1
A
claude-opus-4-6-thinking
claude-opus-4-6-thinkingAnthropic
100.0
2.6K
1M
¥36 / ¥180输入/输出
对话 · 文本 · 法律与政务排行榜
基于公开偏好评测数据展示 文本 / 法律与政务 榜单，每个榜单独立排序。
法律与政务模型怎么选？
法律与政务排行榜用于回答“法律与政务哪个 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 claude-opus-4-6-thinking，厂商为 anthropic，百分制分数 100.0，样本量 2.6K。 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。
claude-opus-4-6-thinkingclaude-opus-4-6claude-opus-4-7-thinkingmuse-sparkgemini-3-pro
2
Aclaude-opus-4-6
claude-opus-4-6Anthropic
99.7
2.7K
1M
¥36 / ¥180输入/输出
3
Aclaude-opus-4-7-thinking
claude-opus-4-7-thinkingAnthropic
99.4
1.6K
1M
¥36 / ¥180输入/输出
4
M
muse-spark
muse-sparkMeta
99.1
876
-
-
5
G
gemini-3-pro
gemini-3-proGoogle
98.8
2.9K
1.05M
¥14.4 / ¥86.4输入/输出
6
Ggemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
98.5
3.3K
1.05M
¥14.4 / ¥86.4输入/输出
7
Ggemini-3.5-flash
gemini-3.5-flashGoogle
98.2
689
1.05M
¥10.8 / ¥64.8输入/输出
8
O
gpt-5.4-high
gpt-5.4-highOpenai
97.9
2.2K
1.05M
¥18 / ¥108输入/输出
9
A
qwen3.5-max-preview
qwen3.5-max-previewAlibaba
97.6
1.6K
-
-
10
Ggemini-2.5-pro
gemini-2.5-proGoogle
97.3
8.7K
1.05M
¥9 / ¥72输入/输出
11
Ogpt-5.5-high
gpt-5.5-highOpenai
97.0
1.3K
1.05M
¥36 / ¥216输入/输出
12
Aclaude-opus-4-7
claude-opus-4-7Anthropic
96.7
1.6K
1M
¥36 / ¥180输入/输出
13
Ggemini-3-flash
gemini-3-flashGoogle
96.4
2.3K
1.05M
¥3.6 / ¥21.6输入/输出
14
Aqwen3.7-max-preview
qwen3.7-max-previewAlibaba
96.1
292
1M
¥18 / ¥54输入/输出
15
B
ernie-5.1
ernie-5.1Baidu
95.8
1.1K
119K
¥5.4 / ¥21.6输入/输出
16
MI
mimo-v2.5-pro
mimo-v2.5-proXiaomi
95.5
1.2K
1.05M
¥7.2 / ¥21.6输入/输出
17
Z
glm-5.1
glm-5.1Zai
95.2
997
200K
¥0 / ¥0输入/输出
18
Ogpt-5.4
gpt-5.4Openai
94.9
2.2K
1.05M
¥18 / ¥108输入/输出
19
Ogpt-5.5
gpt-5.5Openai
94.6
1.2K
1.05M
¥36 / ¥216输入/输出
20
Aclaude-sonnet-4-6
claude-sonnet-4-6Anthropic
94.3
2.1K
1M
¥21.6 / ¥108输入/输出
21
D
deepseek-v4-pro-thinking
deepseek-v4-pro-thinkingDeepseek
94.0
1.2K
1M
¥3.13 / ¥6.26输入/输出
22
A
amazon-nova-experimental-chat-26-02-10
amazon-nova-experimental-chat-26-02-10Amazon
93.7
247
-
-
23
Bernie-5.0-preview-1022
ernie-5.0-preview-1022Baidu
93.4
322
128K
¥7.92 / ¥14.4输入/输出
24
Ddeepseek-v3.1-terminus-thinking
deepseek-v3.1-terminus-thinkingDeepseek
93.1
262
128K
¥1.8 / ¥5.04输入/输出
25
B
dola-seed-2.0-pro
dola-seed-2.0-proBytedance
92.8
2.7K
-
-
26
Ogpt-5.1-high
gpt-5.1-highOpenai
92.5
2.9K
400K
¥9 / ¥72输入/输出
27
Aclaude-opus-4-5-20251101
claude-opus-4-5-20251101Anthropic
92.2
4.8K
200K
¥36 / ¥180输入/输出
28
Ddeepseek-v4-pro
deepseek-v4-proDeepseek
91.9
1.2K
1M
¥3.13 / ¥6.26输入/输出
29
M
kimi-k2.6
kimi-k2.6Moonshot
91.6
1.1K
262K
¥6.84 / ¥28.8输入/输出
30
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
91.3
4.1K
1.05M
¥3.6 / ¥21.6输入/输出
31
X
grok-4.20-multi-agent-beta-0309
grok-4.20-multi-agent-beta-0309Xai
91.0
2.2K
2M
¥14.4 / ¥43.2输入/输出
32
Ggemma-4-26b-a4b
gemma-4-26b-a4bGoogle
90.7
386
262K
¥0.94 / ¥2.88输入/输出
33
Aclaude-opus-4-5-20251101-thinking-32k
claude-opus-4-5-20251101-thinking-32kAnthropic
90.4
2.7K
200K
¥108 / ¥540输入/输出
34
Zglm-4.6
glm-4.6Zai
90.1
2.4K
205K
¥4.32 / ¥15.8输入/输出
35
Zglm-5
glm-5Zai
89.8
1.7K
205K
¥7.2 / ¥23输入/输出
36
Bernie-5.0-preview-1203
ernie-5.0-preview-1203Baidu
89.5
763
128K
¥7.92 / ¥14.4输入/输出
37
Aclaude-sonnet-4-5-20250929
claude-sonnet-4-5-20250929Anthropic
89.2
5.4K
200K
¥21.6 / ¥108输入/输出
38
MA
mistral-large-3
mistral-large-3Mistral
88.9
3K
