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 1617 ± 1, rank #217 of 1392 rated models, from 25 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CritPt | 60 | Accuracy (self-reported) | 91.9 |
| OmniGAIA - Overall | 57.2 | Overall Accuracy (%) | 86.7 |
| Video-MME-v2 | 38.2 | Avg Accuracy w/o sub (%) | 83.7 |
| AA TAU-2 Bench | 88.3 | Accuracy (%) | 82.5 |
| Omni-DeepSearch | 13.91 | Avg (self-reported) | 72.7 |
| AA GPQA Diamond | 82.63 | Accuracy (%) | 71.2 |
| Artificial Analysis Intelligence Index | 23.96 | Intelligence Index | 71.2 |
| BenchmarkList ECI | 126.79 | Capability Index (ECI) | 70.2 |
| AA Omniscience | -13.12 | Score | 69.6 |
| AA Humanity's Last Exam | 14.87 | Accuracy (%) | 65.8 |
| AA IFBench | 51.16 | Accuracy (%) | 61 |
| AA Terminal-Bench Hard | 21.21 | Accuracy (%) | 60.9 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-omni-plus · How It Works · Data refreshed daily, snapshot 2026-09-05.