Qwen 3 30B A3B Instruct: benchmark results
Provider: Alibaba. Released 2025-04-29. Access: Open.
Unified ELO 1658 ± 27, rank #432 of 2656 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EComStage - Solution Decision | 94.25 | Task Score (%) | 100 |
| Self-Driving Negotiator | 68 | Average success rate (%) | 100 |
| EComStage | 83.63 | Task Score (%) | 81.2 |
| Medmarks - LongHealth Task 2 | 88.58 | Score (%) | 80.7 |
| Medmarks - PubMedQA | 76.6 | Score (%) | 75.7 |
| Medmarks - M-ARC | 46.33 | Score (%) | 75 |
| Medmarks - CareQA EN | 88.84 | Score (%) | 72.9 |
| Medmarks - SCTpublic | 65.74 | Score (%) | 70 |
| Medmarks - SuperGPQA Medicine Easy | 55.74 | Score (%) | 69.3 |
| Medmarks - MedCalc-Bench | 57.45 | Score (%) | 68.6 |
| Medmarks - MedMCQA | 71.62 | Score (%) | 67.1 |
| Medmarks - Medbullets OP4 | 77.16 | Score (%) | 67.1 |
Interactive version: theaggregate.ai/model?slug=qwen-3-30b-a3b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.