Nov 15, 2026
Alibaba's Qwen 4 Max is the top Chinese model on the Vals Index
We evaluated Alibaba’s new Qwen 4 Max on Vals Index v2.2, its components and the Vals Finance Index.
-
#11 of 38 on the Vals Index (63.20%), the highest-scoring Chinese model, ahead of Kimi K3.1 Pro (62.52%) and up from 59.05% for Qwen 3.8 Max 0902.
-
Strong on finance: #8 of 41 on Finance Agent v2.1 (66.68%) and #8 of 41 on the Vals Finance Index (61.99%). It also ranks #13 of 86 on Tax Agent Bench (40.35%).
-
On coding, it scores 86.66% on Vibe Code Bench (#15 of 129) and 48.49% on Terminal-Bench 4.0 (#15 of 65).
-
#7 of 39 on HLAB-Vals-1.1 (21.25%), but weaker on EMB v1.1 (70.83%, #18 of 43) and Legal Research Bench (41.35%, tied for #32 of 95).
Qwen 4 Max is a reasoning model with a 1M-token context window and 262k max output tokens. We evaluated it at xhigh reasoning effort, temperature 1.0, top_p 0.95 and top_k 20.
Congrats to the Qwen team on the release!