Chat · Text · English Leaderboard

Ranking for Text / English, based on public preference data.

Selection guide

English model ranking guide

Ranking for Text / English, based on public preference data.

claude-opus-4-6-thinkingclaude-opus-4-6claude-opus-4-7-thinkingclaude-opus-4-7glm-5.1
Current DirectoryChat · Text · English
Models360
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / EnglishPublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
claude-opus-4-6-thinking
Anthropic
100.0
15.7K
1M
¥36 / ¥180Input/Output
2
claude-opus-4-6
Anthropic
99.7
17.1K
1M
¥36 / ¥180Input/Output
3
claude-opus-4-7-thinking
Anthropic
99.4
9.6K
1M
¥36 / ¥180Input/Output
4
claude-opus-4-7
Anthropic
99.2
10K
1M
¥36 / ¥180Input/Output
5
glm-5.1
Zai
98.9
6.7K
200K
¥0 / ¥0Input/Output
6
muse-spark
Meta
98.6
5.8K
-
-
7
gemini-3-pro
Google
98.3
19K
1.05M
¥14.4 / ¥86.4Input/Output
8
gemini-3.1-pro-preview
Google
98.1
20.5K
1.05M
¥14.4 / ¥86.4Input/Output
9
qwen3.5-max-preview
Alibaba
97.8
9.5K
-
-
10
gemini-3.5-flash
Google
97.5
4.4K
1.05M
¥10.8 / ¥64.8Input/Output
11
ernie-5.1
Baidu
97.2
6.9K
119K
¥5.4 / ¥21.6Input/Output
12
mimo-v2.5-pro
Xiaomi
96.9
7.2K
1.05M
¥7.2 / ¥21.6Input/Output
13
qwen3.7-max-preview
Alibaba
96.7
1.8K
1M
¥18 / ¥54Input/Output
14
gpt-5.4-high
Openai
96.4
13.1K
1.05M
¥18 / ¥108Input/Output
15
gpt-5.5-high
Openai
96.1
8K
1.05M
¥36 / ¥216Input/Output
16
claude-sonnet-4-6
Anthropic
95.8
13.1K
1M
¥21.6 / ¥108Input/Output
17
gemini-3-flash
Google
95.5
14.1K
1.05M
¥3.6 / ¥21.6Input/Output
18
gpt-5.5
Openai
95.3
8.2K
1.05M
¥36 / ¥216Input/Output
19
claude-opus-4-5-20251101
Anthropic
95.0
30.8K
200K
¥36 / ¥180Input/Output
20
kimi-k2.6
Moonshot
94.7
7.1K
262K
¥6.84 / ¥28.8Input/Output
21
gpt-5.4
Openai
94.4
14K
1.05M
¥18 / ¥108Input/Output
22
claude-opus-4-5-20251101-thinking-32k
Anthropic
94.2
17K
200K
¥108 / ¥540Input/Output
23
gemini-2.5-pro
Google
93.9
58.1K
1.05M
¥9 / ¥72Input/Output
24
grok-4.20-beta-0309-reasoning
Xai
93.6
13.7K
2M
¥14.4 / ¥43.2Input/Output
25
glm-5
Zai
93.3
10.2K
205K
¥7.2 / ¥23Input/Output
26
amazon-nova-experimental-chat-26-02-10
Amazon
93.0
1.6K
-
-
27
deepseek-v4-pro-thinking
Deepseek
92.8
7.3K
1M
¥3.13 / ¥6.26Input/Output
28
glm-4.7
Zai
92.5
5.6K
205K
¥0 / ¥0Input/Output
29
mimo-v2-pro
Xiaomi
92.2
10.1K
1.05M
¥7.2 / ¥21.6Input/Output
30
longcat-flash-chat-2602-exp
Meituan
91.9
11.4K
128K
¥1.08 / ¥10.8Input/Output
31
grok-4.20-beta1
Xai
91.6
11.6K
2M
