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 1594 ± 1, rank #458 of 1761 rated models, from 46 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
CritPt90Accuracy (self-reported)97.7
CPTU Bench4.29Average Score (1-5)93.6
AA TAU-2 Bench93.57Accuracy (%)90.5
UGI - Natural Intelligence30.67NatInt Score75.3
AA Omniscience - Software Engineering (SWE) - Rust56Accuracy (%)74.1
AA GPQA Diamond82.93Accuracy (%)72.4
Artificial Analysis Intelligence Index23.31Intelligence Index70.1
UGI - Writing38.83Writing Score68.8
AA Humanity's Last Exam15.06Accuracy (%)66.4
AA Omniscience - Software Engineering (SWE) - TypeScript25.56Accuracy (%)65.9
AA Omniscience - Software Engineering (SWE) - PHP26Accuracy (%)65
AA CritPt0.86Accuracy (%)62.5

Interactive version: theaggregate.ai/model?slug=qwen-3-6-27b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.