262K
¥3.6 / ¥10.8输入/输出
39
Ddeepseek-v4-flash-thinking
deepseek-v4-flash-thinkingDeepseek
88.6
1.2K
1M
¥1.01 / ¥2.02输入/输出
40
Ggemma-4-31b
gemma-4-31bGoogle
88.3
428
262K
¥3.24 / ¥7.2输入/输出
41
Xgrok-4.1
grok-4.1Xai
88.0
4.7K
200K
¥14.4 / ¥72输入/输出
42
Zglm-4.7
glm-4.7Zai
87.7
958
205K
¥0 / ¥0输入/输出
43
Aqwen3-vl-235b-a22b-instruct
qwen3-vl-235b-a22b-instructAlibaba
87.3
753
128K
¥2.16 / ¥8.64输入/输出
44
Xgrok-4.20-beta-0309-reasoning
grok-4.20-beta-0309-reasoningXai
87.0
2.2K
2M
¥14.4 / ¥43.2输入/输出
45
MImimo-v2-pro
mimo-v2-proXiaomi
86.7
1.6K
1.05M
¥7.2 / ¥21.6输入/输出
46
Ochatgpt-4o-latest-20250326
chatgpt-4o-latest-20250326Openai
86.4
5.3K
128K
¥18 / ¥72输入/输出
47
Aqwen3.6-max-preview
qwen3.6-max-previewAlibaba
86.1
330
246K
¥9.5 / ¥56.9输入/输出
48
Xgrok-3-preview-02-24
grok-3-preview-02-24Xai
85.8
1.9K
1M
¥9 / ¥18输入/输出
49
Xgrok-4.1-thinking
grok-4.1-thinkingXai
85.5
4.6K
200K
¥14.4 / ¥72输入/输出
50
MAmistral-medium-2508
mistral-medium-2508Mistral
85.2
6.4K
262K
¥2.88 / ¥14.4输入/输出
51
Ogpt-5.1
gpt-5.1Openai
84.9
3.1K
400K
¥9 / ¥72输入/输出
52
Bernie-5.0-0110
ernie-5.0-0110Baidu
84.6
2.5K
128K
¥7.92 / ¥14.4输入/输出
53
Xgrok-4.20-beta1
grok-4.20-beta1Xai
84.3
1.8K
2M
¥14.4 / ¥43.2输入/输出
54
Aqwen3.6-plus
qwen3.6-plusAlibaba
84.0
1.3K
1M
¥3.6 / ¥21.6输入/输出
55
Ddeepseek-v4-flash
deepseek-v4-flashDeepseek
83.7
1.2K
1M
¥1.01 / ¥2.02输入/输出
56
Zglm-4.5
glm-4.5Zai
83.4
1.5K
131K
¥4.32 / ¥15.8输入/输出
57
Mkimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
83.1
2.7K
262K
¥4.32 / ¥21.6输入/输出
58
Aclaude-sonnet-4-5-20250929-thinking-32k
claude-sonnet-4-5-20250929-thinking-32kAnthropic
82.8
5.3K
200K
¥21.6 / ¥108输入/输出
59
Aqwen3.5-397b-a17b
qwen3.5-397b-a17bAlibaba
82.5
2.3K
262K
¥3.1 / ¥18.6输入/输出
60
Ogpt-5.2-chat-latest-20260210
gpt-5.2-chat-latest-20260210Openai
82.2
2.4K
400K
¥12.6 / ¥101输入/输出
61
Aqwen3-next-80b-a3b-instruct
qwen3-next-80b-a3b-instructAlibaba
81.9
1.4K
131K
¥1.04 / ¥4.13输入/输出
62
Aqwen3-max-preview
qwen3-max-previewAlibaba
81.6
1.7K
262K
¥6.2 / ¥24.8输入/输出
63
Aamazon-nova-experimental-chat-12-10
amazon-nova-experimental-chat-12-10Amazon
81.3
256
-
-
64
Ogpt-4.5-preview-2025-02-27
gpt-4.5-preview-2025-02-27Openai
81.0
701
8.19K
¥216 / ¥432输入/输出
65
Ggemini-2.5-flash
gemini-2.5-flashGoogle
80.7
8.5K
1.05M
¥2.16 / ¥18输入/输出
66
Mkimi-k2.5-instant
kimi-k2.5-instantMoonshot
80.4
517
262K
¥4.32 / ¥21.6输入/输出
67
Aamazon-nova-experimental-chat-11-10
amazon-nova-experimental-chat-11-10Amazon
80.1
1.8K
-
-
68
Ogpt-5-chat
gpt-5-chatOpenai
79.8
2K
400K
¥9 / ¥72输入/输出
69
Aqwen3-235b-a22b-instruct-2507
qwen3-235b-a22b-instruct-2507Alibaba
79.5
6.4K
128K
¥2.09 / ¥8.23输入/输出
70
Ogpt-5.2
gpt-5.2Openai
79.2
3.5K
400K
¥12.6 / ¥101输入/输出
71
Xgrok-4-0709
grok-4-0709Xai
78.9
2.7K
256K
¥21.6 / ¥108输入/输出
72
Oo3-2025-04-16
o3-2025-04-16Openai
78.6
3.8K
200K
¥14.4 / ¥57.6输入/输出
73
Ggemini-2.5-flash-preview-09-2025
gemini-2.5-flash-preview-09-2025Google
78.3
2.2K
1M
¥2.16 / ¥18输入/输出
74
Xgrok-4-fast-reasoning
grok-4-fast-reasoningXai
78.0
1.2K
2M
¥1.44 / ¥3.6输入/输出
75
Ogpt-5.2-high
gpt-5.2-highOpenai
77.7
3.4K
400K
¥12.6 / ¥101输入/输出
76
TE
hunyuan-hy3-preview
hunyuan-hy3-previewTencent
77.4
441
256K
¥0 / ¥0输入/输出
77
Ddeepseek-v3.2
deepseek-v3.2Deepseek
77.1
3.3K
128K
¥2.09 / ¥3.1输入/输出
78
Aqwen3.5-122b-a10b
qwen3.5-122b-a10bAlibaba
76.8
2.1K
262K
¥2.88 / ¥23输入/输出
79
