Qwen 3 1.7B (Thinking): benchmark results
Provider: Alibaba. Released 2025-04-28. Access: Open.
Unified ELO 1405 ± 1, rank #1346 of 1761 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BRIDGE Medical Leaderboard - CoT | 27.71 | Average Performance (%) | 32.4 |
| AA TAU-2 Bench | 26.02 | Accuracy (%) | 30.3 |
| AA Humanity's Last Exam | 4.64 | Accuracy (%) | 25.5 |
| AA CritPt | 0 | Accuracy (%) | 24.4 |
| BRIDGE Medical Leaderboard | 28.95 | Average Performance (%) | 23.1 |
| BRIDGE Medical Leaderboard - Zero-Shot | 26.28 | Average Performance (%) | 23.1 |
| BRIDGE Medical Leaderboard - Few-Shot | 32.87 | Average Performance (%) | 20.4 |
| AA GPQA Diamond | 35.56 | Accuracy (%) | 12.1 |
| AA Omniscience - Science, Engineering & Mathematics | 14.3 | Accuracy (%) | 11.6 |
| AA IFBench | 26.87 | Accuracy (%) | 10.2 |
| AA Omniscience - Law | 5.5 | Accuracy (%) | 9.7 |
| Artificial Analysis Intelligence Index | 1 | Intelligence Index | 9.4 |
Interactive version: theaggregate.ai/model?slug=qwen-3-1-7b-thinking · How It Works · Data refreshed daily, snapshot 2026-09-05.