All Alibaba Qwen models ranked by benchmark performance.
Unless noted otherwise, ranking surfaces on this page use BenchLM's provisional leaderboard lane rather than the stricter sourced-only verified leaderboard.
Bottom line: Alibaba's Qwen series has improved significantly. Qwen3.5 397B (Reasoning) leads with strong math (92) and coding (85). The MoE variants offer efficient alternatives.
According to BenchLM.ai, Qwen3.5 397B (Reasoning) leads this ranking with a score of 80, followed by Qwen3.6 Plus (76) and Qwen3.6-35B-A3B (70). There is a significant gap between the leading models and the rest of the field.
The best open-weight option is Qwen3.5 397B (Reasoning) (ranked #1 with a score of 80). Open-weight models are highly competitive in this category — self-hosting is a viable alternative to proprietary APIs.
This ranking is based on provisional overall weighted scores across BenchLM.ai's scoring formula tracked by BenchLM.ai. For detailed model profiles, click any model name below. To compare two specific models head-to-head, use the "vs #" links.
Qwen3.5 397B (Reasoning)
Alibaba · 128K
Best Alibaba model. Reasoning model with top math and coding.
Qwen3.6 Plus
Alibaba · 1M
Newest Qwen. 1M context window with strong instruction following.
Qwen3.6-35B-A3B
Alibaba · 262K
Qwen3.5 397B (Reasoning) leads Alibaba's lineup — best math (92) and coding (85).
Qwen3.6 Plus newest generation with 1M context and strong instruction following (90).
Qwen3.5-122B-A10B efficient MoE variant — good performance per compute.
Get notified when models move. One email a week with what changed and why.
Free. No spam. Unsubscribe anytime.
The top model is Qwen3.5 397B (Reasoning) by Alibaba with a provisional score of 80.
The best open-weight model is Qwen3.5 397B (Reasoning) at position #1.
11 models are included in this ranking.
Models are ranked by the same overall BenchLM score used across all leaderboards. Comparing within Alibaba's lineup helps identify which model fits your use case and budget.
This page only shows Alibaba models. Cross-provider comparison requires the overall or category-specific leaderboards. Newer models may have limited benchmark coverage initially.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.