Qwen 3.5 35B A3B (Non-reasoning) — benchmark results

Qwen 3.5 35B A3B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-02-24. Access: Open.

Unified ELO 1607 ± 25, rank #465 of 1776 rated models, from 56 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA TAU-2 Bench86.26Accuracy (%)78.9
AA GPQA Diamond81.92Accuracy (%)76.1
AA Humanity's Last Exam12.79Accuracy (%)69.9
AA Global-MMLU-Lite - Yoruba63.58Accuracy (%)67.6
Artificial Analysis Intelligence Index23.99Intelligence Index66.8
AA CritPt0.57Accuracy (%)64.9
AA Long Context Reasoning55.33Accuracy (%)64.6
UGI - Writing37Writing Score62.4
UGI - Natural Intelligence24.97NatInt Score62.2
AA Global-MMLU-Lite - Spanish88.67Accuracy (%)59
AA MMMU-Pro69.19Accuracy (%)56.4
AA Global-MMLU-Lite - Swahili75.33Accuracy (%)55.9

Interactive version: theaggregate.ai/model?slug=qwen-3-5-35b-a3b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.