1
O
gpt-5.5
gpt-5.5Openai
100.0
808
1.05M
¥36 / ¥216输入/输出
对话 · 文本 · 中文排行榜
基于公开偏好评测数据展示 文本 / 中文 榜单，每个榜单独立排序。
中文模型怎么选？
中文排行榜用于回答“中文哪个 AI 模型更强”这类选型问题。页面基于公开偏好评测数据展示模型排名，每个榜单独立排序，不把不同任务的原始分数直接混合。当前榜首是 gpt-5.5，厂商为 openai，百分制分数 100.0，样本量 808。 数据来源保留 Arena 原始榜单和 LMArena leaderboard dataset，更新时间以榜单发布时间 2026-05-27 为准。
gpt-5.5claude-opus-4-6-thinkingclaude-opus-4-6qwen3.5-max-previewgpt-5.5-high
2
A
claude-opus-4-6-thinking
claude-opus-4-6-thinkingAnthropic
99.7
1.8K
1M
¥36 / ¥180输入/输出
3
Aclaude-opus-4-6
claude-opus-4-6Anthropic
99.4
1.9K
1M
¥36 / ¥180输入/输出
4
A
qwen3.5-max-preview
qwen3.5-max-previewAlibaba
99.1
1.2K
-
-
5
Ogpt-5.5-high
gpt-5.5-highOpenai
98.8
812
1.05M
¥36 / ¥216输入/输出
6
Aclaude-opus-4-7-thinking
claude-opus-4-7-thinkingAnthropic
98.5
1.1K
1M
¥36 / ¥180输入/输出
7
G
gemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
98.2
2.3K
1.05M
¥14.4 / ¥86.4输入/输出
8
Aclaude-opus-4-7
claude-opus-4-7Anthropic
97.9
1K
1M
¥36 / ¥180输入/输出
9
Aqwen3.7-max-preview
qwen3.7-max-previewAlibaba
97.6
268
1M
¥18 / ¥54输入/输出
10
M
kimi-k2.6
kimi-k2.6Moonshot
97.3
808
262K
¥6.84 / ¥28.8输入/输出
11
Ggemini-3-pro
gemini-3-proGoogle
97.0
2.1K
1.05M
¥14.4 / ¥86.4输入/输出
12
Ggemini-3.5-flash
gemini-3.5-flashGoogle
96.7
492
1.05M
¥10.8 / ¥64.8输入/输出
13
Ogpt-5.4
gpt-5.4Openai
96.4
1.7K
1.05M
¥18 / ¥108输入/输出
14
Ogpt-5.4-high
gpt-5.4-highOpenai
96.0
1.5K
1.05M
¥18 / ¥108输入/输出
15
Z
glm-5
glm-5Zai
95.7
1.1K
205K
¥7.2 / ¥23输入/输出
16
Zglm-5.1
glm-5.1Zai
95.4
843
200K
¥0 / ¥0输入/输出
17
Ggemini-3-flash
gemini-3-flashGoogle
95.1
1.5K
1.05M
¥3.6 / ¥21.6输入/输出
18
B
ernie-5.1
ernie-5.1Baidu
94.8
692
119K
¥5.4 / ¥21.6输入/输出
19
M
muse-spark
muse-sparkMeta
94.5
723
-
-
20
B
dola-seed-2.0-pro
dola-seed-2.0-proBytedance
94.2
2K
-
-
21
Ggemini-2.5-pro
gemini-2.5-proGoogle
93.9
6.3K
1.05M
¥9 / ¥72输入/输出
22
Mkimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
93.6
1.7K
262K
¥4.32 / ¥21.6输入/输出
23
Aqwen3.5-397b-a17b
qwen3.5-397b-a17bAlibaba
93.3
1.6K
262K
¥3.1 / ¥18.6输入/输出
24
Bernie-5.0-preview-1022
ernie-5.0-preview-1022Baidu
93.0
280
128K
¥7.92 / ¥14.4输入/输出
25
D
deepseek-v4-pro
deepseek-v4-proDeepseek
92.7
936
1M
¥3.13 / ¥6.26输入/输出
26
Bernie-5.0-0110
ernie-5.0-0110Baidu
92.4
1.6K
128K
¥7.92 / ¥14.4输入/输出
27
Zglm-4.6
glm-4.6Zai
92.1
1.6K
205K
¥4.32 / ¥15.8输入/输出
28
MI
mimo-v2.5-pro
mimo-v2.5-proXiaomi
91.8
849
1.05M
¥7.2 / ¥21.6输入/输出
29
Ddeepseek-v4-pro-thinking
deepseek-v4-pro-thinkingDeepseek
91.5
842
1M
¥3.13 / ¥6.26输入/输出
30
Ogpt-5.1-high
gpt-5.1-highOpenai
91.2
2K
400K
¥9 / ¥72输入/输出
31
Aqwen3-max-preview
qwen3-max-previewAlibaba
90.9
1.5K
262K
¥6.2 / ¥24.8输入/输出
32
X
grok-4.20-beta-0309-reasoning
grok-4.20-beta-0309-reasoningXai
90.6
1.5K
2M
¥14.4 / ¥43.2输入/输出
33
Zglm-4.7
glm-4.7Zai
90.3
688
205K
¥0 / ¥0输入/输出
34
Aqwen3.6-max-preview
qwen3.6-max-previewAlibaba
90.0
283
246K
¥9.5 / ¥56.9输入/输出
35
Aclaude-sonnet-4-6
claude-sonnet-4-6Anthropic
89.7
1.3K
1M
¥21.6 / ¥108输入/输出
36
Xgrok-4.20-multi-agent-beta-0309
grok-4.20-multi-agent-beta-0309Xai
89.4
1.5K
2M
¥14.4 / ¥43.2输入/输出
37
Bernie-5.0-preview-1203
ernie-5.0-preview-1203Baidu
89.1
534
128K
¥7.92 / ¥14.4输入/输出
38
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
88.8
2.6K
1.05M
¥3.6 / ¥21.6输入/输出
39
Xgrok-4.20-beta1
grok-4.20-beta1Xai
88.4
1.2K
2M
¥14.4 / ¥43.2输入/输出
40
Ggemma-4-26b-a4b
