Qwen 3.5 0.8B (Thinking) — benchmark results
Provider: Alibaba. Released 2026-03-02. Access: Open.
Unified ELO 1221 ± 65, rank #1663 of 1776 rated models, from 38 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience | -35.18 | Score | 58.5 |
| MedLayXPlain | 58.2 | S (self-reported) | 51.6 |
| AA TAU-2 Bench | 47.66 | Accuracy (%) | 51.4 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| Artificial Analysis Intelligence Index | 5.48 | Intelligence Index | 16.8 |
| AA Long Context Reasoning | 5.33 | Accuracy (%) | 16.7 |
| AA Omniscience - Software Engineering (SWE) - Julia | 0 | Accuracy (%) | 7.9 |
| GDPval-AA | 111 | Elo | 6.5 |
| AA Terminal-Bench Hard | 0 | Accuracy (%) | 5.5 |
| AA Omniscience - Software Engineering (SWE) - Dart | 4 | Accuracy (%) | 3.3 |
| AA IFBench | 21.63 | Accuracy (%) | 3.1 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-0-8b-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.