Chat · Text · Software & IT Services Leaderboard

Ranking for Text / Software & IT Services, based on public preference data.

Selection guide

Software & IT Services model ranking guide

Ranking for Text / Software & IT Services, based on public preference data.

claude-opus-4-6-thinkingclaude-opus-4-6claude-opus-4-7-thinkingclaude-opus-4-7qwen3.7-max-preview
Current DirectoryChat · Text · Software & IT Services
Models360
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / Industry Software And It ServicesPublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
claude-opus-4-6-thinking
Anthropic
100.0
12.5K
1M
¥36 / ¥180Input/Output
2
claude-opus-4-6
Anthropic
99.7
13.8K
1M
¥36 / ¥180Input/Output
3
claude-opus-4-7-thinking
Anthropic
99.4
8K
1M
¥36 / ¥180Input/Output
4
claude-opus-4-7
Anthropic
99.2
8.2K
1M
¥36 / ¥180Input/Output
5
qwen3.7-max-preview
Alibaba
98.9
1.6K
1M
¥18 / ¥54Input/Output
6
glm-5.1
Zai
98.6
5.5K
200K
¥0 / ¥0Input/Output
7
gemini-3.5-flash
Google
98.3
3.7K
1.05M
¥10.8 / ¥64.8Input/Output
8
gpt-5.5-high
Openai
98.1
6.4K
1.05M
¥36 / ¥216Input/Output
9
ernie-5.1
Baidu
97.8
5.7K
119K
¥5.4 / ¥21.6Input/Output
10
gpt-5.4-high
Openai
97.5
10.8K
1.05M
¥18 / ¥108Input/Output
11
mimo-v2.5-pro
Xiaomi
97.2
6.2K
1.05M
¥7.2 / ¥21.6Input/Output
12
gemini-3.1-pro-preview
Google
96.9
16.6K
1.05M
¥14.4 / ¥86.4Input/Output
13
claude-sonnet-4-6
Anthropic
96.7
10.4K
1M
¥21.6 / ¥108Input/Output
14
gemini-3-pro
Google
96.4
14.3K
1.05M
¥14.4 / ¥86.4Input/Output
15
qwen3.5-max-preview
Alibaba
96.1
7.8K
-
-
16
muse-spark
Meta
95.8
4.6K
-
-
17
kimi-k2.6
Moonshot
95.5
6.2K
262K
¥6.84 / ¥28.8Input/Output
18
gpt-5.5
Openai
95.3
6.6K
1.05M
¥36 / ¥216Input/Output
19
amazon-nova-experimental-chat-26-02-10
Amazon
95.0
1.3K
-
-
20
claude-opus-4-5-20251101
Anthropic
94.7
24.1K
200K
¥36 / ¥180Input/Output
21
claude-opus-4-5-20251101-thinking-32k
Anthropic
94.4
12.7K
200K
¥108 / ¥540Input/Output
22
gpt-5.4
Openai
94.2
11.5K
1.05M
¥18 / ¥108Input/Output
23
dola-seed-2.0-pro
Bytedance
93.9
14.4K
-
-
24
claude-sonnet-4-5-20250929
Anthropic
93.6
27.7K
200K
¥21.6 / ¥108Input/Output
25
gemini-3-flash
Google
93.3
10.5K
1.05M
¥3.6 / ¥21.6Input/Output
26
kimi-k2.5-thinking
Moonshot
93.0
14K
262K
¥4.32 / ¥21.6Input/Output
27
kimi-k2.5-instant
Moonshot
92.8
2.9K
262K
¥4.32 / ¥21.6Input/Output
28
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
92.5
27.9K
200K
¥21.6 / ¥108Input/Output
29
mimo-v2-pro
Xiaomi
92.2
8.9K
1.05M
¥7.2 / ¥21.6Input/Output
30
qwen3.5-397b-a17b
Alibaba
91.9
12.3K
262K
¥3.1 / ¥18.6Input/Output
31
longcat-flash-chat-2602-exp
Meituan
91.6
9.1K
128K
¥1.08 / ¥10.8Input/Output
32
ernie-5.0-0110
Baidu
91.4
12.6K
128K
¥7.92 / ¥14.4Input/Output
33
grok-4.20-multi-agent-beta-0309
Xai
91.1
11.1K
2M
¥14.4 / ¥43.2Input/Output
34
grok-4.20-beta-0309-reasoning
Xai
90.8
11.1K
2M
¥14.4 / ¥43.2Input/Output
35
deepseek-v4-pro
Deepseek
90.5
6.9K
1M
¥3.13 / ¥6.26Input/Output
36
mimo-v2.5
Xiaomi
90.3
6.5K
1.05M
¥2.88 / ¥14.4Input/Output
37
gemma-4-31b
Google
90.0
2.1K
262K