Ddeepseek-v3.2-thinking
deepseek-v3.2-thinkingDeepseek
76.5
2.9K
128K
¥2.09 / ¥3.1输入/输出
80
Ogpt-5.4-mini-high
gpt-5.4-mini-highOpenai
76.2
2K
400K
¥5.4 / ¥32.4输入/输出
81
Ogpt-5-high
gpt-5-highOpenai
75.9
1.9K
400K
¥9 / ¥72输入/输出
82
Ddeepseek-v3.2-exp-thinking
deepseek-v3.2-exp-thinkingDeepseek
75.6
521
128K
¥0 / ¥0输入/输出
83
Ddeepseek-r1-0528
deepseek-r1-0528Deepseek
75.3
1.4K
164K
¥3.6 / ¥15.5输入/输出
84
TEhunyuan-t1-20250711
hunyuan-t1-20250711Tencent
75.0
273
131K
¥0 / ¥0输入/输出
85
Ogpt-5.5-instant
gpt-5.5-instantOpenai
74.7
2.1K
400K
¥9 / ¥72输入/输出
86
Ddeepseek-v3.1
deepseek-v3.1Deepseek
74.4
1K
128K
¥1.44 / ¥5.04输入/输出
87
Aclaude-opus-4-1-20250805-thinking-16k
claude-opus-4-1-20250805-thinking-16kAnthropic
74.1
3.2K
200K
¥108 / ¥540输入/输出
88
Ddeepseek-v3.1-thinking
deepseek-v3.1-thinkingDeepseek
73.8
780
128K
¥1.44 / ¥5.04输入/输出
89
Mkimi-k2-thinking-turbo
kimi-k2-thinking-turboMoonshot
73.5
4.3K
262K
¥17.3 / ¥72输入/输出
90
Aclaude-opus-4-1-20250805
claude-opus-4-1-20250805Anthropic
73.2
5.3K
200K
¥108 / ¥540输入/输出
91
M
longcat-flash-chat
longcat-flash-chatMeituan
72.9
778
128K
¥1.08 / ¥10.8输入/输出
92
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
72.6
2.7K
1.05M
¥1.8 / ¥10.8输入/输出
93
MImimo-v2-flash (non-thinking)
mimo-v2-flash (non-thinking)Xiaomi
72.3
3.1K
262K
¥0.72 / ¥2.16输入/输出
94
Mlongcat-flash-chat-2602-exp
longcat-flash-chat-2602-expMeituan
72.0
1.7K
128K
¥1.08 / ¥10.8输入/输出
95
M
minimax-m2.1-preview
minimax-m2.1-previewMinimax
71.7
1.2K
205K
¥0 / ¥0输入/输出
96
Xgrok-4-fast-chat
grok-4-fast-chatXai
71.4
436
2M
¥1.44 / ¥3.6输入/输出
97
Aqwen3-vl-235b-a22b-thinking
qwen3-vl-235b-a22b-thinkingAlibaba
71.1
511
131K
¥2.06 / ¥8.26输入/输出
98
Ddeepseek-v3.2-exp
deepseek-v3.2-expDeepseek
70.8
782
128K
¥0 / ¥0输入/输出
99
MImimo-v2.5
mimo-v2.5Xiaomi
70.5
1.2K
1.05M
¥2.88 / ¥14.4输入/输出
100
ST
step-3.5-flash
step-3.5-flashStepfun
70.2
2.5K
256K
¥0.69 / ¥2.07输入/输出
101
Aqwen3-235b-a22b-thinking-2507
qwen3-235b-a22b-thinking-2507Alibaba
69.9
539
131K
¥2.07 / ¥8.26输入/输出
102
Ddeepseek-v3.1-terminus
deepseek-v3.1-terminusDeepseek
69.6
271
128K
¥1.8 / ¥5.04输入/输出
103
Aqwen3.5-27b
qwen3.5-27bAlibaba
69.3
2K
262K
¥2.16 / ¥17.3输入/输出
104
Aqwen3-max-2025-09-23
qwen3-max-2025-09-23Alibaba
69.0
570
258K
¥6.19 / ¥24.7输入/输出
105
MImimo-v2-flash (thinking)
mimo-v2-flash (thinking)Xiaomi
68.7
856
262K
¥0.72 / ¥2.16输入/输出
106
Mkimi-k2-0905-preview
kimi-k2-0905-previewMoonshot
68.4
781
262K
¥4.32 / ¥18输入/输出
107
Xgrok-4-1-fast-reasoning
grok-4-1-fast-reasoningXai
68.1
3.9K
2M
¥1.44 / ¥3.6输入/输出
108
Mminimax-m2.7
minimax-m2.7Minimax
67.8
1.7K
205K
¥0 / ¥0输入/输出
109
Ogpt-4.1-2025-04-14
gpt-4.1-2025-04-14Openai
67.5
3.3K
1.05M
¥14.4 / ¥57.6输入/输出
110
Aqwen3.5-35b-a3b
qwen3.5-35b-a3bAlibaba
67.2
2.1K
262K
¥1.8 / ¥14.4输入/输出
111
Zglm-4.6v
glm-4.6vZai
66.9
203
128K
¥2.16 / ¥6.48输入/输出
112
Xgrok-4.3
grok-4.3Xai
66.6
1.2K
1M
¥9 / ¥18输入/输出
113
Aqwen3-235b-a22b-no-thinking
qwen3-235b-a22b-no-thinkingAlibaba
66.3
2.6K
131K
¥2.07 / ¥8.26输入/输出
114
Aqwen3.5-flash
qwen3.5-flashAlibaba
66.0
2.2K
1M
¥1.24 / ¥12.4输入/输出
115
MImimo-v2-omni
mimo-v2-omniXiaomi
65.7
199
262K
¥2.88 / ¥14.4输入/输出
116
Aclaude-haiku-4-5-20251001
claude-haiku-4-5-20251001Anthropic
65.4
5.5K
200K
¥7.2 / ¥36输入/输出
117
Ggemini-2.5-flash-lite-preview-09-2025-no-thinking
gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle
65.1
3.2K
1.05M
¥0.72 / ¥2.88输入/输出
118
NV
nvidia-nemotron-3-super-120b-a12b
nvidia-nemotron-3-super-120b-a12bNvidia
64.8
512
262K
¥1.44 / ¥5.76输入/输出
119
Ogpt-5.3-chat-latest
gpt-5.3-chat-latestOpenai
64.5
2.4K
128K
¥12.6 / ¥101输入/输出
120
Aamazon-nova-experimental-chat-10-20
amazon-nova-experimental-chat-10-20Amazon
64.2
814
-
-
121
Xgrok-3-mini-high
grok-3-mini-highXai
63.9
1.2K
128K
¥0 / ¥0输入/输出
122
Zglm-4.5-air
glm-4.5-airZai
63.6
1.9K
131K
¥0 / ¥0输入/输出
123
Aqwen3-30b-a3b-instruct-2507
qwen3-30b-a3b-instruct-2507Alibaba
63.3
1.5K
262K
¥2.16 / ¥3.6输入/输出
124
MAmistral-medium-2505
mistral-medium-2505Mistral
63.0
2.1K
262K
¥2.88 / ¥14.4输入/输出
125
Aamazon-nova-experimental-chat-26-01-10
amazon-nova-experimental-chat-26-01-10Amazon
62.7
264
-
-
126
Ggemma-3-12b-it
gemma-3-12b-itGoogle
62.3
217
128K
¥1.96 / ¥1.96输入/输出
127
Ddeepseek-v3-0324
deepseek-v3-0324Deepseek
62.0
2.9K
75K
¥1.44 / ¥5.76输入/输出
128
Ogpt-5-mini-high
gpt-5-mini-highOpenai
61.7
1.7K
400K
¥1.8 / ¥14.4输入/输出
129
Ggemma-3-27b-it
gemma-3-27b-itGoogle
61.4
2.7K
128K
¥2.15 / ¥2.15输入/输出
130
Aqwen2.5-max
qwen2.5-maxAlibaba
61.1
1.9K
32K
¥11.5 / ¥46输入/输出
131
Aclaude-opus-4-20250514
claude-opus-4-20250514Anthropic
60.8
2.9K
200K
¥108 / ¥540输入/输出
132
Ggemini-2.5-flash-lite-preview-06-17-thinking
gemini-2.5-flash-lite-preview-06-17-thinkingGoogle
60.5
2.1K
65.5K
¥0.72 / ¥2.88输入/输出
133
Ggemini-2.0-flash-001
gemini-2.0-flash-001Google
60.2
2.6K
1.05M
¥1.08 / ¥4.32输入/输出
134
TEhunyuan-turbos-20250416
hunyuan-turbos-20250416Tencent
59.9
741
131K
¥0 / ¥0输入/输出
135
Ddeepseek-r1
deepseek-r1Deepseek
59.6
1.1K
164K
¥5.04 / ¥18输入/输出
136
AG
ling-flash-2.0
ling-flash-2.0Ant Group
59.3
437
131K
¥1.01 / ¥4.1输入/输出
137
Oo1-2024-12-17
o1-2024-12-17Openai
59.0
1.5K
128K
¥108 / ¥432输入/输出
138
Xgrok-3-mini-beta
grok-3-mini-betaXai
58.7
1.5K
1M
¥9 / ¥18输入/输出
139
Aamazon-nova-experimental-chat-10-09
amazon-nova-experimental-chat-10-09Amazon
58.4
208
-
-
140
Mminimax-m2.5
minimax-m2.5Minimax
58.1
2.8K
205K
¥0 / ¥0输入/输出
141
Aclaude-opus-4-20250514-thinking-16k
claude-opus-4-20250514-thinking-16kAnthropic
57.8
2.5K
200K
¥108 / ¥540输入/输出
142
Aqwen3-next-80b-a3b-thinking
qwen3-next-80b-a3b-thinkingAlibaba
57.5
868
131K
¥1.04 / ¥10.3输入/输出
143
Ogpt-5.4-nano-high
gpt-5.4-nano-highOpenai
57.2
2K
400K
¥1.44 / ¥9输入/输出
144
Zglm-4-plus-0111
glm-4-plus-0111Zai
56.9
367
128K
¥72 / ¥72输入/输出
145
Zglm-4.7-flash
glm-4.7-flashZai
56.6
825
200K
¥0 / ¥0输入/输出
146
Aqwen3-coder-480b-a35b-instruct
qwen3-coder-480b-a35b-instructAlibaba
56.3
1.6K
262K
¥6.2 / ¥24.8输入/输出
147
Ogpt-oss-120b
gpt-oss-120bOpenai
56.0
1.9K
131K
¥1.08 / ¥4.32输入/输出
148
Mkimi-k2-0711-preview
kimi-k2-0711-previewMoonshot
55.7
1.8K
131K
¥4.32 / ¥18输入/输出
149
Aqwen3-235b-a22b
qwen3-235b-a22bAlibaba
55.4
1.7K
131K
¥2.07 / ¥8.26输入/输出
150
Anova-2-lite
nova-2-liteAmazon
55.1
891
128K
¥2.38 / ¥19.8输入/输出
151
STstep-1o-turbo-202506
step-1o-turbo-202506Stepfun
54.8
657
-
-
152
Oo4-mini-2025-04-16
o4-mini-2025-04-16Openai
54.5
2.8K
200K
¥7.92 / ¥31.7输入/输出
153
Aqwen-plus-0125
qwen-plus-0125Alibaba
54.2
392
1M
¥0.83 / ¥2.07输入/输出
154
NVnvidia-nemotron-3-nano-30b-a3b-bf16
nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia
53.9
1.2K
131K
¥0 / ¥0输入/输出
155
CO
command-a-03-2025
command-a-03-2025Cohere
53.6
3.5K
256K
¥18 / ¥72输入/输出
156
Oo1-preview
o1-previewOpenai
