Alibaba (Qwen)
Qwen3.5-35B-A3B benchmark results
5 results on 5 benchmarks from 3 sources.
Also listed as: qwen3.5-35b-a3b · qwen3.5-35b-a3b_none
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1394 | 167 | Overall, style control on; 30493 votes; 95% CI 1390–1398“qwen3.5-35b-a3b” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1254 | 128 | Overall; 1617 votes; 95% CI 1237–1271“qwen3.5-35b-a3b” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 81.2% | 111 | Epoch AI run, accuracy | Independent run | Aug 28, 2026 |
| MMLU-Pro | 85.3% | 32 | Overall accuracy; data source: Self-Reported; 35B | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 70.0% | 130 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 30, 2026 |
FAQ
Where do these Qwen3.5-35B-A3B scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.