gemma-4-26b-a4bGoogle
88.1
383
262K
¥0.94 / ¥2.88输入/输出
41
Aqwen3.6-plus
qwen3.6-plusAlibaba
87.8
902
1M
¥3.6 / ¥21.6输入/输出
42
Ogpt-5.1
gpt-5.1Openai
87.5
2K
400K
¥9 / ¥72输入/输出
43
Xgrok-4-fast-chat
grok-4-fast-chatXai
87.2
358
2M
¥1.44 / ¥3.6输入/输出
44
MImimo-v2.5
mimo-v2.5Xiaomi
86.9
766
1.05M
¥2.88 / ¥14.4输入/输出
45
Aclaude-opus-4-5-20251101
claude-opus-4-5-20251101Anthropic
86.6
3.3K
200K
¥36 / ¥180输入/输出
46
Aqwen3.5-27b
qwen3.5-27bAlibaba
86.3
1.4K
262K
¥2.16 / ¥17.3输入/输出
47
Ddeepseek-v4-flash-thinking
deepseek-v4-flash-thinkingDeepseek
86.0
883
1M
¥1.01 / ¥2.02输入/输出
48
Ggemma-4-31b
gemma-4-31bGoogle
85.7
364
262K
¥3.24 / ¥7.2输入/输出
49
Xgrok-4.1
grok-4.1Xai
85.4
3.5K
200K
¥14.4 / ¥72输入/输出
50
Aqwen3-next-80b-a3b-instruct
qwen3-next-80b-a3b-instructAlibaba
85.1
1.2K
131K
¥1.04 / ¥4.13输入/输出
51
Aqwen3-235b-a22b-thinking-2507
qwen3-235b-a22b-thinking-2507Alibaba
84.8
413
131K
¥2.07 / ¥8.26输入/输出
52
Ddeepseek-v3.1-thinking
deepseek-v3.1-thinkingDeepseek
84.5
874
128K
¥1.44 / ¥5.04输入/输出
53
Zglm-4.5
glm-4.5Zai
84.2
1.3K
131K
¥4.32 / ¥15.8输入/输出
54
Ddeepseek-v4-flash
deepseek-v4-flashDeepseek
83.9
848
1M
¥1.01 / ¥2.02输入/输出
55
Aqwen3.5-35b-a3b
qwen3.5-35b-a3bAlibaba
83.6
1.5K
262K
¥1.8 / ¥14.4输入/输出
56
Ogpt-5.2-chat-latest-20260210
gpt-5.2-chat-latest-20260210Openai
83.3
1.6K
400K
¥12.6 / ¥101输入/输出
57
A
amazon-nova-experimental-chat-11-10
amazon-nova-experimental-chat-11-10Amazon
83.0
1.2K
-
-
58
Aqwen3.5-122b-a10b
qwen3.5-122b-a10bAlibaba
82.7
1.5K
262K
¥2.88 / ¥23输入/输出
59
Aqwen3-235b-a22b-instruct-2507
qwen3-235b-a22b-instruct-2507Alibaba
82.4
4.8K
128K
¥2.09 / ¥8.23输入/输出
60
Aqwen3.5-flash
qwen3.5-flashAlibaba
82.1
1.5K
1M
¥1.24 / ¥12.4输入/输出
61
M
longcat-flash-chat-2602-exp
longcat-flash-chat-2602-expMeituan
81.8
1.3K
128K
¥1.08 / ¥10.8输入/输出
62
Ddeepseek-v3.2-exp
deepseek-v3.2-expDeepseek
81.5
629
128K
¥0 / ¥0输入/输出
63
TE
hunyuan-hy3-preview
hunyuan-hy3-previewTencent
81.2
334
256K
¥0 / ¥0输入/输出
64
MImimo-v2-flash (non-thinking)
mimo-v2-flash (non-thinking)Xiaomi
80.9
2.2K
262K
¥0.72 / ¥2.16输入/输出
65
Aclaude-sonnet-4-5-20250929
claude-sonnet-4-5-20250929Anthropic
80.5
3.6K
200K
¥21.6 / ¥108输入/输出
66
Aclaude-opus-4-5-20251101-thinking-32k
claude-opus-4-5-20251101-thinking-32kAnthropic
80.2
1.8K
200K
¥108 / ¥540输入/输出
67
Aclaude-sonnet-4-5-20250929-thinking-32k
claude-sonnet-4-5-20250929-thinking-32kAnthropic
79.9
3.6K
200K
¥21.6 / ¥108输入/输出
68
Mkimi-k2.5-instant
kimi-k2.5-instantMoonshot
79.6
242
262K
¥4.32 / ¥21.6输入/输出
69
Ogpt-5.5-instant
gpt-5.5-instantOpenai
79.3
1.4K
400K
¥9 / ¥72输入/输出
70
Aqwen3-vl-235b-a22b-instruct
qwen3-vl-235b-a22b-instructAlibaba
79.0
494
128K
¥2.16 / ¥8.64输入/输出
71
Ddeepseek-r1-0528
deepseek-r1-0528Deepseek
78.7
1K
164K
¥3.6 / ¥15.5输入/输出
72
Ogpt-5.4-mini-high
gpt-5.4-mini-highOpenai
78.4
1.4K
400K
¥5.4 / ¥32.4输入/输出
73
Ddeepseek-v3.1
deepseek-v3.1Deepseek
78.1
1.1K
128K
¥1.44 / ¥5.04输入/输出
74
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
77.8
1.9K
1.05M
¥1.8 / ¥10.8输入/输出
75
Ddeepseek-v3.2
deepseek-v3.2Deepseek
77.5
2.4K
128K
¥2.09 / ¥3.1输入/输出
76
Aamazon-nova-experimental-chat-26-02-10
amazon-nova-experimental-chat-26-02-10Amazon
77.2
213
-
-
77
Ddeepseek-v3.2-exp-thinking
deepseek-v3.2-exp-thinkingDeepseek
76.9
304
128K
¥0 / ¥0输入/输出
78
Ogpt-5.2
gpt-5.2Openai
76.6
2.2K
400K
