Qwen 3 1.7B (Thinking) — benchmark results

Provider: Alibaba. Released 2025-04-28. Access: Open.

Unified ELO 1392 ± 35, rank #1263 of 1776 rated models, from 41 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA MATH-50089.4Accuracy (%)64.9
AA AIME 202538.67Accuracy (%)40
AA LiveCodeBench30.79Pass@1 (%)36.5
BRIDGE Medical Leaderboard - CoT27.71Average Performance (%)33
CritPt0Accuracy (self-reported)30.3
AA TAU-2 Bench26.02Accuracy (%)30.1
AA Humanity's Last Exam4.77Accuracy (%)28.3
AA CritPt0Accuracy (%)27.1
BRIDGE Medical Leaderboard28.95Average Performance (%)23.6
BRIDGE Medical Leaderboard - Zero-Shot26.28Average Performance (%)23.6
BRIDGE Medical Leaderboard - Few-Shot32.87Average Performance (%)20.8
AA MMLU-Pro56.97Accuracy (%)18.9

Interactive version: theaggregate.ai/model?slug=qwen-3-1-7b-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.