Qwen 3.5 35B A3B — benchmark results
Alibaba's open Qwen 3.5 35B A3B MoE (3B active). Provider: Alibaba. Released 2026-02-24. Access: Open.
Unified ELO 1626 ± 14, rank #420 of 1776 rated models, from 176 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (AndroidWorld_SR) | 71.1 | Score (%) | 100 |
| JudgeBench Reasoning | 96.94 | Accuracy (%) | 98 |
| InvisibleBench | 10.5 | Hard Fail Rate (self-reported) | 95 |
| LIBRA - MatreshkaNames * | 68.97 | Dataset Total Score (%) | 91.7 |
| LIBRA - ruBABILongQA1 | 68.38 | Dataset Total Score (%) | 91.7 |
| LIBRA - ruBABILongQA2 | 54.97 | Dataset Total Score (%) | 91.7 |
| LIBRA - ruBABILongQA3 * | 32.6 | Dataset Total Score (%) | 91.7 |
| LIBRA - ruSciFi | 51.47 | Dataset Total Score (%) | 91.7 |
| LIBRA - ruSciPassageCount * | 21.89 | Dataset Total Score (%) | 91.7 |
| StemBind | 39.3 | F Overall (self-reported) | 91.3 |
| SAGE | 71.79 | OA (%) (self-reported) | 90.9 |
| LLM Stats (MMStar) | 81.9 | Score (%) | 90.5 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-35b-a3b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.