¥12.6 / ¥101输入/输出
79
Ogpt-5.2-high
gpt-5.2-highOpenai
76.3
2.4K
400K
¥12.6 / ¥101输入/输出
80
Xgrok-4.1-thinking
grok-4.1-thinkingXai
76.0
3.3K
200K
¥14.4 / ¥72输入/输出
81
Mkimi-k2-thinking-turbo
kimi-k2-thinking-turboMoonshot
75.7
3K
262K
¥17.3 / ¥72输入/输出
82
Ddeepseek-v3.2-thinking
deepseek-v3.2-thinkingDeepseek
75.4
1.9K
128K
¥2.09 / ¥3.1输入/输出
83
Ggemini-2.5-flash
gemini-2.5-flashGoogle
75.1
6.2K
1.05M
¥2.16 / ¥18输入/输出
84
Ochatgpt-4o-latest-20250326
chatgpt-4o-latest-20250326Openai
74.8
4.1K
128K
¥18 / ¥72输入/输出
85
Ggemini-2.5-flash-preview-09-2025
gemini-2.5-flash-preview-09-2025Google
74.5
1.4K
1M
¥2.16 / ¥18输入/输出
86
Aqwen3-vl-235b-a22b-thinking
qwen3-vl-235b-a22b-thinkingAlibaba
74.2
296
131K
¥2.06 / ¥8.26输入/输出
87
MImimo-v2-pro
mimo-v2-proXiaomi
73.9
1.1K
1.05M
¥7.2 / ¥21.6输入/输出
88
Aamazon-nova-experimental-chat-12-10
amazon-nova-experimental-chat-12-10Amazon
73.6
238
-
-
89
MA
mistral-medium-2508
mistral-medium-2508Mistral
73.3
4.7K
262K
¥2.88 / ¥14.4输入/输出
90
Xgrok-3-preview-02-24
grok-3-preview-02-24Xai
72.9
1.8K
1M
¥9 / ¥18输入/输出
91
Xgrok-4.3
grok-4.3Xai
72.6
787
1M
¥9 / ¥18输入/输出
92
Xgrok-4-1-fast-reasoning
grok-4-1-fast-reasoningXai
72.3
2.8K
2M
¥1.44 / ¥3.6输入/输出
93
ST
step-3.5-flash
step-3.5-flashStepfun
72.0
1.6K
256K
¥0.69 / ¥2.07输入/输出
94
MAmistral-large-3
mistral-large-3Mistral
71.7
2K
262K
¥3.6 / ¥10.8输入/输出
95
Oo3-2025-04-16
o3-2025-04-16Openai
71.4
3K
200K
¥14.4 / ¥57.6输入/输出
96
Aqwen3-30b-a3b-instruct-2507
qwen3-30b-a3b-instruct-2507Alibaba
71.1
1.3K
262K
¥2.16 / ¥3.6输入/输出
97
Xgrok-4-fast-reasoning
grok-4-fast-reasoningXai
70.8
695
2M
¥1.44 / ¥3.6输入/输出
98
TEhunyuan-t1-20250711
hunyuan-t1-20250711Tencent
70.5
258
131K
¥0 / ¥0输入/输出
99
Zglm-4.5-air
glm-4.5-airZai
70.2
1.6K
131K
¥0 / ¥0输入/输出
100
NV
nvidia-nemotron-3-super-120b-a12b
nvidia-nemotron-3-super-120b-a12bNvidia
69.9
388
262K
¥1.44 / ¥5.76输入/输出
101
MImimo-v2-flash (thinking)
mimo-v2-flash (thinking)Xiaomi
69.6
448
262K
¥0.72 / ¥2.16输入/输出
102
Mlongcat-flash-chat
longcat-flash-chatMeituan
69.3
682
128K
¥1.08 / ¥10.8输入/输出
103
Xgrok-4-0709
grok-4-0709Xai
69.0
2K
256K
¥21.6 / ¥108输入/输出
104
M
minimax-m2.1-preview
minimax-m2.1-previewMinimax
68.7
821
205K
¥0 / ¥0输入/输出
105
Aqwen3-max-2025-09-23
qwen3-max-2025-09-23Alibaba
68.4
353
258K
¥6.19 / ¥24.7输入/输出
106
Aqwen3-235b-a22b-no-thinking
qwen3-235b-a22b-no-thinkingAlibaba
68.1
2K
131K
¥2.07 / ¥8.26输入/输出
107
Zglm-4.7-flash
glm-4.7-flashZai
67.8
443
200K
¥0 / ¥0输入/输出
108
Aclaude-opus-4-1-20250805
claude-opus-4-1-20250805Anthropic
67.5
3.8K
200K
¥108 / ¥540输入/输出
109
Ogpt-5-high
gpt-5-highOpenai
67.2
1.6K
400K
¥9 / ¥72输入/输出
110
Mminimax-m2.7
minimax-m2.7Minimax
66.9
1.2K
205K
¥0 / ¥0输入/输出
111
Ogpt-5.3-chat-latest
gpt-5.3-chat-latestOpenai
66.6
1.6K
128K
¥12.6 / ¥101输入/输出
112
Ogpt-4.5-preview-2025-02-27
gpt-4.5-preview-2025-02-27Openai
66.3
907
8.19K
¥216 / ¥432输入/输出
113
Ogpt-5-chat
gpt-5-chatOpenai
66.0
1.7K
400K
¥9 / ¥72输入/输出
114
Aclaude-opus-4-1-20250805-thinking-16k
claude-opus-4-1-20250805-thinking-16kAnthropic
65.7
2.6K
200K
¥108 / ¥540输入/输出
115
TEhunyuan-turbos-20250416
hunyuan-turbos-20250416Tencent
65.3
466
131K
¥0 / ¥0输入/输出
116
Aqwen3-next-80b-a3b-thinking
qwen3-next-80b-a3b-thinkingAlibaba
65.0
718
131K
¥1.04 / ¥10.3输入/输出
117
Aclaude-haiku-4-5-20251001
claude-haiku-4-5-20251001Anthropic
