Qwen 3 8B (Thinking) — benchmark results
Qwen 3 8B evaluated with thinking enabled. Provider: Alibaba. Released 2025-04-28. Access: Open.
Unified ELO 1532 ± 12, rank #680 of 1776 rated models, from 93 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medmarks - Med-HALT Reasoning NOTA | 67.8 | Score (%) | 82.9 |
| BRIDGE Medical Leaderboard - Zero-Shot | 39.98 | Average Performance (%) | 81.1 |
| Medmarks - SCTpublic | 67.82 | Score (%) | 80 |
| BRIDGE Medical Leaderboard - CoT | 37.06 | Average Performance (%) | 73.6 |
| BRIDGE Medical Leaderboard | 40.74 | Average Performance (%) | 70.8 |
| Medmarks - LongHealth Task 2 | 87.88 | Score (%) | 66.4 |
| AA MATH-500 | 90.4 | Accuracy (%) | 66.3 |
| Medmarks - LongHealth Task 1 | 87.17 | Score (%) | 58.6 |
| BRIDGE Medical Leaderboard - Few-Shot | 45.19 | Average Performance (%) | 58.5 |
| AA Omniscience - Software Engineering (SWE) - Dart | 22 | Accuracy (%) | 54.7 |
| Medmarks - HEAD-QA v2 | 82.43 | Score (%) | 52.1 |
| Medmarks - PubMedQA | 74.8 | Score (%) | 52.1 |
Interactive version: theaggregate.ai/model?slug=qwen-3-8b-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.