Qwen 4 Max (xHigh): benchmark results
Provider: Alibaba. Released 2026-11-16. Access: API.
Aggregate Rating 1904 ± 45, rank #43 of 2257 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Arena AI Code | 1749.81 | Arena ELO (imported) | 96.5 |
| Vals AI Vibe Code Bench | 86.66 | Accuracy (%) | 89.1 |
| LMArena WebDev Arena | 1749.81 | Arena rating (imported) | 88.6 |
| Vals AI Tax Agent Bench | 40.35 | Accuracy (%) | 85.9 |
| Vals AI Harvey Legal Agent Bench v1.1 | 21.25 | Task Resolution (%) | 84.2 |
| Vals AI Finance Agent v2.1 | 66.68 | Dealbreaker-gated Partial Credit (%) | 82.5 |
| Vals AI Finance Index | 61.99 | Finance Index (%) | 82.5 |
| Vals AI Terminal-Bench 4.0 | 48.49 | Accuracy (%) | 78.1 |
| LLM2014 Logic 2026-11 | 53.03 | Median Score | 75 |
| Vals AI (Vals Index) | 63.2 | Accuracy (%) | 73 |
| Vals AI Legal Research Bench | 41.35 | Accuracy (%) | 65.4 |
| Vals AI Excel Modeling v1.1 | 70.83 | Accuracy (%) | 59.5 |
Interactive version: theaggregate.ai/model?slug=qwen-4-max-xhigh · How It Works · Data refreshed daily, snapshot 2026-11-17.