64.7
3.8K
200K
¥7.2 / ¥36输入/输出
118
Mkimi-k2-0905-preview
kimi-k2-0905-previewMoonshot
64.4
737
262K
¥4.32 / ¥18输入/输出
119
AG
ling-flash-2.0
ling-flash-2.0Ant Group
64.1
300
131K
¥1.01 / ¥4.1输入/输出
120
Aamazon-nova-experimental-chat-10-20
amazon-nova-experimental-chat-10-20Amazon
63.8
606
-
-
121
Ogpt-5.4-nano-high
gpt-5.4-nano-highOpenai
63.5
1.4K
400K
¥1.44 / ¥9输入/输出
122
AGring-flash-2.0
ring-flash-2.0Ant Group
63.2
317
131K
¥1.01 / ¥4.1输入/输出
123
Ggemini-2.5-flash-lite-preview-09-2025-no-thinking
gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle
62.9
2.2K
1.05M
¥0.72 / ¥2.88输入/输出
124
Ggemini-2.5-flash-lite-preview-06-17-thinking
gemini-2.5-flash-lite-preview-06-17-thinkingGoogle
62.6
1.7K
65.5K
¥0.72 / ¥2.88输入/输出
125
Ddeepseek-r1
deepseek-r1Deepseek
62.3
1.2K
164K
¥5.04 / ¥18输入/输出
126
STstep-3
step-3Stepfun
62.0
234
65.5K
¥1.8 / ¥4.68输入/输出
127
Mkimi-k2-0711-preview
kimi-k2-0711-previewMoonshot
61.7
1.6K
131K
¥4.32 / ¥18输入/输出
128
Mminimax-m2.5
minimax-m2.5Minimax
61.4
1.9K
205K
¥0 / ¥0输入/输出
129
Oo1-2024-12-17
o1-2024-12-17Openai
61.1
1.8K
128K
¥108 / ¥432输入/输出
130
NVnvidia-nemotron-3-nano-30b-a3b-bf16
nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia
60.8
850
131K
¥0 / ¥0输入/输出
131
Ogpt-5-mini-high
gpt-5-mini-highOpenai
60.5
1.3K
400K
¥1.8 / ¥14.4输入/输出
132
Zglm-4-plus-0111
glm-4-plus-0111Zai
60.2
387
128K
¥72 / ¥72输入/输出
133
Ddeepseek-v3-0324
deepseek-v3-0324Deepseek
59.9
2.5K
75K
¥1.44 / ¥5.76输入/输出
134
Aclaude-opus-4-20250514-thinking-16k
claude-opus-4-20250514-thinking-16kAnthropic
59.6
1.9K
200K
¥108 / ¥540输入/输出
135
Aclaude-opus-4-20250514
claude-opus-4-20250514Anthropic
59.3
2.4K
200K
¥108 / ¥540输入/输出
136
Mminimax-m2
minimax-m2Minimax
59.0
278
197K
¥0 / ¥0输入/输出
137
UNtrinity-large-thinking
-
58.7
1.5K
262K
¥1.8 / ¥6.48输入/输出
138
Aqwen2.5-max
qwen2.5-maxAlibaba
58.4
2K
32K
¥11.5 / ¥46输入/输出
139
Aqwen3-235b-a22b
qwen3-235b-a22bAlibaba
58.1
1.3K
131K
¥2.07 / ¥8.26输入/输出
140
Xgrok-3-mini-high
grok-3-mini-highXai
57.8
718
128K
¥0 / ¥0输入/输出
141
Ggemini-2.0-flash-001
gemini-2.0-flash-001Google
57.4
2.4K
1.05M
¥1.08 / ¥4.32输入/输出
142
Aqwq-32b
qwq-32bAlibaba
57.1
1.4K
131K
¥2.07 / ¥6.2输入/输出
143
Oo3-mini-high
o3-mini-highOpenai
56.8
1.2K
200K
¥7.92 / ¥31.7输入/输出
144
Ogpt-oss-120b
gpt-oss-120bOpenai
56.5
1.6K
131K
¥1.08 / ¥4.32输入/输出
145
Xgrok-3-mini-beta
grok-3-mini-betaXai
56.2
1.1K
1M
¥9 / ¥18输入/输出
146
MAmistral-medium-2505
mistral-medium-2505Mistral
55.9
1.6K
262K
¥2.88 / ¥14.4输入/输出
147
Ogpt-4.1-2025-04-14
gpt-4.1-2025-04-14Openai
55.6
2.5K
1.05M
¥14.4 / ¥57.6输入/输出
148
Anova-2-lite
nova-2-liteAmazon
55.3
685
128K
¥2.38 / ¥19.8输入/输出
149
UNintellect-3
-
55.0
293
131K
¥1.44 / ¥7.92输入/输出
150
STstep-1o-turbo-202506
step-1o-turbo-202506Stepfun
54.7
457
-
-
151
Mminimax-m1
minimax-m1Minimax
54.4
1.8K
1M
¥0.95 / ¥9.03输入/输出
152
Aqwen3-32b
qwen3-32bAlibaba
54.1
187
131K
¥2.07 / ¥8.26输入/输出
153
TEhunyuan-turbo-0110
hunyuan-turbo-0110Tencent
53.8
208
-
-
154
Aqwen3-coder-480b-a35b-instruct
qwen3-coder-480b-a35b-instructAlibaba
53.5
1.4K
262K
¥6.2 / ¥24.8输入/输出
155
Aqwen3-30b-a3b
qwen3-30b-a3bAlibaba
53.2
1.3K
128K
¥0.79 / ¥7.78输入/输出
156
Aclaude-sonnet-4-20250514-thinking-32k
claude-sonnet-4-20250514-thinking-32kAnthropic
52.9
1.8K
200K
¥21.6 / ¥108输入/输出
157
Ogpt-5-nano-high
gpt-5-nano-highOpenai
