Qwen 3.5 Plus (Thinking): benchmark results
Qwen 3.5 Plus evaluated with thinking enabled. Provider: Alibaba. Released 2026-02-16. Access: API.
Aggregate Rating 1720 ± 11, rank #302 of 2168 rated models, from 109 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GroupTravelBench - Plan Validity | 12 | Plan Validity (%): share of final itineraries that pass all | 100 |
| IndustryBench-MIPU - Single-Image | 81.3 | Image-level F1 (%) of single-image extraction (each image pr | 100 |
| OccuBench - Commerce & Consumer | 81 | Completion rate (%) on the Commerce & Consumer industry's ta | 100 |
| SecCodeBench | 67.08 | Total Score | 97.1 |
| TempCloze | 85.74 | Mean Accuracy (%) | 96.8 |
| OccuBench - Healthcare & Life Sciences | 81 | Completion rate (%) on the Healthcare & Life Sciences indust | 96.4 |
| BenchTable - Reasoning | 84.2 | Weighted Score (%) | 95.3 |
| BenchTable - Tech | 85.5 | Weighted Score (%) | 94.8 |
| OccuBench - Agriculture & Environment | 77 | Completion rate (%) on the Agriculture & Environment industr | 92.9 |
| BenchTable | 72.7 | Total Score (%) | 89.5 |
| CCTU (Thinking) - Solve Rate | 24.83 | Solve rate (%): the share of cases in which the model solves | 87.5 |
| MedQA | 95.21 | Score (%) | 87.2 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-plus-thinking · How It Works · Data refreshed daily, snapshot 2026-10-20.