Qwen 3.6 27B (Non-reasoning) — benchmark results

Qwen 3.6 27B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-04-22. Access: Open.

Unified ELO 1649 ± 36, rank #372 of 1776 rated models, from 39 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA TAU-2 Bench93.57Accuracy (%)90.5
AA GPQA Diamond82.93Accuracy (%)78.6
UGI - Natural Intelligence30.67NatInt Score76.1
Artificial Analysis Intelligence Index30.46Intelligence Index76
AA Humanity's Last Exam13.58Accuracy (%)71.8
UGI - Writing38.83Writing Score69.5
AA CritPt0.86Accuracy (%)68.8
AA MMMU-Pro71.73Accuracy (%)64.9
AA Long Context Reasoning55Accuracy (%)63.8
AA GDPval1112.72ELO62.8
AA SciCode37.27Accuracy (%)62.8
GDPval-AA1113Elo61.5

Interactive version: theaggregate.ai/model?slug=qwen-3-6-27b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.