Qwen 3.7 Plus (Non-reasoning): benchmark results
Provider: Alibaba. Released 2026-06-02. Access: API.
Aggregate Rating 1658 ± 22, rank #497 of 2170 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UAV-DualCog - Flight Behavior Recognition (Atomic) | 34 | Atomic-level behavior accuracy (%; the atomic flight actions | 92.3 |
| RideWay - Success Rate | 82.2 | Success rate (%; share of trials passing the three-judge LLM | 89.1 |
| UAV-DualCog - Landmark Visibility Counting | 53.6 | Visibility-count accuracy (%; 1,024 flight videos in which t | 85.7 |
| UAV-DualCog - Landmark-Relative Direction | 55.4 | Answer accuracy (%; 1,024 questions asking where a landmark | 85.7 |
| PatternEval (Non-Thinking) | 66.28 | Accuracy (%; correctness of the final user-visible answer un | 83.3 |
| UAV-DualCog - Future Observation Prediction | 34.6 | Answer accuracy (%; 1,024 questions asking which view the UA | 79.4 |
| RideWay | 62.4 | Efficiency Utility (success-gated, held-out custom14 mean ov | 78.3 |
| UAV-DualCog - Self-Relative Position | 33.3 | Answer accuracy (%; 1,024 questions asking where the UAV is | 77.1 |
| BrainBench (EEG) - BrainAgent - Foundational Analysis | 73.08 | EEG analysis score (0-100) | 75 |
| BrainBench (EEG) - CodeAct - Neurocognitive Assessment | 64.17 | EEG analysis score (0-100) | 75 |
| BrainBench (EEG) - BrainAgent - Sleep Assessment | 68.08 | EEG analysis score (0-100) | 66.7 |
| BrainBench (EEG) - CodeAct - Foundational Analysis | 68.33 | EEG analysis score (0-100) | 66.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-7-plus-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.