¥3.24 / ¥7.2Input/Output
38
gemini-2.5-pro
Google
89.7
42.9K
1.05M
¥9 / ¥72Input/Output
39
deepseek-v4-pro-thinking
Deepseek
89.4
6.3K
1M
¥3.13 / ¥6.26Input/Output
40
qwen3.6-plus
Alibaba
89.1
7.5K
1M
¥3.6 / ¥21.6Input/Output
41
qwen3-max-preview
Alibaba
88.9
9.5K
262K
¥6.2 / ¥24.8Input/Output
42
longcat-flash-chat
Meituan
88.6
3.9K
128K
¥1.08 / ¥10.8Input/Output
43
qwen3.6-max-preview
Alibaba
88.3
1.9K
246K
¥9.5 / ¥56.9Input/Output
44
glm-5
Zai
88.0
8.1K
205K
¥7.2 / ¥23Input/Output
45
glm-4.6
Zai
87.7
12.6K
205K
¥4.32 / ¥15.8Input/Output
46
claude-opus-4-1-20250805-thinking-16k
Anthropic
87.5
17K
200K
¥108 / ¥540Input/Output
47
gpt-5.2-chat-latest-20260210
Openai
87.2
12.3K
400K
¥12.6 / ¥101Input/Output
48
glm-4.7
Zai
86.9
4.1K
205K
¥0 / ¥0Input/Output
49
gemma-4-26b-a4b
Google
86.6
2.1K
262K
¥0.94 / ¥2.88Input/Output
50
gpt-5.1-high
Openai
86.4
14K
400K
¥9 / ¥72Input/Output
51
grok-4.1-thinking
Xai
86.1
22.6K
200K
¥14.4 / ¥72Input/Output
52
grok-4.20-beta1
Xai
85.8
9.2K
2M
¥14.4 / ¥43.2Input/Output
53
grok-4.1
Xai
85.5
23.6K
200K
¥14.4 / ¥72Input/Output
54
claude-opus-4-1-20250805
Anthropic
85.2
26.3K
200K
¥108 / ¥540Input/Output
55
gemini-3-flash (thinking-minimal)
Google
85.0
19.5K
1.05M
¥3.6 / ¥21.6Input/Output
56
mistral-large-3
Mistral
84.7
15K
262K
¥3.6 / ¥10.8Input/Output
57
deepseek-v4-flash
Deepseek
84.4
6.7K
1M
¥1.01 / ¥2.02Input/Output
58
qwen3-next-80b-a3b-instruct
Alibaba
84.1
8.1K
131K
¥1.04 / ¥4.13Input/Output
59
deepseek-v3.2-thinking
Deepseek
83.8
13.5K
128K
¥2.09 / ¥3.1Input/Output
60
ernie-5.0-preview-1203
Baidu
83.6
3.4K
128K
¥7.92 / ¥14.4Input/Output
61
qwen3-235b-a22b-instruct-2507
Alibaba
83.3
33.8K
128K
¥2.09 / ¥8.23Input/Output
62
amazon-nova-experimental-chat-12-10
Amazon
83.0
1.2K
-
-
63
kimi-k2-thinking-turbo
Moonshot
82.7
21.9K
262K
¥17.3 / ¥72Input/Output
64
qwen3-vl-235b-a22b-instruct
Alibaba
82.5
4.1K
128K
¥2.16 / ¥8.64Input/Output
65
mimo-v2-omni
Xiaomi
82.2
1.2K
262K
¥2.88 / ¥14.4Input/Output
66
minimax-m2.7
Minimax
81.9
9.3K
205K
¥0 / ¥0Input/Output
67
mimo-v2-flash (non-thinking)
Xiaomi
81.6
16.7K
262K
¥0.72 / ¥2.16Input/Output
68
deepseek-v3.2
Deepseek
81.3
16.4K
128K
¥2.09 / ¥3.1Input/Output
69
amazon-nova-experimental-chat-11-10
Amazon
81.1
8.8K
-
-
70
deepseek-v4-flash-thinking
Deepseek
80.8
6.6K
1M
¥1.01 / ¥2.02Input/Output
71
amazon-nova-experimental-chat-26-01-10
Amazon
80.5
1.2K
-
-
72
mistral-medium-2508
Mistral
80.2
32.7K
262K
¥2.88 / ¥14.4Input/Output
73
glm-4.5
Zai
79.9
8.3K
131K
¥4.32 / ¥15.8Input/Output
74
grok-3-preview-02-24
Xai
79.7
9.3K
1M
¥9 / ¥18Input/Output
75
qwen3-max-2025-09-23
Alibaba
79.4
3.4K
258K
¥6.19 / ¥24.7Input/Output
76
deepseek-v3.2-exp-thinking
Deepseek
79.1
3.2K
128K
¥0 / ¥0Input/Output
77
gpt-5.1
Openai
78.8
15.2K
400K
¥9 / ¥72Input/Output
78
qwen3.5-122b-a10b
Alibaba
78.6
10.2K
262K
¥2.88 / ¥23Input/Output
79
gpt-5.4-mini-high
Openai
78.3
10.2K
400K
¥5.4 / ¥32.4Input/Output
80
ernie-5.0-preview-1022
Baidu
78.0
1.6K
128K
¥7.92 / ¥14.4Input/Output
81
gpt-5.2-high
Openai
77.7
16.8K
400K
