Alibaba (Qwen)
Qwen3.5 397B-A17B benchmark results
10 results on 7 benchmarks from 4 sources.
Also listed as: qwen3.5-397b-a17b · qwen3.5-397b-a17b_none · Qwen3.5-397B-A17B
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1442 | 92 | Overall, style control on; 91190 votes; 95% CI 1439–1445“qwen3.5-397b-a17b” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1400 | 90 | Overall; 21189 votes; 95% CI 1395–1405“qwen3.5-397b-a17b” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1247 | 54 | Overall, style control on; 31441 votes; 95% CI 1242–1252“qwen3.5-397b-a17b” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 85.9% | 77 | Epoch AI run, accuracy | Independent run | Aug 7, 2026 |
| MMLU-Pro | 87.8% | 7 | Overall accuracy; data source: Self-Reported; 397B“Qwen3.5-397B-A17B” | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 88.9% | 73 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 7, 2026 |
| τ²-bench | 81.5% | 5 | airline domain, pass^1; effort: enabled; submitted by Sierra; v1.0.1“Qwen3.5-397B-A17B” | Official leaderboard | Feb 27, 2026 |
| τ²-bench | 9.8% | 27 | banking_knowledge domain, pass^1; effort: enabled; submitted by Sierra; v1.0.1“Qwen3.5-397B-A17B” | Official leaderboard | Feb 27, 2026 |
| τ²-bench | 84.4% | 3 | retail domain, pass^1; effort: enabled; submitted by Sierra; v1.0.1“Qwen3.5-397B-A17B” | Official leaderboard | Feb 27, 2026 |
| τ²-bench | 97.8% | 4 | telecom domain, pass^1; effort: enabled; submitted by Sierra; v1.0.1“Qwen3.5-397B-A17B” | Official leaderboard | Feb 27, 2026 |
Related on this site
FAQ
Where do these Qwen3.5 397B-A17B scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, MMLU-Pro leaderboard (TIGER-Lab), and τ²-bench leaderboard submissions. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.