¥14.4 / ¥43.2Input/Output
32
grok-4.20-multi-agent-beta-0309
Xai
91.4
13.4K
2M
¥14.4 / ¥43.2Input/Output
33
kimi-k2.5-thinking
Moonshot
91.1
16.4K
262K
¥4.32 / ¥21.6Input/Output
34
deepseek-v4-pro
Deepseek
90.8
7.7K
1M
¥3.13 / ¥6.26Input/Output
35
claude-sonnet-4-5-20250929
Anthropic
90.5
36.3K
200K
¥21.6 / ¥108Input/Output
36
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
90.3
36.6K
200K
¥21.6 / ¥108Input/Output
37
gemma-4-31b
Google
90.0
2.6K
262K
¥3.24 / ¥7.2Input/Output
38
gpt-5.1-high
Openai
89.7
18.8K
400K
¥9 / ¥72Input/Output
39
qwen3.5-397b-a17b
Alibaba
89.4
15.2K
262K
¥3.1 / ¥18.6Input/Output
40
mimo-v2.5
Xiaomi
89.1
7.4K
1.05M
¥2.88 / ¥14.4Input/Output
41
dola-seed-2.0-pro
Bytedance
88.9
17.5K
-
-
42
glm-4.6
Zai
88.6
17.2K
205K
¥4.32 / ¥15.8Input/Output
43
ernie-5.0-0110
Baidu
88.3
15.3K
128K
¥7.92 / ¥14.4Input/Output
44
grok-4.1
Xai
88.0
30.6K
200K
¥14.4 / ¥72Input/Output
45
gemini-3-flash (thinking-minimal)
Google
87.7
24.7K
1.05M
¥3.6 / ¥21.6Input/Output
46
qwen3.6-plus
Alibaba
87.5
8.3K
1M
¥3.6 / ¥21.6Input/Output
47
qwen3.6-max-preview
Alibaba
87.2
2.1K
246K
¥9.5 / ¥56.9Input/Output
48
grok-4.1-thinking
Xai
86.9
29.5K
200K
¥14.4 / ¥72Input/Output
49
gpt-5.2-chat-latest-20260210
Openai
86.6
15.1K
400K
¥12.6 / ¥101Input/Output
50
gemma-4-26b-a4b
Google
86.4
2.5K
262K
¥0.94 / ¥2.88Input/Output
51
deepseek-v3.2-thinking
Deepseek
86.1
18.1K
128K
¥2.09 / ¥3.1Input/Output
52
deepseek-v3.2-exp-thinking
Deepseek
85.8
4.4K
128K
¥0 / ¥0Input/Output
53
mistral-large-3
Mistral
85.5
19.9K
262K
¥3.6 / ¥10.8Input/Output
54
longcat-flash-chat
Meituan
85.2
5.4K
128K
¥1.08 / ¥10.8Input/Output
55
ernie-5.0-preview-1203
Baidu
85.0
4.6K
128K
¥7.92 / ¥14.4Input/Output
56
amazon-nova-experimental-chat-12-10
Amazon
84.7
1.7K
-
-
57
qwen3-max-preview
Alibaba
84.4
13K
262K
¥6.2 / ¥24.8Input/Output
58
deepseek-v3.2-exp
Deepseek
84.1
5.7K
128K
¥0 / ¥0Input/Output
59
deepseek-v4-flash
Deepseek
83.8
7.7K
1M
¥1.01 / ¥2.02Input/Output
60
mistral-medium-2508
Mistral
83.6
43.4K
262K
¥2.88 / ¥14.4Input/Output
61
grok-3-preview-02-24
Xai
83.3
18.1K
1M
¥9 / ¥18Input/Output
62
deepseek-v3.2
Deepseek
83.0
20.9K
128K
¥2.09 / ¥3.1Input/Output
63
deepseek-r1-0528
Deepseek
82.7
8.9K
164K
¥3.6 / ¥15.5Input/Output
64
deepseek-v4-flash-thinking
Deepseek
82.5
7.6K
1M
¥1.01 / ¥2.02Input/Output
65
claude-opus-4-1-20250805-thinking-16k
Anthropic
82.2
23.6K
200K
¥108 / ¥540Input/Output
66
glm-4.5
Zai
81.9
11.4K
131K