¥12.6 / ¥101Input/Output
82
deepseek-r1-0528
Deepseek
77.4
5.7K
164K
¥3.6 / ¥15.5Input/Output
83
deepseek-v3.2-exp
Deepseek
77.2
4.1K
128K
¥0 / ¥0Input/Output
84
grok-4-fast-chat
Xai
76.9
2.3K
2M
¥1.44 / ¥3.6Input/Output
85
claude-haiku-4-5-20251001
Anthropic
76.6
28.3K
200K
¥7.2 / ¥36Input/Output
86
gpt-5.5-instant
Openai
76.3
10.2K
400K
¥9 / ¥72Input/Output
87
step-3.5-flash
Stepfun
76.0
12.8K
256K
¥0.69 / ¥2.07Input/Output
88
qwen3-235b-a22b-thinking-2507
Alibaba
75.8
3K
131K
¥2.07 / ¥8.26Input/Output
89
gpt-5.2
Openai
75.5
17.3K
400K
¥12.6 / ¥101Input/Output
90
chatgpt-4o-latest-20250326
Openai
75.2
27.1K
128K
¥18 / ¥72Input/Output
91
qwen3.5-27b
Alibaba
74.9
9.9K
262K
¥2.16 / ¥17.3Input/Output
92
deepseek-v3.1
Deepseek
74.7
4.8K
128K
¥1.44 / ¥5.04Input/Output
93
hunyuan-hy3-preview
Tencent
74.4
2.3K
256K
¥0 / ¥0Input/Output
94
deepseek-v3.1-thinking
Deepseek
74.1
3.6K
128K
¥1.44 / ¥5.04Input/Output
95
qwen3-vl-235b-a22b-thinking
Alibaba
73.8
2.8K
131K
¥2.06 / ¥8.26Input/Output
96
deepseek-v3.1-terminus-thinking
Deepseek
73.5
1.2K
128K
¥1.8 / ¥5.04Input/Output
97
gemini-2.5-flash
Google
73.3
42.6K
1.05M
¥2.16 / ¥18Input/Output
98
grok-4.3
Xai
73.0
6.3K
1M
¥9 / ¥18Input/Output
99
hunyuan-vision-1.5-thinking
Tencent
72.7
783
-
-
100
amazon-nova-experimental-chat-10-20
Amazon
72.4
3.9K
-
-
101
mimo-v2-flash (thinking)
Xiaomi
72.1
3.7K
262K
¥0.72 / ¥2.16Input/Output
102
gpt-5-high
Openai
71.9
10.9K
400K
¥9 / ¥72Input/Output
103
grok-4-1-fast-reasoning
Xai
71.6
19.4K
2M
¥1.44 / ¥3.6Input/Output
104
qwen3.5-35b-a3b
Alibaba
71.3
10.5K
262K
¥1.8 / ¥14.4Input/Output
105
qwen3-30b-a3b-instruct-2507
Alibaba
71.0
8.2K
262K
¥2.16 / ¥3.6Input/Output
106
qwen3.5-flash
Alibaba
70.8
11.7K
1M
¥1.24 / ¥12.4Input/Output
107
minimax-m2.1-preview
Minimax
70.5
5.8K
205K
¥0 / ¥0Input/Output
108
o3-2025-04-16
Openai
70.2
19.6K
200K
¥14.4 / ¥57.6Input/Output
109
gpt-4.5-preview-2025-02-27
Openai
69.9
3.4K
8.19K
¥216 / ¥432Input/Output
110
gemini-3.1-flash-lite-preview
Google
69.6
13.5K
1.05M
¥1.8 / ¥10.8Input/Output
111
grok-4-fast-reasoning
Xai
69.4
6.8K
2M
¥1.44 / ¥3.6Input/Output
112
deepseek-v3.1-terminus
Deepseek
69.1
1.3K
128K
¥1.8 / ¥5.04Input/Output
113
grok-4-0709
Xai
68.8
14.3K
256K
¥21.6 / ¥108Input/Output
114
nvidia-nemotron-3-super-120b-a12b
Nvidia
68.5
2.7K
262K
¥1.44 / ¥5.76Input/Output
115
gemini-2.5-flash-preview-09-2025
Google
68.2
11.8K
1M
¥2.16 / ¥18Input/Output
116
qwen3-235b-a22b-no-thinking
Alibaba
68.0
12.8K
131K
¥2.07 / ¥8.26Input/Output
117
gpt-5-chat
Openai
67.7
10.8K
400K
¥9 / ¥72Input/Output
118
hunyuan-t1-20250711
Tencent
67.4
1.6K
131K
¥0 / ¥0Input/Output
119
claude-opus-4-20250514-thinking-16k
Anthropic
67.1
12.3K
200K
¥108 / ¥540Input/Output
120
gpt-5.3-chat-latest
Openai
66.9
11.7K
128K
¥12.6 / ¥101Input/Output
121
ling-flash-2.0
Ant Group
66.6
2.5K
131K
¥1.01 / ¥4.1Input/Output
122
gpt-5.4-nano-high
Openai
66.3
9.9K
400K
¥1.44 / ¥9Input/Output
123
glm-4.5-air
Zai
66.0
10.7K
131K
¥0 / ¥0Input/Output
124
gpt-5-mini-high
Openai
65.7
9K
400K