53.3
1.9K
128K
¥108 / ¥432输入/输出
157
IB
granite-4.1-8b
granite-4.1-8bIbm
53.0
206
131K
¥0.36 / ¥0.72输入/输出
158
Mminimax-m2
minimax-m2Minimax
52.7
429
197K
¥0 / ¥0输入/输出
159
NVnvidia-llama-3.3-nemotron-super-49b-v1.5
nvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia
52.4
233
131K
¥2.88 / ¥2.88输入/输出
160
Ogpt-4.1-mini-2025-04-14
gpt-4.1-mini-2025-04-14Openai
52.1
2.5K
1.05M
¥2.88 / ¥11.5输入/输出
161
Ggemini-2.0-flash-lite-preview-02-05
gemini-2.0-flash-lite-preview-02-05Google
51.8
1.4K
1.05M
¥0.54 / ¥2.16输入/输出
162
UNtrinity-large-thinking
-
51.5
1.8K
262K
¥1.8 / ¥6.48输入/输出
163
Aclaude-sonnet-4-20250514
claude-sonnet-4-20250514Anthropic
51.2
2.7K
200K
¥21.6 / ¥108输入/输出
164
Ddeepseek-v3
deepseek-v3Deepseek
50.9
1.3K
128K
¥0 / ¥0输入/输出
165
Mminimax-m1
minimax-m1Minimax
50.6
2.4K
1M
¥0.95 / ¥9.03输入/输出
166
UNtrinity-large-preview
-
50.3
2K
262K
¥1.8 / ¥6.48输入/输出
167
MAmistral-small-2506
mistral-small-2506Mistral
50.0
1.2K
262K
¥2.88 / ¥14.4输入/输出
168
STstep-3
step-3Stepfun
49.7
416
65.5K
¥1.8 / ¥4.68输入/输出
169
Zglm-4.5v
glm-4.5vZai
49.4
277
64K
¥4.32 / ¥13输入/输出
170
Aqwq-32b
qwq-32bAlibaba
49.1
1.6K
131K
¥2.07 / ¥6.2输入/输出
171
STstep-2-16k-exp-202412
step-2-16k-exp-202412Stepfun
48.8
278
16.4K
¥37.5 / ¥118输入/输出
172
Aclaude-sonnet-4-20250514-thinking-32k
claude-sonnet-4-20250514-thinking-32kAnthropic
48.5
2.3K
200K
¥21.6 / ¥108输入/输出
173
AI
olmo-3.1-32b-instruct
olmo-3.1-32b-instructAllenai
48.2
908
200K
¥14.4 / ¥57.6输入/输出
174
Oo3-mini-high
o3-mini-highOpenai
47.9
1K
200K
¥7.92 / ¥31.7输入/输出
175
Ggemini-1.5-pro-002
gemini-1.5-pro-002Google
47.6
3.3K
-
-
176
UNyi-lightning
-
47.3
1.7K
12K
¥1.44 / ¥1.44输入/输出
177
Ggemma-3-4b-it
gemma-3-4b-itGoogle
47.0
245
128K
¥1.44 / ¥1.44输入/输出
178
Xgrok-2-2024-08-13
grok-2-2024-08-13Xai
46.7
3.8K
1M
¥9 / ¥18输入/输出
179
Aqwen3-32b
qwen3-32bAlibaba
46.4
285
131K
¥2.07 / ¥8.26输入/输出
180
UNintellect-3
-
46.1
398
131K
¥1.44 / ¥7.92输入/输出
181
Oo1-mini
o1-miniOpenai
45.8
3.1K
128K
¥7.92 / ¥31.7输入/输出
182
Ogpt-4o-2024-05-13
gpt-4o-2024-05-13Openai
45.5
6.7K
128K
¥36 / ¥108输入/输出
183
Aqwen3-30b-a3b
qwen3-30b-a3bAlibaba
45.2
1.8K
128K
¥0.79 / ¥7.78输入/输出
184
Ggemma-3n-e4b-it
gemma-3n-e4b-itGoogle
44.9
1.4K
128K
¥0 / ¥0输入/输出
185
Zglm-4-plus
glm-4-plusZai
44.6
1.7K
128K
¥54 / ¥54输入/输出
186
AGring-flash-2.0
ring-flash-2.0Ant Group
44.3
444
131K
¥1.01 / ¥4.1输入/输出
187
Aqwen2.5-plus-1127
qwen2.5-plus-1127Alibaba
44.0
588
-
-
188
Oo3-mini
o3-miniOpenai
43.7
3.6K
200K
¥7.92 / ¥31.7输入/输出
189
Ogpt-4o-mini-2024-07-18
gpt-4o-mini-2024-07-18Openai
43.4
3.9K
128K
¥1.08 / ¥4.32输入/输出
190
Ggemini-advanced-0514
gemini-advanced-0514Google
43.1
3K
-
-
191
Mllama-3.1-405b-instruct-fp8
llama-3.1-405b-instruct-fp8Meta
42.8
3.4K
128K
¥0 / ¥0输入/输出
192
NVllama-3.1-nemotron-70b-instruct
llama-3.1-nemotron-70b-instructNvidia
42.5
489
128K
¥0 / ¥0输入/输出
193
Ggemini-1.5-flash-002
gemini-1.5-flash-002Google
42.2
2.2K
2M
¥0.54 / ¥2.2输入/输出
194
Aclaude-3-7-sonnet-20250219-thinking-32k
claude-3-7-sonnet-20250219-thinking-32kAnthropic
41.9
2.5K
-
-
195
Mllama-3.1-405b-instruct-bf16
llama-3.1-405b-instruct-bf16Meta
41.6
2.3K
128K
¥0 / ¥0输入/输出
196
Ogpt-5-nano-high
gpt-5-nano-highOpenai
41.3
471
400K
¥0.36 / ¥2.88输入/输出
197
Ogpt-4.1-nano-2025-04-14
gpt-4.1-nano-2025-04-14Openai
41.0
382
1.05M
¥14.4 / ¥57.6输入/输出
198
Aclaude-3-7-sonnet-20250219
