Qwen 3.7 Max (Non-reasoning): benchmark results
Provider: Alibaba. Released 2026-05-20. Access: API.
Aggregate Rating 1668 ± 18, rank #463 of 2170 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Text2GraphQuery-Bench (Zero-Shot) - Cypher | 53.8 | Execution accuracy (%) of the generated Cypher query with ze | 100 |
| PatternEval (Non-Thinking) | 67.07 | Accuracy (%; correctness of the final user-visible answer un | 95.8 |
| RideWay | 66.1 | Efficiency Utility (success-gated, held-out custom14 mean ov | 95.7 |
| BrainBench (EEG) - CodeAct - Neurocognitive Assessment | 65.13 | EEG analysis score (0-100) | 91.7 |
| BunchCount - Group Counting | 5.55 | Mean absolute error (semantic groups per image, lower is bet | 85.7 |
| Text2GraphQuery-Bench (Zero-Shot) - GQL | 46.9 | Execution accuracy (%) of the generated ISO GQL query with z | 85.7 |
| BrainBench (EEG) - BrainAgent - Physiological Integration | 66.4 | EEG analysis score (0-100) | 83.3 |
| BrainBench (EEG) - BrainAgent - Sleep Assessment | 70.54 | EEG analysis score (0-100) | 83.3 |
| BrainBench (EEG) - CodeAct - Overall | 65.72 | Difficulty-weighted EEG analysis score (0-100) | 83.3 |
| BrainBench (EEG) - CodeAct - Physiological Integration | 60.4 | EEG analysis score (0-100) | 83.3 |
| BrainBench (EEG) - CodeAct - Sleep Assessment | 67.8 | EEG analysis score (0-100) | 83.3 |
| BrainBench (EEG) - BrainAgent - Overall | 69.77 | Difficulty-weighted EEG analysis score (0-100) | 75 |
Interactive version: theaggregate.ai/model?slug=qwen-3-7-max-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.