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

BenchmarkScoreMetricPercentile
BRIDGE Medical Leaderboard - CoT27.71Average Performance (%)32.4
AA TAU-2 Bench26.02Accuracy (%)30.3
AA Humanity's Last Exam4.64Accuracy (%)25.5
AA CritPt0Accuracy (%)24.4
BRIDGE Medical Leaderboard28.95Average Performance (%)23.1
BRIDGE Medical Leaderboard - Zero-Shot26.28Average Performance (%)23.1
BRIDGE Medical Leaderboard - Few-Shot32.87Average Performance (%)20.4
AA GPQA Diamond35.56Accuracy (%)12.1
AA Omniscience - Science, Engineering & Mathematics14.3Accuracy (%)11.6
AA IFBench26.87Accuracy (%)10.2
AA Omniscience - Law5.5Accuracy (%)9.7
Artificial Analysis Intelligence Index1Intelligence Index9.4

Interactive version: theaggregate.ai/model?slug=qwen-3-1-7b-thinking · How It Works · Data refreshed daily, snapshot 2026-09-05.