¥4.32 / ¥15.8Input/Output
67
kimi-k2.5-instant
Moonshot
81.6
3.7K
262K
¥4.32 / ¥21.6Input/Output
68
chatgpt-4o-latest-20250326
Openai
81.3
41.2K
128K
¥18 / ¥72Input/Output
69
deepseek-v3.1-thinking
Deepseek
81.1
5.3K
128K
¥1.44 / ¥5.04Input/Output
70
ernie-5.0-preview-1022
Baidu
80.8
2.4K
128K
¥7.92 / ¥14.4Input/Output
71
deepseek-v3.1
Deepseek
80.5
6.8K
128K
¥1.44 / ¥5.04Input/Output
72
mimo-v2-flash (non-thinking)
Xiaomi
80.2
20.2K
262K
¥0.72 / ¥2.16Input/Output
73
qwen3-vl-235b-a22b-instruct
Alibaba
79.9
5.6K
128K
¥2.16 / ¥8.64Input/Output
74
deepseek-v3.1-terminus-thinking
Deepseek
79.7
1.7K
128K
¥1.8 / ¥5.04Input/Output
75
qwen3.5-122b-a10b
Alibaba
79.4
12.5K
262K
¥2.88 / ¥23Input/Output
76
claude-opus-4-1-20250805
Anthropic
79.1
36.4K
200K
¥108 / ¥540Input/Output
77
kimi-k2-thinking-turbo
Moonshot
78.8
27.5K
262K
¥17.3 / ¥72Input/Output
78
qwen3-235b-a22b-thinking-2507
Alibaba
78.6
4.4K
131K
¥2.07 / ¥8.26Input/Output
79
qwen3-next-80b-a3b-instruct
Alibaba
78.3
10.9K
131K
¥1.04 / ¥4.13Input/Output
80
gpt-5.1
Openai
78.0
20.1K
400K
¥9 / ¥72Input/Output
81
qwen3-235b-a22b-instruct-2507
Alibaba
77.7
44.2K
128K
¥2.09 / ¥8.23Input/Output
82
amazon-nova-experimental-chat-11-10
Amazon
77.4
11.7K
-
-
83
deepseek-v3.1-terminus
Deepseek
77.2
1.9K
128K
¥1.8 / ¥5.04Input/Output
84
gpt-5.2-high
Openai
76.9
21.3K
400K
¥12.6 / ¥101Input/Output
85
qwen3.5-27b
Alibaba
76.6
12.1K
262K
¥2.16 / ¥17.3Input/Output
86
minimax-m2.7
Minimax
76.3
10.5K
205K
¥0 / ¥0Input/Output
87
gpt-5.5-instant
Openai
76.0
12K
400K
¥9 / ¥72Input/Output
88
qwen3-max-2025-09-23
Alibaba
75.8
4.5K
258K
¥6.19 / ¥24.7Input/Output
89
gpt-4.5-preview-2025-02-27
Openai
75.5
8.4K
8.19K
¥216 / ¥432Input/Output
90
mimo-v2-omni
Xiaomi
75.2
1.4K
262K
¥2.88 / ¥14.4Input/Output
91
grok-4-0709
Xai
74.9
20.3K
256K
¥21.6 / ¥108Input/Output
92
gemini-2.5-flash
Google
74.7
58.4K
1.05M
¥2.16 / ¥18Input/Output
93
step-3.5-flash
Stepfun
74.4
15.2K
256K
¥0.69 / ¥2.07Input/Output
94
grok-4-1-fast-reasoning
Xai
74.1
25.3K
2M
¥1.44 / ¥3.6Input/Output
95
qwen3-vl-235b-a22b-thinking
Alibaba
73.8
3.9K
131K
¥2.06 / ¥8.26Input/Output
96
hunyuan-vision-1.5-thinking
Tencent
73.5
1.1K
-
-
97
grok-4-fast-chat
Xai
73.3
3.2K
2M
¥1.44 / ¥3.6Input/Output
98
amazon-nova-experimental-chat-26-01-10
Amazon
73.0
1.6K
-
-
99
gemini-3.1-flash-lite-preview
Google
72.7
16.5K
1.05M
¥1.8 / ¥10.8Input/Output
100
grok-4.3
Xai
72.4
7.8K
1M
¥9 / ¥18Input/Output
101