¥1.8 / ¥14.4Input/Output
125
glm-4.6v
Zai
65.5
928
128K
¥2.16 / ¥6.48Input/Output
126
nova-2-lite
Amazon
65.2
4.3K
128K
¥2.38 / ¥19.8Input/Output
127
kimi-k2-0905-preview
Moonshot
64.9
4K
262K
¥4.32 / ¥18Input/Output
128
qwen3-next-80b-a3b-thinking
Alibaba
64.6
4.8K
131K
¥1.04 / ¥10.3Input/Output
129
qwen3-coder-480b-a35b-instruct
Alibaba
64.3
8.7K
262K
¥6.2 / ¥24.8Input/Output
130
glm-4.7-flash
Zai
64.1
4.3K
200K
¥0 / ¥0Input/Output
131
hunyuan-turbos-20250416
Tencent
63.8
3.1K
131K
¥0 / ¥0Input/Output
132
gpt-4.1-2025-04-14
Openai
63.5
16.8K
1.05M
¥14.4 / ¥57.6Input/Output
133
gpt-oss-120b
Openai
63.2
10.5K
131K
¥1.08 / ¥4.32Input/Output
134
qwen3-235b-a22b
Alibaba
63.0
8.1K
131K
¥2.07 / ¥8.26Input/Output
135
mistral-medium-2505
Mistral
62.7
10.8K
262K
¥2.88 / ¥14.4Input/Output
136
mercury-2
Inception Ai
62.4
1.1K
128K
¥1.8 / ¥5.4Input/Output
137
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
62.1
16.6K
1.05M
¥0.72 / ¥2.88Input/Output
138
kimi-k2-0711-preview
Moonshot
61.8
9.2K
131K
¥4.32 / ¥18Input/Output
139
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
61.6
5.2K
131K
¥0 / ¥0Input/Output
140
minimax-m2.5
Minimax
61.3
13.6K
205K
¥0 / ¥0Input/Output
141
claude-sonnet-4-20250514-thinking-32k
Anthropic
61.0
11.8K
200K
¥21.6 / ¥108Input/Output
142
deepseek-v3-0324
Deepseek
60.7
14.6K
75K
¥1.44 / ¥5.76Input/Output
143
claude-opus-4-20250514
Anthropic
60.4
14.9K
200K
¥108 / ¥540Input/Output
144
amazon-nova-experimental-chat-10-09
Amazon
60.2
1K
-
-
145
minimax-m2
Minimax
59.9
2.5K
197K
¥0 / ¥0Input/Output
146
gemini-2.5-flash-lite-preview-06-17-thinking
Google
59.6
10.9K
65.5K
¥0.72 / ¥2.88Input/Output
147
deepseek-r1
Deepseek
59.3
4K
164K
¥5.04 / ¥18Input/Output
148
grok-3-mini-high
Xai
59.1
5.9K
128K
¥0 / ¥0Input/Output
149
intellect-3
-
58.8
1.7K
131K
¥1.44 / ¥7.92Input/Output
150
qwen2.5-max
Alibaba
58.5
8.6K
32K
¥11.5 / ¥46Input/Output
151
grok-3-mini-beta
Xai
58.2
7.6K
1M
¥9 / ¥18Input/Output
152
trinity-large-thinking
-
57.9
9.4K
262K
¥1.8 / ¥6.48Input/Output
153
o4-mini-2025-04-16
Openai
57.7
15K
200K
¥7.92 / ¥31.7Input/Output
154
o1-2024-12-17
Openai
57.4
6.6K
128K
¥108 / ¥432Input/Output
155
trinity-large-preview
-
57.1
10.6K
262K
¥1.8 / ¥6.48Input/Output
156
qwen3-32b
Alibaba
56.8
843
131K
¥2.07 / ¥8.26Input/Output
157
ring-flash-2.0
Ant Group
56.5
2.6K
131K
¥1.01 / ¥4.1Input/Output
158
step-3
Stepfun
56.3
2.2K
65.5K
¥1.8 / ¥4.68Input/Output
159
o3-mini-high
Openai
56.0
4.3K
200K
¥7.92 / ¥31.7Input/Output
160
o1-preview
Openai
55.7
8.2K
128K
¥108 / ¥432Input/Output
161
gemini-2.0-flash-001
Google
55.4
12.3K
1.05M
¥1.08 / ¥4.32Input/Output
162
mistral-small-2506
Mistral
55.2
6.1K
262K
¥2.88 / ¥14.4Input/Output
163
gpt-4.1-mini-2025-04-14
Openai
54.9
12.7K
1.05M
¥2.88 / ¥11.5Input/Output
164
claude-sonnet-4-20250514
Anthropic
54.6
13.7K
200K
¥21.6 / ¥108Input/Output
165
minimax-m1
Minimax
54.3
11.7K
1M
¥0.95 / ¥9.03Input/Output
166
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia
54.0
1.2K
131K
¥2.88 / ¥2.88Input/Output
167
glm-4.5v
Zai