claude-3-7-sonnet-20250219Anthropic
40.7
2.5K
200K
¥21.6 / ¥108输入/输出
199
UNathene-v2-chat
-
40.4
1.4K
-
-
200
AIolmo-3-32b-think
olmo-3-32b-thinkAllenai
40.1
430
128K
¥2.16 / ¥3.24输入/输出
201
UNathene-70b-0725
-
39.8
1K
-
-
202
Xgrok-2-mini-2024-08-13
grok-2-mini-2024-08-13Xai
39.5
3K
1M
¥9 / ¥18输入/输出
203
TEhunyuan-standard-2025-02-10
hunyuan-standard-2025-02-10Tencent
39.2
288
-
-
204
Aqwen2.5-72b-instruct
qwen2.5-72b-instructAlibaba
38.9
2.4K
131K
¥4.13 / ¥12.4输入/输出
205
Mllama-4-scout-17b-16e-instruct
llama-4-scout-17b-16e-instructMeta
38.6
2K
128K
¥1.44 / ¥5.62输入/输出
206
Mllama-4-maverick-17b-128e-instruct
llama-4-maverick-17b-128e-instructMeta
38.3
2.6K
1M
¥1.8 / ¥6.26输入/输出
207
Mllama-3.3-70b-instruct
llama-3.3-70b-instructMeta
38.0
3.2K
128K
¥0 / ¥0输入/输出
208
Mllama-3.1-70b-instruct
llama-3.1-70b-instructMeta
37.7
3.2K
131K
¥2.88 / ¥2.88输入/输出
209
Aqwen-max-0919
qwen-max-0919Alibaba
37.3
1.1K
131K
¥2.48 / ¥9.91输入/输出
210
Ddeepseek-v2.5
deepseek-v2.5Deepseek
37.0
1.5K
1M
¥1.01 / ¥2.02输入/输出
211
Aamazon-nova-pro-v1.0
amazon-nova-pro-v1.0Amazon
36.7
1.3K
300K
¥5.76 / ¥23输入/输出
212
TEhunyuan-large-2025-02-10
hunyuan-large-2025-02-10Tencent
36.4
252
-
-
213
Ogpt-oss-20b
gpt-oss-20bOpenai
36.1
694
131K
¥0.32 / ¥1.3输入/输出
214
AIolmo-3.1-32b-think
olmo-3.1-32b-thinkAllenai
35.8
636
200K
¥14.4 / ¥57.6输入/输出
215
Ddeepseek-v2.5-1210
deepseek-v2.5-1210Deepseek
35.5
375
1M
¥1.01 / ¥2.02输入/输出
216
Aclaude-3-5-sonnet-20241022
claude-3-5-sonnet-20241022Anthropic
35.2
5.5K
200K
¥21.6 / ¥108输入/输出
217
MAmistral-large-2407
mistral-large-2407Mistral
34.9
2.7K
131K
¥14.4 / ¥43.2输入/输出
218
Ogpt-4o-2024-08-06
gpt-4o-2024-08-06Openai
34.6
2.7K
128K
¥18 / ¥72输入/输出
219
MAmistral-large-2411
mistral-large-2411Mistral
34.3
1.6K
128K
¥14.4 / ¥43.2输入/输出
220
UNreka-core-20240904
-
34.0
371
-
-
221
MAmistral-small-3.1-24b-instruct-2503
mistral-small-3.1-24b-instruct-2503Mistral
33.7
2.2K
262K
¥2.88 / ¥14.4输入/输出
222
Ggemini-1.5-pro-001
gemini-1.5-pro-001Google
33.4
4.8K
-
-
223
UNgemma-2-9b-it-simpo
-
33.1
543
8.19K
¥1.44 / ¥1.44输入/输出
224
COcommand-r-plus-08-2024
command-r-plus-08-2024Cohere
32.8
592
128K
¥18 / ¥72输入/输出
225
Aclaude-3-5-sonnet-20240620
claude-3-5-sonnet-20240620Anthropic
32.5
4.8K
200K
¥21.6 / ¥108输入/输出
226
Ogpt-4-turbo-2024-04-09
gpt-4-turbo-2024-04-09Openai
32.2
5.4K
128K
¥72 / ¥216输入/输出
227
Aclaude-3-opus-20240229
claude-3-opus-20240229Anthropic
31.9
11.1K
200K
¥108 / ¥540输入/输出
228
UNjamba-1.5-large
-
31.6
448
256K
¥0 / ¥0输入/输出
229
Ogpt-4-0125-preview
gpt-4-0125-previewOpenai
31.3
5K
8.19K
¥216 / ¥432输入/输出
230
Aclaude-3-5-haiku-20241022
claude-3-5-haiku-20241022Anthropic
31.0
4.3K
200K
¥5.76 / ¥28.8输入/输出
231
Aqwen2.5-coder-32b-instruct
qwen2.5-coder-32b-instructAlibaba
30.7
273
131K
¥2.07 / ¥6.2输入/输出
232
NVllama-3.1-nemotron-51b-instruct
llama-3.1-nemotron-51b-instructNvidia
30.4
230
128K
¥0 / ¥0输入/输出
233
Ogpt-4-1106-preview
gpt-4-1106-previewOpenai
30.1
5.6K
8.19K
¥216 / ¥432输入/输出
234
COc4ai-aya-expanse-32b
c4ai-aya-expanse-32bCohere
29.8
1.7K
-
-
235
Ggemini-1.5-flash-8b-001
gemini-1.5-flash-8b-001Google
29.5
2.1K
2M
¥0.54 / ¥2.2输入/输出
236
Ggemini-1.5-flash-001
gemini-1.5-flash-001Google
29.2
3.8K
2M
¥0.54 / ¥2.2输入/输出
237
TEhunyuan-large-vision
hunyuan-large-visionTencent
28.9
397
-
-
238
NVnemotron-4-340b-instruct
