Qwen 3.5 35B — benchmark results
Provider: Alibaba. Released 2026-02-24. Access: Open.
Unified ELO 1606 ± 60, rank #462 of 1751 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Structured Output Benchmark | 86.1 | Overall (%) | 80.4 |
| SLR-Bench - Easy | 92 | Accuracy (%) | 79.6 |
| SLR-Bench - Hard | 10 | Accuracy (%) | 76.9 |
| Wolfram LLM Benchmarking Project | 52.1 | Correct Functionality (%) | 75.9 |
| SLR-Bench - Medium | 30 | Accuracy (%) | 74.1 |
| SLR-Bench - Basic | 99 | Accuracy (%) | 63.9 |
| SEA-HELM | 59.68 | Mean Score (%) | 57.4 |
| ALL Bench LLM | 52.4 | Average Numeric Benchmark Score (%) | 0 |
| LibEvoBench | 52.6 | SEUS (self-reported) | 0 |
| RuneBench | 57 | Total Peak XP Rate (XP/min) | 0 |
Interactive version: aibenchmarks.dev/model?slug=qwen-3-5-35b · How the rankings work · Data refreshed daily, snapshot 2026-07-12.