Skip to main content

Best Chinese AI Models in 2026

Top AI models from Chinese labs — DeepSeek, Alibaba Qwen, Zhipu GLM, Moonshot Kimi, and more — 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.

Chinese AI labs have produced some of the strongest models on our leaderboard, especially in math, reasoning, and agentic workflows. DeepSeek models are notable for being open weight while matching proprietary competitors. Alibaba's Qwen series, Zhipu's GLM line, ByteDance Seed, and StepFun now compete directly with GPT and Claude on a growing share of practical benchmarks.

Bottom line: Chinese AI labs produce some of the strongest models — GLM-5 (Reasoning) scores within striking distance of top proprietary APIs. DeepSeek and Qwen are strong open-weight alternatives.

According to BenchLM.ai, Qwen3.7 Max leads this ranking with a score of 91, followed by DeepSeek V4 Pro (Max) (87) and Kimi K2.6 (84). There is meaningful separation between the top models, suggesting genuine performance differences.

The best open-weight option is DeepSeek V4 Pro (Max) (ranked #2 with a score of 87). 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.

What changed

GLM-5 (Reasoning) leads Chinese models — strong math (93), reasoning (88), and agentic (86).

GLM-5.1 Z.AI's latest with strong instruction following (93) and math (89).

Qwen3.5 397B (Reasoning) Alibaba's flagship — top math (92) and coding (85).

How to choose

Full Rankings (42 models)

Qwen3.7 Max
Alibaba·Proprietary·1M

91

prov. overall

DeepSeek V4 Pro (Max)
DeepSeek·Open Weight·1M

87

prov. overall

Kimi K2.6
Moonshot AI·Open Weight·256K

84

prov. overall

4
DeepSeek V4 Pro (High)
DeepSeek·Open Weight·1M

83

prov. overall

5
GLM-5.1
Z.AI·Open Weight·203K

82

prov. overall

6
GLM-5 (Reasoning)
Z.AI·Open Weight·200K

80

prov. overall

7
Qwen3.5 397B (Reasoning)
Alibaba·Open Weight·128K

78

prov. overall

8
Kimi K2.5 (Reasoning)
Moonshot AI·Proprietary·128K

76

prov. overall

9
MiniMax M3
MiniMax·Open Weight·1M

76

prov. overall

10
DeepSeek V4 Flash (Max)
DeepSeek·Open Weight·1M

75

prov. overall

11
Qwen3.6 Plus
Alibaba·Proprietary·1M

73

prov. overall

12
Qwen3.6-27B
Alibaba·Open Weight·262K

73

prov. overall

13
DeepSeek V4 Flash (High)
DeepSeek·Open Weight·1M

71

prov. overall

14
DeepSeek V4 Pro
DeepSeek·Open Weight·1M

69

prov. overall

15
GLM-4.7
Z.AI·Open Weight·200K

68

prov. overall

16
GLM-5
Z.AI·Open Weight·200K

67

prov. overall

17
Qwen3.6-35B-A3B
Alibaba·Open Weight·262K

66

prov. overall

18
Kimi K2.5
Moonshot AI·Open Weight·256K

64

prov. overall

19
Qwen3.5-122B-A10B
Alibaba·Open Weight·262K

64

prov. overall

20
Qwen3.5 397B
Alibaba·Open Weight·128K

63

prov. overall

21
Qwen3.5-27B
Alibaba·Open Weight·262K

62

prov. overall

22
DeepSeek V3.2 (Thinking)
DeepSeek·Open Weight·128K

61

prov. overall

23
MiMo-V2-Flash
Xiaomi·Open Weight·256K

59

prov. overall

24
DeepSeek V4 Flash
DeepSeek·Open Weight·1M

57

prov. overall

25
DeepSeek V3.2
DeepSeek·Open Weight·128K

57

prov. overall

26
Qwen3.5-35B-A3B
Alibaba·Open Weight·262K

56

prov. overall

27
MiniMax M2.7
MiniMax·Open Weight·200K

54

prov. overall

28
DeepSeek Coder 2.0
DeepSeek·Open Weight·128K

51

prov. overall

29
DeepSeek LLM 2.0
DeepSeek·Open Weight·128K

51

prov. overall

30
Qwen2.5-1M
Alibaba·Open Weight·1M

51

prov. overall

31
DeepSeekMath V2
DeepSeek·Open Weight·128K

50

prov. overall

32
Qwen2.5-72B
Alibaba·Open Weight·128K

49

prov. overall

33
Qwen3 235B 2507 (Reasoning)
Alibaba·Open Weight·128K

46

prov. overall

34
Kimi K2
Moonshot AI·Proprietary·128K

41

prov. overall

35
DeepSeek V3
DeepSeek·Open Weight·128K

35

prov. overall

36
DeepSeek-R1
DeepSeek·Open Weight·128K

33

prov. overall

37
Qwen3 235B 2507
Alibaba·Open Weight·128K

32

prov. overall

38
DeepSeek V3.1 (Reasoning)
DeepSeek·Open Weight·128K

29

prov. overall

39
GLM-4.5
Z.AI·Proprietary·128K

26

prov. overall

40
DeepSeek V3.1
DeepSeek·Open Weight·128K

25

prov. overall

41
Moonshot v1
Moonshot AI·Proprietary·128K

23

prov. overall

42
GLM-4.5-Air
Z.AI·Proprietary·128K

19

prov. overall

These rankings update weekly

Get notified when models move. One email a week with what changed and why.

Free. No spam. Unsubscribe anytime.

Key Takeaways

The top model is Qwen3.7 Max by Alibaba with a provisional score of 91.

The best open-weight model is DeepSeek V4 Pro (Max) at position #2.

42 models are included in this ranking.

Score in Context

What these scores mean

Chinese models are ranked by the same overall BenchLM score. This page collects models from Chinese labs for easier comparison within this ecosystem.

Known limitations

Some Chinese models have limited English-language benchmark coverage. Models from smaller labs may have sparse data. Regional API availability varies.

Last updated: June 2, 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.