nemotron-4-340b-instructNvidia
28.6
1.2K
-
-
239
COcommand-r-plus
command-r-plusCohere
28.3
4.4K
128K
¥18 / ¥72输入/输出
240
Zglm-4-0520
glm-4-0520Zai
28.0
556
128K
¥108 / ¥108输入/输出
241
Ggemma-2-27b-it
gemma-2-27b-itGoogle
27.7
4.5K
8.19K
¥0.58 / ¥0.58输入/输出
242
M
phi-4
phi-4Microsoft
27.4
1.3K
128K
¥0.9 / ¥3.6输入/输出
243
Aamazon-nova-lite-v1.0
amazon-nova-lite-v1.0Amazon
27.1
1.1K
300K
¥0.43 / ¥1.73输入/输出
244
MAmagistral-medium-2506
magistral-medium-2506Mistral
26.8
853
128K
¥14.4 / ¥36输入/输出
245
IBibm-granite-h-small
ibm-granite-h-smallIbm
26.5
323
-
-
246
COcommand-r-08-2024
command-r-08-2024Cohere
26.2
569
128K
¥18 / ¥72输入/输出
247
AIolmo-2-0325-32b-instruct
olmo-2-0325-32b-instructAllenai
25.9
202
-
-
248
Mllama-3-70b-instruct
llama-3-70b-instructMeta
25.6
8.3K
8.19K
¥3.67 / ¥5.33输入/输出
249
COc4ai-aya-expanse-8b
c4ai-aya-expanse-8bCohere
25.3
551
-
-
250
UNjamba-1.5-mini
-
25.0
531
256K
¥0 / ¥0输入/输出
251
Aamazon-nova-micro-v1.0
amazon-nova-micro-v1.0Amazon
24.7
1.1K
128K
¥0.25 / ¥1.01输入/输出
252
MAmistral-small-24b-instruct-2501
mistral-small-24b-instruct-2501Mistral
24.4
869
262K
¥2.88 / ¥14.4输入/输出
253
UNreka-flash-20240904
-
24.1
414
65.5K
¥0.72 / ¥1.44输入/输出
254
Ggemma-2-9b-it
gemma-2-9b-itGoogle
23.8
3.2K
8.19K
¥1.44 / ¥1.44输入/输出
255
Aclaude-3-sonnet-20240229
claude-3-sonnet-20240229Anthropic
23.5
6.1K
200K
¥21.6 / ¥108输入/输出
256
MAministral-8b-2410
ministral-8b-2410Mistral
23.2
324
128K
¥0.72 / ¥0.72输入/输出
257
COcommand-r
command-rCohere
22.9
3.1K
128K
¥18 / ¥72输入/输出
258
Mllama-3.1-8b-instruct
llama-3.1-8b-instructMeta
22.6
2.9K
131K
¥0.79 / ¥0.79输入/输出
259
UNyi-1.5-34b-chat
-
22.3
1.5K
-
-
260
UNreka-flash-21b-20240226-online
-
22.0
876
-
-
261
Aqwen2-72b-instruct
qwen2-72b-instructAlibaba
21.7
2.3K
131K
¥4.13 / ¥12.4输入/输出
262
Ogpt-4-0314
gpt-4-0314Openai
21.4
2.9K
8.19K
¥216 / ¥432输入/输出
263
Aclaude-3-haiku-20240307
claude-3-haiku-20240307Anthropic
21.1
6.8K
200K
¥1.8 / ¥9输入/输出
264
Aqwen1.5-110b-chat
qwen1.5-110b-chatAlibaba
20.8
1.5K
-
-
265
MAmistral-large-2402
mistral-large-2402Mistral
20.5
3.3K
262K
¥2.88 / ¥14.4输入/输出
266
UNreka-flash-21b-20240226
-
20.2
1.4K
-
-
267
Aqwen1.5-72b-chat
qwen1.5-72b-chatAlibaba
19.9
2.1K
-
-
268
IBgranite-3.1-8b-instruct
granite-3.1-8b-instructIbm
19.6
215
-
-
269
MAmistral-medium
mistral-mediumMistral
19.3
1.8K
262K
¥2.88 / ¥14.4输入/输出
270
Ggemma-2-2b-it
gemma-2-2b-itGoogle
19.0
2.7K
128K
¥0 / ¥0输入/输出
271
Mllama-3-8b-instruct
llama-3-8b-instructMeta
18.7
5.6K
8.19K
¥0.29 / ¥0.29输入/输出
272
Ggemini-pro-dev-api
gemini-pro-dev-apiGoogle
18.4
970
1.05M
¥14.4 / ¥86.4输入/输出
273
MAmixtral-8x22b-instruct-v0.1
mixtral-8x22b-instruct-v0.1Mistral
18.1
2.8K
64K
¥14.4 / ¥43.2输入/输出
274
Ddeepseek-coder-v2
deepseek-coder-v2Deepseek
17.8
888
1M
¥1.01 / ¥2.02输入/输出
275
Ogpt-4-0613
gpt-4-0613Openai
17.5
4.7K
8.19K
¥216 / ¥432输入/输出
276
UNinternlm2_5-20b-chat
-
17.2
685
-
-
277
UNstarling-lm-7b-beta
-
16.9
878
200K
¥5.4 / ¥18.7输入/输出
278
Aqwq-32b-preview
qwq-32b-previewAlibaba
16.6
214
131K
¥2.07 / ¥6.2输入/输出
279
Aqwen1.5-32b-chat
qwen1.5-32b-chatAlibaba
16.3
1.2K
-
-
280
UNyi-34b-chat
-
16.0
857
-
-
281
UNtulu-2-dpo-70b
-
15.7
377
-
-
282
UNzephyr-orpo-141b-A35b-v0.1
-
15.4
240
200K
¥108 / ¥432输入/输出
283
MAmixtral-8x7b-instruct-v0.1
mixtral-8x7b-instruct-v0.1Mistral
15.1
4K
32K
¥5.04 / ¥5.04输入/输出
284
Mphi-3-medium-4k-instruct
