Agents · Benchmark profile
Qwen's internal OpenClaw-style benchmark for measuring broad real-world agent performance across practical productivity and research tasks.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on QwenClawBench
Qwen3.7-Max leads at 64.3%, followed by Qwen3.7-Plus (61.8%) and Qwen 3.6 Max (preview) (59%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
10 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Qwen3.7-Max | #1 | Alibaba Cloud | 64.3% |
| Qwen3.7-Plus | #2 | Alibaba Cloud | 61.8% |
| Qwen 3.6 Max (preview) | #3 | Alibaba Cloud | 59% |
| Qwen3.6 Plus | #4 | Alibaba Cloud | 57.2% |
| Kimi K2.5 | #5 | Moonshot AI | 54.3% |
| GLM-5 | #6 | Z.AI | 54.1% |
| Qwen3.6 27B | #7 | Alibaba Cloud | 53.4% |
| Qwen3.6-35B-A3B | #8 | Alibaba Cloud | 52.6% |
| Claude Opus 4.5 | #9 | Anthropic | 52.3% |
| Qwen3.5 397B | #10 | Alibaba Cloud | 51.8% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Qwen3.7-Max qwen3.7-max | Alibaba Cloud | — | Reference only | 64.3% |
| #2 | Qwen3.7-Plus qwen3.7-plus | Alibaba Cloud | — | Reference only | 61.8% |
| #3 | Qwen 3.6 Max (preview) qwen3-6-max-preview | Alibaba Cloud | closed | Reference only | 59% |
| #4 | Qwen3.6 Plus qwen3-6-plus | Alibaba Cloud | closed | Reference only | 57.2% |
| #5 | Kimi K2.5 kimi-k2.5 | Moonshot AI | — | Reference only | 54.3% |
| #6 | GLM-5 glm-5 | Z.AI | open | Reference only | 54.1% |
| #7 | Qwen3.6 27B qwen3.6-27b | Alibaba Cloud | open | Estimated reference | 53.4% |
| #8 | Qwen3.6-35B-A3B qwen3-6-35b-a3b | Alibaba Cloud | open | Estimated reference | 52.6% |
| #9 | Claude Opus 4.5 claude-opus-4-5 | Anthropic | closed | Reference only | 52.3% |
| #10 | Qwen3.5 397B qwen3.5-397b-a17b | Alibaba Cloud | open | Estimated reference | 51.8% |
The top of this snapshot is led by Qwen3.7-Max at 64.3%; third place is 5.3 points behind. The top-10 spread is 12.5 points.
About QwenClawBench
Qwen's internal OpenClaw-style benchmark for measuring broad real-world agent performance across practical productivity and research tasks. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
Qwen's internal OpenClaw-style benchmark for measuring broad real-world agent performance across practical productivity and research tasks.
Qwen3.7-Max by Alibaba Cloud currently leads with 64.3%.
10 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
