Qwen 3.5 397B A17B (Non-reasoning) — benchmark results

Qwen 3.5 397B A17B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-02-16. Access: Open.

Unified ELO 1684 ± 21, rank #303 of 1776 rated models, from 53 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI - Writing50.06Writing Score89
UGI - Natural Intelligence41.01NatInt Score87.6
AA GPQA Diamond86.06Accuracy (%)86.3
AA Global-MMLU-Lite - Portuguese91.33Accuracy (%)84.8
AA Terminal-Bench Hard35.61Accuracy (%)82
AA Global-MMLU-Lite - Korean88Accuracy (%)80.9
AA Humanity's Last Exam18.77Accuracy (%)78.7
Artificial Analysis Intelligence Index31.98Intelligence Index78.4
AA SciCode41.09Accuracy (%)78.2
AA Global-MMLU-Lite - German89.75Accuracy (%)77.1
AA Global-MMLU-Lite - Yoruba71.08Accuracy (%)76.1
AA TAU-2 Bench83.92Accuracy (%)74.8

Interactive version: theaggregate.ai/model?slug=qwen-3-5-397b-a17b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.