53.8
1.8K
64K
¥4.32 / ¥13Input/Output
168
gemma-3-27b-it
Google
53.5
14.4K
128K
¥2.15 / ¥2.15Input/Output
169
o1-mini
Openai
53.2
13.2K
128K
¥7.92 / ¥31.7Input/Output
170
hunyuan-turbos-20250226
Tencent
52.9
470
131K
¥0 / ¥0Input/Output
171
step-1o-turbo-202506
Stepfun
52.6
2.8K
-
-
172
olmo-3.1-32b-instruct
Allenai
52.4
4.2K
200K
¥14.4 / ¥57.6Input/Output
173
qwq-32b
Alibaba
52.1
7.5K
131K
¥2.07 / ¥6.2Input/Output
174
gpt-5-nano-high
Openai
51.8
2.9K
400K
¥0.36 / ¥2.88Input/Output
175
o3-mini
Openai
51.5
16.9K
200K
¥7.92 / ¥31.7Input/Output
176
qwen-plus-0125
Alibaba
51.3
1.4K
1M
¥0.83 / ¥2.07Input/Output
177
qwen3-30b-a3b
Alibaba
51.0
8.3K
128K
¥0.79 / ¥7.78Input/Output
178
command-a-03-2025
Cohere
50.7
18.2K
256K
¥18 / ¥72Input/Output
179
deepseek-v3
Deepseek
50.4
5.2K
128K
¥0 / ¥0Input/Output
180
gemini-2.0-flash-lite-preview-02-05
Google
50.1
5.7K
1.05M
¥0.54 / ¥2.16Input/Output
181
hunyuan-turbo-0110
Tencent
49.9
517
-
-
182
olmo-3-32b-think
Allenai
49.6
1.9K
128K
¥2.16 / ¥3.24Input/Output
183
llama-3.1-nemotron-ultra-253b-v1
Nvidia
49.3
588
128K
¥4.32 / ¥13Input/Output
184
granite-4.1-8b
Ibm
49.0
1.4K
131K
¥0.36 / ¥0.72Input/Output
185
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
48.7
11.7K
-
-
186
mercury
Inception Ai
48.5
676
128K
¥1.8 / ¥5.4Input/Output
187
glm-4-plus-0111
Zai
48.2
1.4K
128K
¥72 / ¥72Input/Output
188
qwen2.5-plus-1127
Alibaba
47.9
2.4K
-
-
189
claude-3-5-sonnet-20241022
Anthropic
47.6
25.3K
200K
¥21.6 / ¥108Input/Output
190
step-2-16k-exp-202412
Stepfun
47.4
1.2K
16.4K
¥37.5 / ¥118Input/Output
191
yi-lightning
-
47.1
7.1K
12K
¥1.44 / ¥1.44Input/Output
192
deepseek-v2.5-1210
Deepseek
46.8
1.7K
1M
¥1.01 / ¥2.02Input/Output
193
claude-3-7-sonnet-20250219
Anthropic
46.5
13K
200K
¥21.6 / ¥108Input/Output
194
gemma-3-12b-it
Google
46.2
867
128K
¥1.96 / ¥1.96Input/Output
195
gpt-oss-20b
Openai
46.0
3.7K
131K
¥0.32 / ¥1.3Input/Output
196
athene-v2-chat
-
45.7
6.2K
-
-
197
gemma-3n-e4b-it
Google
45.4
6.6K
128K
¥0 / ¥0Input/Output
198
hunyuan-large-2025-02-10
Tencent
45.1
828
-
-
199
gpt-4.1-nano-2025-04-14
Openai
44.8
1.5K
1.05M
¥14.4 / ¥57.6Input/Output
200
gemini-1.5-pro-002
Google
44.6
14.4K
-
-
201
mistral-small-3.1-24b-instruct-2503
Mistral
44.3
11.1K
262K
¥2.88 / ¥14.4Input/Output
202
llama-3.3-nemotron-49b-super-v1
Nvidia
44.0
493
131K
¥0 / ¥0Input/Output
203
llama-4-maverick-17b-128e-instruct
Meta
43.7
12.6K
1M
¥1.8 / ¥6.26Input/Output
204
molmo-2-8b
Allenai
43.5
288
-
-
205
gpt-4o-2024-05-13
Openai
43.2
31.4K
128K
¥36 / ¥108Input/Output
206
olmo-3.1-32b-think
Allenai
42.9
2.8K
200K
¥14.4 / ¥57.6Input/Output
207
deepseek-v2.5
Deepseek
42.6
6.7K
1M
¥1.01 / ¥2.02Input/Output
208
grok-2-2024-08-13
Xai
42.3
16.6K
1M
¥9 / ¥18Input/Output
209
qwen2.5-72b-instruct
Alibaba
42.1
10.4K
131K
¥4.13 / ¥12.4Input/Output
210
glm-4-plus
Zai
41.8
7.1K
128K
¥54 / ¥54Input/Output
211
gpt-4o-mini-2024-07-18
Openai
41.5
17.8K
128K
¥1.08 / ¥4.32Input/Output
212
qwen-max-0919
Alibaba
41.2
4.4K
131K
¥2.48 / ¥9.91Input/Output
213
llama-3.1-405b-instruct-bf16
