Qwen 3.6 35B A3B (Non-reasoning): benchmark results

Qwen 3.6 35B A3B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-04-16. Access: Open.

Unified ELO 1563 ± 1, rank #590 of 1761 rated models, from 43 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA TAU-2 Bench85.09Accuracy (%)77.4
AA Omniscience - Software Engineering (SWE) - Rust56Accuracy (%)74.1
AA Omniscience - Software Engineering (SWE) - TypeScript28.89Accuracy (%)73.4
AA GPQA Diamond81.72Accuracy (%)69.7
AA Terminal-Bench Hard25.76Accuracy (%)67.1
Epoch AI - Mystery Game Puzzles22Score65.3
AA Humanity's Last Exam13.9Accuracy (%)64.2
UGI - Natural Intelligence25.43NatInt Score63.2
Artificial Analysis Intelligence Index17.14Intelligence Index61.9
AA Omniscience - Software Engineering (SWE) - C36Accuracy (%)60.4
AA Long Context Reasoning64.33Accuracy (%)59.6
UGI - Writing35.83Writing Score58

Interactive version: theaggregate.ai/model?slug=qwen-3-6-35b-a3b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.