52.6
384
400K
¥0.36 / ¥2.88输入/输出
158
Oo4-mini-2025-04-16
o4-mini-2025-04-16Openai
52.3
2.3K
200K
¥7.92 / ¥31.7输入/输出
159
UNtrinity-large-preview
-
52.0
1.4K
262K
¥1.8 / ¥6.48输入/输出
160
Aqwen-plus-0125
qwen-plus-0125Alibaba
51.7
459
1M
¥0.83 / ¥2.07输入/输出
161
Ggemma-3-27b-it
gemma-3-27b-itGoogle
51.4
2.3K
128K
¥2.15 / ¥2.15输入/输出
162
TEhunyuan-large-2025-02-10
hunyuan-large-2025-02-10Tencent
51.1
295
-
-
163
Aclaude-sonnet-4-20250514
claude-sonnet-4-20250514Anthropic
50.8
2.2K
200K
¥21.6 / ¥108输入/输出
164
MAmistral-small-2506
mistral-small-2506Mistral
50.5
828
262K
¥2.88 / ¥14.4输入/输出
165
Ggemini-2.0-flash-lite-preview-02-05
gemini-2.0-flash-lite-preview-02-05Google
50.2
1.5K
1.05M
¥0.54 / ¥2.16输入/输出
166
Ddeepseek-v3
deepseek-v3Deepseek
49.8
1.5K
128K
¥0 / ¥0输入/输出
167
Ggemini-1.5-pro-002
gemini-1.5-pro-002Google
49.5
4.4K
-
-
168
STstep-2-16k-exp-202412
step-2-16k-exp-202412Stepfun
49.2
328
16.4K
¥37.5 / ¥118输入/输出
169
Ogpt-4.1-mini-2025-04-14
gpt-4.1-mini-2025-04-14Openai
48.9
2.1K
1.05M
¥2.88 / ¥11.5输入/输出
170
Zglm-4.5v
glm-4.5vZai
48.6
173
64K
¥4.32 / ¥13输入/输出
171
Oo1-preview
o1-previewOpenai
48.3
2.8K
128K
¥108 / ¥432输入/输出
172
CO
command-a-03-2025
command-a-03-2025Cohere
48.0
3K
256K
¥18 / ¥72输入/输出
173
Oo3-mini
o3-miniOpenai
47.7
3.4K
200K
¥7.92 / ¥31.7输入/输出
174
TEhunyuan-turbos-20250226
hunyuan-turbos-20250226Tencent
47.4
203
131K
¥0 / ¥0输入/输出
175
TEhunyuan-standard-2025-02-10
hunyuan-standard-2025-02-10Tencent
47.1
340
-
-
176
UNyi-lightning
-
46.8
2.7K
12K
¥1.44 / ¥1.44输入/输出
177
Ddeepseek-v2.5-1210
deepseek-v2.5-1210Deepseek
46.5
446
1M
¥1.01 / ¥2.02输入/输出
178
Oo1-mini
o1-miniOpenai
46.2
4.3K
128K
¥7.92 / ¥31.7输入/输出
179
Aqwen2.5-plus-1127
qwen2.5-plus-1127Alibaba
45.9
621
-
-
180
Ogpt-oss-20b
gpt-oss-20bOpenai
45.6
488
131K
¥0.32 / ¥1.3输入/输出
181
Ggemma-3n-e4b-it
gemma-3n-e4b-itGoogle
45.3
1.2K
128K
¥0 / ¥0输入/输出
182
Aclaude-3-7-sonnet-20250219-thinking-32k
claude-3-7-sonnet-20250219-thinking-32kAnthropic
45.0
2K
-
-
183
UNathene-v2-chat
-
44.7
1.8K
-
-
184
AI
olmo-3.1-32b-instruct
olmo-3.1-32b-instructAllenai
44.4
529
200K
¥14.4 / ¥57.6输入/输出
185
Aclaude-3-7-sonnet-20250219
claude-3-7-sonnet-20250219Anthropic
44.1
2.2K
200K
¥21.6 / ¥108输入/输出
186
AIolmo-3-32b-think
olmo-3-32b-thinkAllenai
43.8
261
128K
¥2.16 / ¥3.24输入/输出
187
Zglm-4-plus
glm-4-plusZai
43.5
2.4K
128K
¥54 / ¥54输入/输出
188
Ggemini-1.5-flash-002
gemini-1.5-flash-002Google
43.2
3K
2M
¥0.54 / ¥2.2输入/输出
189
Xgrok-2-2024-08-13
grok-2-2024-08-13Xai
42.9
5.3K
1M
¥9 / ¥18输入/输出
190
Ddeepseek-v2.5
deepseek-v2.5Deepseek
42.6
2.2K
1M
¥1.01 / ¥2.02输入/输出
191
NVllama-3.3-nemotron-49b-super-v1
llama-3.3-nemotron-49b-super-v1Nvidia
42.2
211
131K
¥0 / ¥0输入/输出
192
Ogpt-4o-2024-05-13
gpt-4o-2024-05-13Openai
41.9
11.4K
128K
¥36 / ¥108输入/输出
193
TEhunyuan-large-vision
hunyuan-large-visionTencent
41.6
255
-
-
194
Ggemini-1.5-pro-001
gemini-1.5-pro-001Google
41.3
8.9K
-
-
195
Ggemini-advanced-0514
gemini-advanced-0514Google
41.0
5.9K
-
-
196
Mllama-4-maverick-17b-128e-instruct
llama-4-maverick-17b-128e-instructMeta
40.7
2.1K
1M
¥1.8 / ¥6.26输入/输出
197
Aqwen2.5-72b-instruct
qwen2.5-72b-instructAlibaba
40.4
3.3K
131K
¥4.13 / ¥12.4输入/输出
198
Ogpt-4.1-nano-2025-04-14
gpt-4.1-nano-2025-04-14Openai
40.1
246
1.05M
¥14.4 / ¥57.6输入/输出
199
Aclaude-3-5-sonnet-20241022