Meta
40.9
10.3K
128K
¥0 / ¥0Input/Output
214
claude-3-5-sonnet-20240620
Anthropic
40.7
22.2K
200K
¥21.6 / ¥108Input/Output
215
llama-4-scout-17b-16e-instruct
Meta
40.4
9.7K
128K
¥1.44 / ¥5.62Input/Output
216
hunyuan-standard-2025-02-10
Tencent
40.1
880
-
-
217
llama-3.1-nemotron-70b-instruct
Nvidia
39.8
2.1K
128K
¥0 / ¥0Input/Output
218
magistral-medium-2506
Mistral
39.6
4.1K
128K
¥14.4 / ¥36Input/Output
219
hunyuan-large-vision
Tencent
39.3
1.8K
-
-
220
llama-3.1-405b-instruct-fp8
Meta
39.0
15.8K
128K
¥0 / ¥0Input/Output
221
gemini-1.5-flash-002
Google
38.7
9.2K
2M
¥0.54 / ¥2.2Input/Output
222
gpt-4o-2024-08-06
Openai
38.4
11.9K
128K
¥18 / ¥72Input/Output
223
grok-2-mini-2024-08-13
Xai
38.2
13.9K
1M
¥9 / ¥18Input/Output
224
mistral-large-2407
Mistral
37.9
12.1K
131K
¥14.4 / ¥43.2Input/Output
225
mistral-large-2411
Mistral
37.6
6.8K
128K
¥14.4 / ¥43.2Input/Output
226
llama-3.3-70b-instruct
Meta
37.3
15K
128K
¥0 / ¥0Input/Output
227
gemini-1.5-pro-001
Google
37.0
21.4K
-
-
228
claude-3-5-haiku-20241022
Anthropic
36.8
20K
200K
¥5.76 / ¥28.8Input/Output
229
amazon-nova-pro-v1.0
Amazon
36.5
6.2K
300K
¥5.76 / ¥23Input/Output
230
gemma-3-4b-it
Google
36.2
986
128K
¥1.44 / ¥1.44Input/Output
231
gpt-4-turbo-2024-04-09
Openai
35.9
27.6K
128K
¥72 / ¥216Input/Output
232
gemini-advanced-0514
Google
35.7
13.8K
-
-
233
athene-70b-0725
-
35.4
5K
-
-
234
qwen2.5-coder-32b-instruct
Alibaba
35.1
1.4K
131K
¥2.07 / ¥6.2Input/Output
235
llama-3.1-70b-instruct
Meta
34.8
14.8K
131K
¥2.88 / ¥2.88Input/Output
236
claude-3-opus-20240229
Anthropic
34.5
55K
200K
¥108 / ¥540Input/Output
237
ibm-granite-h-small
Ibm
34.3
2.2K
-
-
238
gpt-4-1106-preview
Openai
34.0
26.4K
8.19K
¥216 / ¥432Input/Output
239
gpt-4-0125-preview
Openai
33.7
25.6K
8.19K
¥216 / ¥432Input/Output
240
mistral-small-24b-instruct-2501
Mistral
33.4
3.5K
262K
¥2.88 / ¥14.4Input/Output
241
llama-3.1-tulu-3-70b
Allenai
33.1
711
-
-
242
gemini-1.5-flash-001
Google
32.9
17.5K
2M
¥0.54 / ¥2.2Input/Output
243
amazon-nova-lite-v1.0
Amazon
32.6
4.9K
300K
¥0.43 / ¥1.73Input/Output
244
deepseek-coder-v2
Deepseek
32.3
4.3K
1M
¥1.01 / ¥2.02Input/Output
245
jamba-1.5-large
-
32.0
2.3K
256K
¥0 / ¥0Input/Output
246
reka-core-20240904
-
31.8
2K
-
-
247
llama-3.1-nemotron-51b-instruct
Nvidia
31.5
1.1K
128K
¥0 / ¥0Input/Output
248
gemma-2-27b-it
Google
31.2
20K
8.19K
¥0.58 / ¥0.58Input/Output
249
phi-4
Microsoft
30.9
5.6K
128K
¥0.9 / ¥3.6Input/Output
250
gemini-1.5-flash-8b-001
Google
30.6
9.6K
2M
¥0.54 / ¥2.2Input/Output
251
glm-4-0520
Zai
30.4
2.8K
128K
¥108 / ¥108Input/Output
252
hunyuan-standard-256k
Tencent
30.1
737
-
-
253
claude-3-sonnet-20240229
Anthropic
29.8
31.4K
200K
¥21.6 / ¥108Input/Output
254
nemotron-4-340b-instruct
Nvidia
29.5
5.4K
-
-
255
amazon-nova-micro-v1.0
Amazon
29.2
4.7K
128K
¥0.25 / ¥1.01Input/Output
256
olmo-2-0325-32b-instruct
Allenai
29.0
740
-
-
257
ministral-8b-2410
Mistral
28.7
1.3K
128K
¥0.72 / ¥0.72Input/Output
258
c4ai-aya-expanse-32b
Cohere
28.4
7.3K
-
-
259
gemma-2-9b-it-simpo
-
28.1
2.5K
