Qwen 3 30B A3B (Thinking): benchmark results
Alibaba Qwen 3 30B A3B evaluated with thinking enabled. Provider: Alibaba. Released 2025-04-29. Access: Open.
Unified ELO 1565 ± 1, rank #870 of 3078 rated models, from 159 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medmarks - PubMedQA | 77.47 | Score (%) | 90 |
| Medmarks - M-ARC | 61.33 | Score (%) | 88.6 |
| BRIDGE Medical Leaderboard - CoT | 39.35 | Average Performance (%) | 88 |
| Medmarks - SuperGPQA Medicine Hard | 46.39 | Score (%) | 85.7 |
| BRIDGE Medical Leaderboard - Zero-Shot | 40.93 | Average Performance (%) | 84.3 |
| BRIDGE Medical Leaderboard | 42.43 | Average Performance (%) | 82.4 |
| Medmarks - SuperGPQA Medicine Easy | 58.23 | Score (%) | 80.7 |
| Medmarks - Med-HALT Reasoning NOTA | 67.19 | Score (%) | 80 |
| Swallow - English MT-Bench - Reasoning | 86.5 | Judge Score (normalized, %) | 78.4 |
| Medmarks - MedConceptsQA Hard | 59.6 | Score (%) | 75.7 |
| Medmarks - MedHallu Medium | 62.58 | Score (%) | 75.7 |
| Swallow - English MT-Bench - Math | 98.6 | Judge Score (normalized, %) | 75.4 |
Interactive version: theaggregate.ai/model?slug=qwen-3-30b-a3b-thinking · How It Works · Data refreshed daily, snapshot 2026-09-19.