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

BenchmarkScoreMetricPercentile
EComStage - Solution Decision94.25Task Score (%)100
Self-Driving Negotiator68Average success rate (%)100
EComStage83.63Task Score (%)81.2
Medmarks - LongHealth Task 288.58Score (%)80.7
Medmarks - PubMedQA76.6Score (%)75.7
Medmarks - M-ARC46.33Score (%)75
Medmarks - CareQA EN88.84Score (%)72.9
Medmarks - SCTpublic65.74Score (%)70
Medmarks - SuperGPQA Medicine Easy55.74Score (%)69.3
Medmarks - MedCalc-Bench57.45Score (%)68.6
Medmarks - MedMCQA71.62Score (%)67.1
Medmarks - Medbullets OP477.16Score (%)67.1

Interactive version: theaggregate.ai/model?slug=qwen-3-30b-a3b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.