8.19K
¥1.44 / ¥1.44Input/Output
260
llama-3-70b-instruct
Meta
27.9
45.1K
8.19K
¥3.67 / ¥5.33Input/Output
261
reka-flash-20240904
-
27.6
2K
65.5K
¥0.72 / ¥1.44Input/Output
262
command-r-plus-08-2024
Cohere
27.3
2.7K
128K
¥18 / ¥72Input/Output
263
gemma-2-9b-it
Google
27.0
14.6K
8.19K
¥1.44 / ¥1.44Input/Output
264
llama-3.1-8b-instruct
Meta
26.7
13.1K
131K
¥0.79 / ¥0.79Input/Output
265
gpt-4-0314
Openai
26.5
14.5K
8.19K
¥216 / ¥432Input/Output
266
claude-3-haiku-20240307
Anthropic
26.2
34.3K
200K
¥1.8 / ¥9Input/Output
267
qwen2-72b-instruct
Alibaba
25.9
10.3K
131K
¥4.13 / ¥12.4Input/Output
268
llama-3.1-tulu-3-8b
Allenai
25.6
761
-
-
269
jamba-1.5-mini
-
25.3
2.3K
256K
¥0 / ¥0Input/Output
270
command-r-plus
Cohere
25.1
22.7K
128K
¥18 / ¥72Input/Output
271
c4ai-aya-expanse-8b
Cohere
24.8
2.5K
-
-
272
qwen1.5-110b-chat
Alibaba
24.5
7.7K
-
-
273
command-r-08-2024
Cohere
24.2
2.8K
128K
¥18 / ¥72Input/Output
274
yi-1.5-34b-chat
-
24.0
6.5K
-
-
275
mistral-large-2402
Mistral
23.7
17.5K
262K
¥2.88 / ¥14.4Input/Output
276
gpt-4-0613
Openai
23.4
23.8K
8.19K
¥216 / ¥432Input/Output
277
reka-flash-21b-20240226-online
-
23.1
4.7K
-
-
278
internlm2_5-20b-chat
-
22.8
2.7K
-
-
279
granite-3.1-8b-instruct
Ibm
22.6
780
-
-
280
qwen1.5-72b-chat
Alibaba
22.3
10.8K
-
-
281
llama-3-8b-instruct
Meta
22.0
29.6K
8.19K
¥0.29 / ¥0.29Input/Output
282
reka-flash-21b-20240226
-
21.7
7.4K
-
-
283
qwq-32b-preview
Alibaba
21.4
824
131K
¥2.07 / ¥6.2Input/Output
284
mixtral-8x22b-instruct-v0.1
Mistral
21.2
14.4K
64K
¥14.4 / ¥43.2Input/Output
285
mistral-medium
Mistral
20.9
9K
262K
¥2.88 / ¥14.4Input/Output
286
qwen1.5-32b-chat
Alibaba
20.6
6.4K
-
-
287
command-r
Cohere
20.3
15.7K
128K
¥18 / ¥72Input/Output
288
starling-lm-7b-beta
-
20.1
4.8K
200K
¥5.4 / ¥18.7Input/Output
289
qwen1.5-14b-chat
Alibaba
19.8
5.2K
-
-
290
granite-3.1-2b-instruct
Ibm
19.5
828
-
-
291
zephyr-orpo-141b-A35b-v0.1
-
19.2
1.3K
200K
¥108 / ¥432Input/Output
292
phi-3-medium-4k-instruct
Microsoft
18.9
6.7K
4.1K
¥1.22 / ¥4.9Input/Output
293
gemma-2-2b-it
Google
18.7
11.8K
128K
¥0 / ¥0Input/Output
294
gemini-pro-dev-api
Google
18.4
4.9K
1.05M
¥14.4 / ¥86.4Input/Output
295
mixtral-8x7b-instruct-v0.1
Mistral
18.1
20.1K
32K
¥5.04 / ¥5.04Input/Output
296
yi-34b-chat
-
17.8
4.1K
-
-
297
dbrx-instruct-preview
-
17.5
9.3K
-
-
298
gpt-3.5-turbo-0125
Openai
17.3
19K
16.4K
¥3.6 / ¥10.8Input/Output
299
gemini-pro
Google
17.0
1.4K
1.05M
¥14.4 / ¥86.4Input/Output
300
tulu-2-dpo-70b
-
16.7
1.5K
-
-
301
phi-3-small-8k-instruct
Microsoft
16.4
5.1K
8.19K
¥1.08 / ¥4.32Input/Output
302
openchat-3.5-0106
-
16.2
3.5K
-
-
303
llama-3.2-3b-instruct
Meta
15.9
2.2K
131K
¥0.22 / ¥0.35Input/Output
304
granite-3.0-8b-instruct
Ibm
15.6
1.8K
-
-
305
llama-2-70b-chat
Meta
15.3
10.2K
-
-
306
gemma-1.1-7b-it
Google
15.0
7.1K
-
-
307
deepseek-llm-67b-chat
Deepseek
14.8
1.2K
1M
¥1.01 / ¥2.02Input/Output
308
nous-hermes-2-mixtral-8x7b-dpo
-
14.5
993
1M
¥36 / ¥180Input/Output
309
starling-lm-7b-alpha
-
14.2
2.6K
200K
¥5.4 / ¥18.7Input/Output
310
gpt-3.5-turbo-1106