phi-3-medium-4k-instructMicrosoft
14.8
1.5K
4.1K
¥1.22 / ¥4.9输入/输出
285
Mwizardlm-70b
wizardlm-70bMicrosoft
14.5
434
-
-
286
UNstarling-lm-7b-alpha
-
14.2
504
200K
¥5.4 / ¥18.7输入/输出
287
Aqwen1.5-14b-chat
qwen1.5-14b-chatAlibaba
13.9
1K
-
-
288
Ogpt-3.5-turbo-0125
gpt-3.5-turbo-0125Openai
13.6
3.6K
16.4K
¥3.6 / ¥10.8输入/输出
289
Mllama-3.2-3b-instruct
llama-3.2-3b-instructMeta
13.3
506
131K
¥0.22 / ¥0.35输入/输出
290
Mllama-2-70b-chat
llama-2-70b-chatMeta
13.0
2.1K
-
-
291
UNopenchat-3.5
-
12.7
467
-
-
292
Ggemini-pro
gemini-proGoogle
12.3
309
1.05M
¥14.4 / ¥86.4输入/输出
293
UNopenchat-3.5-0106
-
12.0
637
-
-
294
UNdbrx-instruct-preview
-
11.7
1.7K
-
-
295
Aqwen1.5-7b-chat
qwen1.5-7b-chatAlibaba
11.4
230
-
-
296
Mphi-3-small-8k-instruct
phi-3-small-8k-instructMicrosoft
11.1
1.2K
8.19K
¥1.08 / ¥4.32输入/输出
297
Mwizardlm-13b
wizardlm-13bMicrosoft
10.8
365
-
-
298
UNopenhermes-2.5-mistral-7b
-
10.5
275
1M
¥36 / ¥180输入/输出
299
UNvicuna-33b
-
10.2
1.2K
-
-
300
MAmistral-7b-instruct-v0.2
mistral-7b-instruct-v0.2Mistral
9.9
976
262K
¥2.88 / ¥14.4输入/输出
301
UNzephyr-7b-beta
-
9.6
621
-
-
302
Ggemma-1.1-7b-it
gemma-1.1-7b-itGoogle
9.3
1.4K
-
-
303
UNsnowflake-arctic-instruct
-
9.0
1.5K
-
-
304
Ddeepseek-llm-67b-chat
deepseek-llm-67b-chatDeepseek
8.7
300
1M
¥1.01 / ¥2.02输入/输出
305
IBgranite-3.0-8b-instruct
granite-3.0-8b-instructIbm
8.4
428
-
-
306
IBgranite-3.0-2b-instruct
granite-3.0-2b-instructIbm
8.1
435
-
-
307
UNsolar-10.7b-instruct-v1.0
-
7.8
219
128K
¥0 / ¥0输入/输出
308
Mllama-2-13b-chat
llama-2-13b-chatMeta
7.5
1K
-
-
309
Mphi-3-mini-4k-instruct
phi-3-mini-4k-instructMicrosoft
7.2
1.1K
4.1K
¥0.94 / ¥3.74输入/输出
310
Mllama-3.2-1b-instruct
llama-3.2-1b-instructMeta
6.9
489
16.4K
¥0.07 / ¥0.08输入/输出
311
Mphi-3-mini-4k-instruct-june-2024
phi-3-mini-4k-instruct-june-2024Microsoft
6.6
706
4.1K
¥0.94 / ¥3.74输入/输出
312
Mllama-2-7b-chat
llama-2-7b-chatMeta
6.3
760
128K
¥4.03 / ¥48输入/输出
313
Mcodellama-34b-instruct
codellama-34b-instructMeta
6.0
383
-
-
314
UNvicuna-13b
-
5.7
899
-
-
315
Ogpt-3.5-turbo-1106
gpt-3.5-turbo-1106Openai
5.4
944
16.4K
¥7.2 / ¥14.4输入/输出
316
Aqwen-14b-chat
qwen-14b-chatAlibaba
5.1
274
32.8K
¥1.04 / ¥3.1输入/输出
317
AIolmo-7b-instruct
olmo-7b-instructAllenai
4.8
301
-
-
318
Ggemma-7b-it
gemma-7b-itGoogle
4.5
462
-
-
319
UNvicuna-7b
-
4.2
305
-
-
320
MAmistral-7b-instruct
mistral-7b-instructMistral
3.9
487
262K
¥2.88 / ¥14.4输入/输出
321
Ggemma-2b-it
gemma-2b-itGoogle
3.6
273
-
-
322
Aqwen1.5-4b-chat
qwen1.5-4b-chatAlibaba
3.3
390
-
-
323
Mphi-3-mini-128k-instruct
phi-3-mini-128k-instructMicrosoft
3.0
1K
128K
¥0.94 / ¥3.74输入/输出
324
Gpalm-2
palm-2Google
2.7
428
-
-
325
UNstripedhyena-nous-7b
-
2.4
309
-
-
326
Ggemma-1.1-2b-it
gemma-1.1-2b-itGoogle
2.1
578
-
-
327
UNRWKV-4-Raven-14B
-
1.8
190
-
-
328
UNchatglm3-6b
-
1.5
268
200K
¥5.4 / ¥18.7输入/输出
329
UNkoala-13b
-
1.2
248
-
-
330
UNoasst-pythia-12b
-
0.9
266
-
-
331
UNalpaca-13b
-
0.6
230
-
-
332
UNfastchat-t5-3b
-
0.3
184
-
-
333
UNchatglm-6b
-
0.0
195
200K
¥5.4 / ¥18.7输入/输出
claude-opus-4-6-thinking 为什么排第一
claude-opus-4-6-thinking 当前排名第 1，厂商为 anthropic，百分制分数 100.0，样本量 2.6K。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
法律与政务常见问题
法律与政务排行榜看什么指标？
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。
法律与政务模型应该怎么选？
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。