claude-3-5-sonnet-20241022Anthropic
39.8
6.6K
200K
¥21.6 / ¥108输入/输出
200
Aclaude-3-5-sonnet-20240620
claude-3-5-sonnet-20240620Anthropic
39.5
8.1K
200K
¥21.6 / ¥108输入/输出
201
Ogpt-4o-mini-2024-07-18
gpt-4o-mini-2024-07-18Openai
39.2
5.8K
128K
¥1.08 / ¥4.32输入/输出
202
NVllama-3.1-nemotron-70b-instruct
llama-3.1-nemotron-70b-instructNvidia
38.9
723
128K
¥0 / ¥0输入/输出
203
Xgrok-2-mini-2024-08-13
grok-2-mini-2024-08-13Xai
38.6
4.5K
1M
¥9 / ¥18输入/输出
204
Mllama-4-scout-17b-16e-instruct
llama-4-scout-17b-16e-instructMeta
38.3
1.6K
128K
¥1.44 / ¥5.62输入/输出
205
Ogpt-4o-2024-08-06
gpt-4o-2024-08-06Openai
38.0
3.8K
128K
¥18 / ¥72输入/输出
206
Aqwen-max-0919
qwen-max-0919Alibaba
37.7
1.4K
131K
¥2.48 / ¥9.91输入/输出
207
AIolmo-3.1-32b-think
olmo-3.1-32b-thinkAllenai
37.4
491
200K
¥14.4 / ¥57.6输入/输出
208
AIllama-3.1-tulu-3-70b
llama-3.1-tulu-3-70bAllenai
37.1
224
-
-
209
Aclaude-3-opus-20240229
claude-3-opus-20240229Anthropic
36.8
23.3K
200K
¥108 / ¥540输入/输出
210
MAmistral-small-3.1-24b-instruct-2503
mistral-small-3.1-24b-instruct-2503Mistral
36.5
1.7K
262K
¥2.88 / ¥14.4输入/输出
211
IB
ibm-granite-h-small
ibm-granite-h-smallIbm
36.2
219
-
-
212
Aamazon-nova-pro-v1.0
amazon-nova-pro-v1.0Amazon
35.9
1.6K
300K
¥5.76 / ¥23输入/输出
213
Ogpt-4-1106-preview
gpt-4-1106-previewOpenai
35.6
9.2K
8.19K
¥216 / ¥432输入/输出
214
Mllama-3.1-405b-instruct-bf16
llama-3.1-405b-instruct-bf16Meta
35.3
3.1K
128K
¥0 / ¥0输入/输出
215
Ogpt-4-turbo-2024-04-09
gpt-4-turbo-2024-04-09Openai
35.0
10.8K
128K
¥72 / ¥216输入/输出
216
TEhunyuan-standard-256k
hunyuan-standard-256kTencent
34.7
305
-
-
217
UNreka-core-20240904
-
34.3
598
-
-
218
MAmistral-large-2407
mistral-large-2407Mistral
34.0
3.9K
131K
¥14.4 / ¥43.2输入/输出
219
Aqwen2-72b-instruct
qwen2-72b-instructAlibaba
33.7
4.1K
131K
¥4.13 / ¥12.4输入/输出
220
MAmistral-large-2411
mistral-large-2411Mistral
33.4
1.9K
128K
¥14.4 / ¥43.2输入/输出
221
UNathene-70b-0725
-
33.1
1.7K
-
-
222
Ogpt-4-0125-preview
gpt-4-0125-previewOpenai
32.8
11.4K
8.19K
¥216 / ¥432输入/输出
223
Mllama-3.1-405b-instruct-fp8
llama-3.1-405b-instruct-fp8Meta
32.5
5.2K
128K
¥0 / ¥0输入/输出
224
Ggemini-1.5-flash-001
gemini-1.5-flash-001Google
32.2
7K
2M
¥0.54 / ¥2.2输入/输出
225
Ggemini-1.5-flash-8b-001
gemini-1.5-flash-8b-001Google
31.9
2.9K
2M
¥0.54 / ¥2.2输入/输出
226
Zglm-4-0520
glm-4-0520Zai
31.6
1.2K
128K
¥108 / ¥108输入/输出
227
COcommand-r-plus-08-2024
command-r-plus-08-2024Cohere
31.3
845
128K
¥18 / ¥72输入/输出
228
Aamazon-nova-lite-v1.0
amazon-nova-lite-v1.0Amazon
31.0
1.3K
300K
¥0.43 / ¥1.73输入/输出
229
MAmagistral-medium-2506
magistral-medium-2506Mistral
30.7
556
128K
¥14.4 / ¥36输入/输出
230
UNgemma-2-9b-it-simpo
-
30.4
753
8.19K
¥1.44 / ¥1.44输入/输出
231
Aclaude-3-5-haiku-20241022
claude-3-5-haiku-20241022Anthropic
30.1
4.2K
200K
¥5.76 / ¥28.8输入/输出
232
Aqwen2.5-coder-32b-instruct
qwen2.5-coder-32b-instructAlibaba
29.8
528
131K
¥2.07 / ¥6.2输入/输出
233
Ggemma-2-27b-it
gemma-2-27b-itGoogle
29.5
6.9K
8.19K
¥0.58 / ¥0.58输入/输出
234
UNreka-flash-20240904
-
29.2
607
65.5K
¥0.72 / ¥1.44输入/输出
235
Aqwq-32b-preview
qwq-32b-previewAlibaba
28.9
206
131K
¥2.07 / ¥6.2输入/输出
236
Mllama-3.3-70b-instruct
llama-3.3-70b-instructMeta
28.6
3.4K
128K
¥0 / ¥0输入/输出
237
Mllama-3.1-70b-instruct
llama-3.1-70b-instructMeta
28.3
4.8K
131K
¥2.88 / ¥2.88输入/输出
238
NVnemotron-4-340b-instruct
