Qwen 3.5 0.8B (Non-reasoning) — benchmark results

Provider: Alibaba. Released 2026-03-02. Access: Open.

Unified ELO 1333 ± 67, rank #1438 of 1756 rated models, from 36 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA TAU-2 Bench65.2Accuracy (%)59.1
CritPt0Accuracy (self-reported)30.3
AA Humanity's Last Exam4.87Accuracy (%)30.2
AA CritPt0Accuracy (%)27.2
AA-LCR6.7Score (self-reported)24.5
AA Omniscience - Software Engineering (SWE) - Julia4Accuracy (%)23.8
AA Long Context Reasoning6.67Accuracy (%)18.7
AA Omniscience - Software Engineering (SWE) - Go8Accuracy (%)17.6
AA Omniscience - Software Engineering (SWE) - Java9Accuracy (%)16.3
AA Omniscience - Software Engineering (SWE) - TypeScript7.78Accuracy (%)13.1
Artificial Analysis Intelligence Index4.42Intelligence Index12.8
AA Omniscience - Software Engineering (SWE) - HTML14Accuracy (%)10.8

Interactive version: aibenchmarks.dev/model?slug=qwen-3-5-0-8b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-17.