Openai
13.9
4.1K
16.4K
¥7.2 / ¥14.4Input/Output
311
qwen1.5-7b-chat
Alibaba
13.6
1.3K
-
-
312
wizardlm-70b
Microsoft
13.4
1.9K
-
-
313
phi-3-mini-4k-instruct-june-2024
Microsoft
13.1
3.1K
4.1K
¥0.94 / ¥3.74Input/Output
314
snowflake-arctic-instruct
-
12.8
9.2K
-
-
315
vicuna-33b
-
12.5
5.5K
-
-
316
openchat-3.5
-
12.3
1.9K
-
-
317
mistral-7b-instruct-v0.2
Mistral
12.0
5.2K
262K
¥2.88 / ¥14.4Input/Output
318
phi-3-mini-4k-instruct
Microsoft
11.7
5.7K
4.1K
¥0.94 / ¥3.74Input/Output
319
granite-3.0-2b-instruct
Ibm
11.4
1.9K
-
-
320
openhermes-2.5-mistral-7b
-
11.1
1.2K
1M
¥36 / ¥180Input/Output
321
llama-2-13b-chat
Meta
10.9
4.9K
-
-
322
solar-10.7b-instruct-v1.0
-
10.6
981
128K
¥0 / ¥0Input/Output
323
codellama-34b-instruct
Meta
10.3
1.8K
-
-
324
gemma-7b-it
Google
10.0
2.4K
-
-
325
mpt-30b-chat
-
9.7
575
-
-
326
codellama-70b-instruct
Meta
9.5
325
-
-
327
llama-3.2-1b-instruct
Meta
9.2
2.2K
16.4K
¥0.07 / ¥0.08Input/Output
328
llama2-70b-steerlm-chat
Nvidia
8.9
877
-
-
329
zephyr-7b-alpha
-
8.6
406
-
-
330
qwen-14b-chat
Alibaba
8.4
1.2K
32.8K
¥1.04 / ¥3.1Input/Output
331
wizardlm-13b
Microsoft
8.1
1.6K
-
-
332
zephyr-7b-beta
-
7.8
2.6K
-
-
333
vicuna-13b
-
7.5
4.7K
-
-
334
smollm2-1.7b-instruct
-
7.2
576
-
-
335
dolphin-2.2.1-mistral-7b
-
7.0
366
262K
¥2.88 / ¥14.4Input/Output
336
olmo-7b-instruct
Allenai
6.7
1.5K
-
-
337
phi-3-mini-128k-instruct
Microsoft
6.4
6.1K
128K
¥0.94 / ¥3.74Input/Output
338
gemma-1.1-2b-it
Google
6.1
3.2K
-
-
339
llama-2-7b-chat
Meta
5.8
3.7K
128K
¥4.03 / ¥48Input/Output
340
falcon-180b-chat
-
5.6
309
-
-
341
stripedhyena-nous-7b
-
5.3
1.3K
-
-
342
gemma-2b-it
Google
5.0
1.3K
-
-
343
vicuna-7b
-
4.7
1.6K
-
-
344
mistral-7b-instruct
Mistral
4.5
2.1K
262K
¥2.88 / ¥14.4Input/Output
345
guanaco-33b
-
4.2
635
200K
¥14.4 / ¥57.6Input/Output
346
palm-2
Google
3.9
2.1K
-
-
347
qwen1.5-4b-chat
Alibaba
3.6
2.2K
-
-
348
chatglm3-6b
-
3.3
1.1K
200K
¥5.4 / ¥18.7Input/Output
349
koala-13b
-
3.1
1.6K
-
-
350
gpt4all-13b-snoozy
-
2.8
422
1M
¥36 / ¥216Input/Output
351
chatglm2-6b
-
2.5
653
200K
¥5.4 / ¥18.7Input/Output
352
RWKV-4-Raven-14B
-
2.2
1.1K
-
-
353
mpt-7b-chat
-
1.9
882
-
-
354
chatglm-6b
-
1.7
1.2K
200K
¥5.4 / ¥18.7Input/Output
355
oasst-pythia-12b
-
1.4
1.4K
-
-
356
stablelm-tuned-alpha-7b
-
1.1
742
-
-
357
fastchat-t5-3b
-
0.8
955
-
-
358
alpaca-13b
-
0.6
1.3K
-
-
359
dolly-v2-12b
-
0.3
824
-
-
360
llama-13b
Meta
0.0
566
-
-
Top model analysis

claude-opus-4-6-thinking why it ranks first

claude-opus-4-6-thinking ranks first with a percent score of 100.0 and 12.5K samples. Use it as the first option for this leaderboard, then compare price, context and availability.

How to choose

Do not only look at rank #1

Start with the leaderboard closest to your task. Compare the top models by score and sample size, then check price, context length, open or closed access, and provider availability.

FAQ

FAQ

软件与 IT 服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。

软件与 IT 服务模型应该怎么选?

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。