nemotron-4-340b-instructNvidia
28.0
2.4K
-
-
239
UNyi-1.5-34b-chat
-
27.7
2.9K
-
-
240
M
phi-4
phi-4Microsoft
27.4
1.5K
128K
¥0.9 / ¥3.6输入/输出
241
COc4ai-aya-expanse-32b
c4ai-aya-expanse-32bCohere
27.1
2.4K
-
-
242
Aamazon-nova-micro-v1.0
amazon-nova-micro-v1.0Amazon
26.7
1.3K
128K
¥0.25 / ¥1.01输入/输出
243
Aqwen1.5-110b-chat
qwen1.5-110b-chatAlibaba
26.4
2.9K
-
-
244
MAmistral-small-24b-instruct-2501
mistral-small-24b-instruct-2501Mistral
26.1
1.1K
262K
¥2.88 / ¥14.4输入/输出
245
UNjamba-1.5-large
-
25.8
675
256K
¥0 / ¥0输入/输出
246
Ddeepseek-coder-v2
deepseek-coder-v2Deepseek
25.5
1.7K
1M
¥1.01 / ¥2.02输入/输出
247
UNinternlm2_5-20b-chat
-
25.2
959
-
-
248
MAministral-8b-2410
ministral-8b-2410Mistral
24.9
478
128K
¥0.72 / ¥0.72输入/输出
249
AIolmo-2-0325-32b-instruct
olmo-2-0325-32b-instructAllenai
24.6
229
-
-
250
COcommand-r-plus
command-r-plusCohere
24.3
10.5K
128K
¥18 / ¥72输入/输出
251
Aclaude-3-sonnet-20240229
claude-3-sonnet-20240229Anthropic
24.0
15.6K
200K
¥21.6 / ¥108输入/输出
252
Aqwen1.5-72b-chat
qwen1.5-72b-chatAlibaba
23.7
4.2K
-
-
253
Ggemma-2-9b-it
gemma-2-9b-itGoogle
23.4
5K
8.19K
¥1.44 / ¥1.44输入/输出
254
Ogpt-4-0314
gpt-4-0314Openai
23.1
5.8K
8.19K
¥216 / ¥432输入/输出
255
COcommand-r-08-2024
command-r-08-2024Cohere
22.8
834
128K
¥18 / ¥72输入/输出
256
COc4ai-aya-expanse-8b
c4ai-aya-expanse-8bCohere
22.5
618
-
-
257
NVllama-3.1-nemotron-51b-instruct
llama-3.1-nemotron-51b-instructNvidia
22.2
403
128K
¥0 / ¥0输入/输出
258
Aqwen1.5-32b-chat
qwen1.5-32b-chatAlibaba
21.9
3.2K
-
-
259
AIllama-3.1-tulu-3-8b
llama-3.1-tulu-3-8bAllenai
21.6
238
-
-
260
UNyi-34b-chat
-
21.3
1.2K
-
-
261
Aclaude-3-haiku-20240307
claude-3-haiku-20240307Anthropic
21.0
16.7K
200K
¥1.8 / ¥9输入/输出
262
Mllama-3.1-8b-instruct
llama-3.1-8b-instructMeta
20.7
4.4K
131K
¥0.79 / ¥0.79输入/输出
263
Aqwen1.5-14b-chat
qwen1.5-14b-chatAlibaba
20.4
3.2K
-
-
264
COcommand-r
command-rCohere
20.1
8.2K
128K
¥18 / ¥72输入/输出
265
IBgranite-3.1-8b-instruct
granite-3.1-8b-instructIbm
19.8
211
-
-
266
UNreka-flash-21b-20240226-online
-
19.5
2K
-
-
267
Aqwen1.5-7b-chat
qwen1.5-7b-chatAlibaba
19.1
417
-
-
268
IBgranite-3.1-2b-instruct
granite-3.1-2b-instructIbm
18.8
231
-
-
269
Ogpt-4-0613
gpt-4-0613Openai
18.5
8.5K
8.19K
¥216 / ¥432输入/输出
270
UNjamba-1.5-mini
-
18.2
711
256K
¥0 / ¥0输入/输出
271
UNreka-flash-21b-20240226
-
17.9
2.8K
-
-
272
Ggemma-2-2b-it
gemma-2-2b-itGoogle
17.6
3.8K
128K
¥0 / ¥0输入/输出
273
Ddeepseek-llm-67b-chat
deepseek-llm-67b-chatDeepseek
17.3
211
1M
¥1.01 / ¥2.02输入/输出
274
Ggemini-pro-dev-api
gemini-pro-dev-apiGoogle
17.0
1.9K
1.05M
¥14.4 / ¥86.4输入/输出
275
MAmistral-large-2402
mistral-large-2402Mistral
16.7
7.8K
262K
¥2.88 / ¥14.4输入/输出
276
MAmixtral-8x22b-instruct-v0.1
mixtral-8x22b-instruct-v0.1Mistral
16.4
5.7K
64K
¥14.4 / ¥43.2输入/输出
277
Mllama-3-70b-instruct
llama-3-70b-instructMeta
16.1
15.9K
8.19K
¥3.67 / ¥5.33输入/输出
278
UNstarling-lm-7b-beta
-
15.8
2.9K
200K
¥5.4 / ¥18.7输入/输出
279
MAmistral-medium
mistral-mediumMistral
15.5
3K
262K
¥2.88 / ¥14.4输入/输出
280
Mphi-3-medium-4k-instruct
phi-3-medium-4k-instructMicrosoft
15.2
2.8K
4.1K
¥1.22 / ¥4.9输入/输出
281
Ggemini-pro
gemini-proGoogle
14.9
236
1.05M
¥14.4 / ¥86.4输入/输出
282
UNopenchat-3.5-0106
-
14.6
1.5K
-
-
283
UNzephyr-orpo-141b-A35b-v0.1
-
14.3
657
200K
¥108 / ¥432输入/输出
284
UNchatglm-6b
-
14.0
267
200K
