Qwen3-32B [4bit]: benchmark results
Provider: Alibaba. Access: Open.
Aggregate Rating 1574 ± 47, rank #1346 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - BLUEX | 85.81 | Accuracy (%) | 99.7 |
| Open Portuguese LLM - ENEM | 89.92 | Accuracy (%) | 99.4 |
| Open Portuguese LLM - FaQuAD NLI | 83.61 | Macro F1 (%) | 96.9 |
| Open Portuguese LLM - ASSIN2 RTE | 93.67 | Macro F1 (%) | 91.2 |
| Open Portuguese LLM - OAB Exams | 57.86 | Accuracy (%) | 91 |
| IntentGrasp - Coronavirus Pandemic | 45.24 | Instance F1 (%) on the Coronavirus Pandemic (CP) domain of t | 90 |
| IntentGrasp - Toxic Speech | 50.5 | Instance F1 (%) on the Toxic Speech (TS) domain of the 12,90 | 90 |
| IntentGrasp - E-Commerce | 28.41 | Instance F1 (%) on the E-Commerce (EC) domain of the 12,909- | 80 |
| IntentGrasp - Teaching | 18.66 | Instance F1 (%) on the Teaching (T) domain of the 12,909-ite | 80 |
| IntentGrasp - Customer Support | 23.11 | Instance F1 (%) on the Customer Support (CS) domain of the 1 | 70 |
| IntentGrasp - Daily Life | 58.6 | Instance F1 (%) on the Daily Life (DL) domain of the 12,909- | 70 |
| IntentGrasp - General | 59.99 | Instance F1 (%) on the General (G) domain of the 12,909-item | 70 |
Interactive version: theaggregate.ai/model?slug=qwen3-32b-4bit · How It Works · Data refreshed daily, snapshot 2026-11-08.