Qwen 3.5 Omni Plus — benchmark results

Alibaba's flagship Qwen 3.5 Omni tier, natively omni-modal with speech output. Provider: Alibaba. Released 2026-03-30. Access: API.

Unified ELO 1632 ± 48, rank #410 of 1776 rated models, from 39 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
OmniGAIA - Overall57.2Overall Accuracy (%)86.7
Video-MME-v238.2Avg Accuracy w/o sub (%)83.7
AA TAU-2 Bench88.3Accuracy (%)82.4
AA GPQA Diamond82.63Accuracy (%)77.3
AA Omniscience-12.3Score77
Artificial Analysis Intelligence Index30.64Intelligence Index76.8
AA SciCode40.51Accuracy (%)75.5
Omni-DeepSearch13.91Avg (self-reported)72.7
AA Humanity's Last Exam13.9Accuracy (%)72.2
CritPt0.6Accuracy (self-reported)71.1
AA-LCR52.7Score (self-reported)67.1
AA CritPt0.56Accuracy (%)63.1

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