¥5.4 / ¥18.7输入/输出
285
Aqwen-14b-chat
qwen-14b-chatAlibaba
13.7
195
32.8K
¥1.04 / ¥3.1输入/输出
286
Mllama-3-8b-instruct
llama-3-8b-instructMeta
13.4
10.8K
8.19K
¥0.29 / ¥0.29输入/输出
287
Ogpt-3.5-turbo-0125
gpt-3.5-turbo-0125Openai
13.1
7.6K
16.4K
¥3.6 / ¥10.8输入/输出
288
UNopenchat-3.5
-
12.8
322
-
-
289
IBgranite-3.0-2b-instruct
granite-3.0-2b-instructIbm
12.5
759
-
-
290
UNdbrx-instruct-preview
-
12.2
5K
-
-
291
UNsnowflake-arctic-instruct
-
11.9
3.1K
-
-
292
UNchatglm3-6b
-
11.6
189
200K
¥5.4 / ¥18.7输入/输出
293
IBgranite-3.0-8b-instruct
granite-3.0-8b-instructIbm
11.2
701
-
-
294
Mphi-3-small-8k-instruct
phi-3-small-8k-instructMicrosoft
10.9
2.4K
8.19K
¥1.08 / ¥4.32输入/输出
295
Ggemma-1.1-7b-it
gemma-1.1-7b-itGoogle
10.6
3.2K
-
-
296
MAmixtral-8x7b-instruct-v0.1
mixtral-8x7b-instruct-v0.1Mistral
10.3
8.3K
32K
¥5.04 / ¥5.04输入/输出
297
Mwizardlm-70b
wizardlm-70bMicrosoft
10.0
334
-
-
298
UNstarling-lm-7b-alpha
-
9.7
858
200K
¥5.4 / ¥18.7输入/输出
299
UNvicuna-13b
-
9.4
1.2K
-
-
300
UNvicuna-33b
-
9.1
1.4K
-
-
301
Ggemma-7b-it
gemma-7b-itGoogle
8.8
1K
-
-
302
Mphi-3-mini-4k-instruct-june-2024
phi-3-mini-4k-instruct-june-2024Microsoft
8.5
1.2K
4.1K
¥0.94 / ¥3.74输入/输出
303
Aqwen1.5-4b-chat
qwen1.5-4b-chatAlibaba
8.2
1K
-
-
304
Mwizardlm-13b
wizardlm-13bMicrosoft
7.9
287
-
-
305
Mphi-3-mini-4k-instruct
phi-3-mini-4k-instructMicrosoft
7.6
2.3K
4.1K
¥0.94 / ¥3.74输入/输出
306
Mllama-3.2-3b-instruct
llama-3.2-3b-instructMeta
7.3
721
131K
¥0.22 / ¥0.35输入/输出
307
Mphi-3-mini-128k-instruct
phi-3-mini-128k-instructMicrosoft
7.0
2K
128K
¥0.94 / ¥3.74输入/输出
308
UNopenhermes-2.5-mistral-7b
-
6.7
205
1M
¥36 / ¥180输入/输出
309
AIolmo-7b-instruct
olmo-7b-instructAllenai
6.4
722
-
-
310
UNtulu-2-dpo-70b
-
6.1
274
-
-
311
Ogpt-3.5-turbo-1106
gpt-3.5-turbo-1106Openai
5.8
708
16.4K
¥7.2 / ¥14.4输入/输出
312
Ggemma-1.1-2b-it
gemma-1.1-2b-itGoogle
5.5
1.3K
-
-
313
MAmistral-7b-instruct-v0.2
mistral-7b-instruct-v0.2Mistral
5.2
2K
262K
¥2.88 / ¥14.4输入/输出
314
Mllama-2-13b-chat
llama-2-13b-chatMeta
4.9
1.2K
-
-
315
Mllama-2-70b-chat
llama-2-70b-chatMeta
4.6
3.6K
-
-
316
Ggemma-2b-it
gemma-2b-itGoogle
4.3
598
-
-
317
UNvicuna-7b
-
4.0
335
-
-
318
Mcodellama-34b-instruct
codellama-34b-instructMeta
3.6
249
-
-
319
Mllama-2-7b-chat
llama-2-7b-chatMeta
3.3
956
128K
¥4.03 / ¥48输入/输出
320
UNzephyr-7b-beta
-
3.0
373
-
-
321
Mllama-3.2-1b-instruct
llama-3.2-1b-instructMeta
2.7
674
16.4K
¥0.07 / ¥0.08输入/输出
322
UNmpt-7b-chat
-
2.4
178
-
-
323
MAmistral-7b-instruct
mistral-7b-instructMistral
2.1
274
262K
¥2.88 / ¥14.4输入/输出
324
UNRWKV-4-Raven-14B
-
1.8
218
-
-
325
Gpalm-2
palm-2Google
1.5
355
-
-
326
UNkoala-13b
-
1.2
374
-
-
327
UNdolly-v2-12b
-
0.9
177
-
-
328
UNoasst-pythia-12b
-
0.6
321
-
-
329
UNalpaca-13b
-
0.3
263
-
-
330
UNfastchat-t5-3b
-
0.0
224
-
-
gpt-5.5 为什么排第一
gpt-5.5 当前排名第 1，厂商为 openai，百分制分数 100.0，样本量 808。如果你的任务与本榜单口径一致，可以优先把它作为候选模型，再结合价格、上下文长度和可用性做最终选择。
不要只看第一名
先选择最接近真实任务的排行榜，再比较 Top 模型的分数和样本量。分数越高说明同一榜单内偏好表现越强；样本量越高通常结果更稳定。最后再结合价格、上下文长度、开源闭源和厂商可用性筛选。
继续比较相近能力
中文常见问题
中文排行榜看什么指标？
主要看排名、百分制分数、样本量和来源。分数用于快速比较同一榜单内模型表现，样本量用于判断结果稳定性。
为什么不同榜单不能直接混合成总分？
不同榜单的任务、样本和评测口径不同，模力榜默认只在同一榜单内排序，避免把写作、代码、图像等能力强行合并。
中文模型应该怎么选？
优先看与你任务最接近的榜单，再结合价格、上下文长度、开源闭源和厂商可用性。排名靠前不代表适合所有预算和部署方式。
榜单多久更新？
页面展示的是最新成功采集的公开榜单数据。当前优先使用 LMArena leaderboard dataset，并在页面来源中保留原始链接。