o3-2025-04-16
Openai
72.1
30.2K
200K
¥14.4 / ¥57.6Input/Output
102
gpt-5.4-mini-high
Openai
71.9
12.5K
400K
¥5.4 / ¥32.4Input/Output
103
hunyuan-hy3-preview
Tencent
71.6
2.8K
256K
¥0 / ¥0Input/Output
104
amazon-nova-experimental-chat-10-20
Amazon
71.3
5.6K
-
-
105
gpt-5.2
Openai
71.0
21.9K
400K
¥12.6 / ¥101Input/Output
106
claude-haiku-4-5-20251001
Anthropic
70.8
36.9K
200K
¥7.2 / ¥36Input/Output
107
gemini-2.5-flash-preview-09-2025
Google
70.5
15.9K
1M
¥2.16 / ¥18Input/Output
108
mimo-v2-flash (thinking)
Xiaomi
70.2
4.9K
262K
¥0.72 / ¥2.16Input/Output
109
gpt-5-high
Openai
69.9
15.2K
400K
¥9 / ¥72Input/Output
110
qwen3.5-35b-a3b
Alibaba
69.6
12.7K
262K
¥1.8 / ¥14.4Input/Output
111
gpt-5-chat
Openai
69.4
15K
400K
¥9 / ¥72Input/Output
112
grok-4-fast-reasoning
Xai
69.1
9.3K
2M
¥1.44 / ¥3.6Input/Output
113
minimax-m2.1-preview
Minimax
68.8
7.6K
205K
¥0 / ¥0Input/Output
114
qwen3.5-flash
Alibaba
68.5
13.2K
1M
¥1.24 / ¥12.4Input/Output
115
nvidia-nemotron-3-super-120b-a12b
Nvidia
68.2
3.4K
262K
¥1.44 / ¥5.76Input/Output
116
qwen3-235b-a22b-no-thinking
Alibaba
68.0
18.6K
131K
¥2.07 / ¥8.26Input/Output
117
hunyuan-t1-20250711
Tencent
67.7
2.1K
131K
¥0 / ¥0Input/Output
118
glm-4.5-air
Zai
67.4
14.8K
131K
¥0 / ¥0Input/Output
119
qwen3-next-80b-a3b-thinking
Alibaba
67.1
6.6K
131K
¥1.04 / ¥10.3Input/Output
120
glm-4.6v
Zai
66.9
1.3K
128K
¥2.16 / ¥6.48Input/Output
121
qwen3-30b-a3b-instruct-2507
Alibaba
66.6
11.1K
262K
¥2.16 / ¥3.6Input/Output
122
gpt-4.1-2025-04-14
Openai
66.3
25.7K
1.05M
¥14.4 / ¥57.6Input/Output
123
gpt-5.3-chat-latest
Openai
66.0
14.4K
128K
¥12.6 / ¥101Input/Output
124
deepseek-v3-0324
Deepseek
65.7
23.3K
75K
¥1.44 / ¥5.76Input/Output
125
claude-opus-4-20250514-thinking-16k
Anthropic
65.5
17.5K
200K
¥108 / ¥540Input/Output
126
deepseek-r1
Deepseek
65.2
10.7K
164K
¥5.04 / ¥18Input/Output
127
mistral-medium-2505
Mistral
64.9
16.7K
262K
¥2.88 / ¥14.4Input/Output
128
minimax-m2.5
Minimax
64.6
16.7K
205K
¥0 / ¥0Input/Output
129
hunyuan-turbos-20250416
Tencent
64.3
5.7K
131K
¥0 / ¥0Input/Output
130
nova-2-lite
Amazon
64.1
5.8K
128K
¥2.38 / ¥19.8Input/Output
131
gpt-5.4-nano-high
Openai
63.8
12.2K
400K
¥1.44 / ¥9Input/Output
132
ling-flash-2.0
Ant Group
63.5
3.4K
131K
¥1.01 / ¥4.1Input/Output
133
o1-preview
Openai
63.2
15.9K
128K
¥108 / ¥432Input/Output
134
amazon-nova-experimental-chat-10-09
Amazon
63.0
1.4K
-
-
135
kimi-k2-0905-preview
Moonshot
62.7
5.5K
262K
¥4.32 / ¥18Input/Output
