Qwen 3 4B (Reasoning) — benchmark results
Qwen 3 4B evaluated with reasoning enabled. Provider: Alibaba. Released 2025-04-28. Access: Open.
Unified ELO 1518 ± 27, rank #737 of 1776 rated models, from 44 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medmarks - M-ARC | 57.67 | Score (%) | 81.4 |
| Medmarks - MedHallu Easy | 67.89 | Score (%) | 75.7 |
| Medmarks - MedHallu Hard | 47.93 | Score (%) | 75.7 |
| AA MATH-500 | 93.33 | Accuracy (%) | 74.3 |
| Medmarks - MedHallu Medium | 62.12 | Score (%) | 72.9 |
| BRIDGE Medical Leaderboard - CoT | 36.98 | Average Performance (%) | 71.7 |
| BRIDGE Medical Leaderboard - Zero-Shot | 38.5 | Average Performance (%) | 67 |
| Medmarks - Med-HALT Reasoning NOTA | 59.38 | Score (%) | 62.9 |
| BRIDGE Medical Leaderboard | 39.39 | Average Performance (%) | 60.4 |
| Medmarks - LongHealth Task 1 | 86.75 | Score (%) | 57.1 |
| Medmarks - MedConceptsQA Hard | 50.8 | Score (%) | 52.9 |
| AA LiveCodeBench | 46.46 | Pass@1 (%) | 52.8 |
Interactive version: theaggregate.ai/model?slug=qwen-3-4b-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.