.
Compare top models on QwenClawBench
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.