136
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
62.4
22.6K
1.05M
¥0.72 / ¥2.88Input/Output
137
intellect-3
-
62.1
2.6K
131K
¥1.44 / ¥7.92Input/Output
138
gpt-5-mini-high
Openai
61.8
12.7K
400K
¥1.8 / ¥14.4Input/Output
139
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
61.6
7.2K
131K
¥0 / ¥0Input/Output
140
mercury-2
Inception Ai
61.3
1.4K
128K
¥1.8 / ¥5.4Input/Output
141
grok-3-mini-high
Xai
61.0
8.4K
128K
¥0 / ¥0Input/Output
142
qwen3-235b-a22b
Alibaba
60.7
13.5K
131K
¥2.07 / ¥8.26Input/Output
143
kimi-k2-0711-preview
Moonshot
60.4
13.2K
131K
¥4.32 / ¥18Input/Output
144
claude-opus-4-20250514
Anthropic
60.2
21.5K
200K
¥108 / ¥540Input/Output
145
glm-4.7-flash
Zai
59.9
5.3K
200K
¥0 / ¥0Input/Output
146
qwen2.5-max
Alibaba
59.6
18.7K
32K
¥11.5 / ¥46Input/Output
147
gemma-3-27b-it
Google
59.3
24.8K
128K
¥2.15 / ¥2.15Input/Output
148
gpt-oss-120b
Openai
59.1
14.7K
131K
¥1.08 / ¥4.32Input/Output
149
grok-3-mini-beta
Xai
58.8
11.6K
1M
¥9 / ¥18Input/Output
150
gemini-2.5-flash-lite-preview-06-17-thinking
Google
58.5
15.8K
65.5K
¥0.72 / ¥2.88Input/Output
151
o1-2024-12-17
Openai
58.2
16.3K
128K
¥108 / ¥432Input/Output
152
step-3
Stepfun
57.9
3.2K
65.5K
¥1.8 / ¥4.68Input/Output
153
o4-mini-2025-04-16
Openai
57.7
23K
200K
¥7.92 / ¥31.7Input/Output
154
claude-sonnet-4-20250514-thinking-32k
Anthropic
57.4
16.8K
200K
¥21.6 / ¥108Input/Output
155
gemini-2.0-flash-001
Google
57.1
24.8K
1.05M
¥1.08 / ¥4.32Input/Output
156
ring-flash-2.0
Ant Group
56.8
3.5K
131K
¥1.01 / ¥4.1Input/Output
157
minimax-m2
Minimax
56.5
3.4K
197K
¥0 / ¥0Input/Output
158
qwen3-coder-480b-a35b-instruct
Alibaba
56.3
12.4K
262K
¥6.2 / ¥24.8Input/Output
159
mistral-small-2506
Mistral
56.0
8.5K
262K
¥2.88 / ¥14.4Input/Output
160
minimax-m1
Minimax
55.7
16.9K
1M
¥0.95 / ¥9.03Input/Output
161
trinity-large-thinking
-
55.4
11.3K
262K
¥1.8 / ¥6.48Input/Output
162
glm-4.5v
Zai
55.2
2.4K
64K
¥4.32 / ¥13Input/Output
163
qwen3-32b
Alibaba
54.9
2.2K
131K
¥2.07 / ¥8.26Input/Output
164
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia
54.6
1.5K
131K
¥2.88 / ¥2.88Input/Output
165
gpt-4.1-mini-2025-04-14
Openai
54.3
19.8K
1.05M
¥2.88 / ¥11.5Input/Output
166
trinity-large-preview
-
54.0
13.2K
262K
¥1.8 / ¥6.48Input/Output
167
llama-3.3-nemotron-49b-super-v1
Nvidia
53.8
1.3K
131K
¥0 / ¥0Input/Output
168
step-1o-turbo-202506
Stepfun
53.5
4.4K
-
-
169
o3-mini-high
Openai
53.2
11.1K
200K
¥7.92 / ¥31.7Input/Output
170
qwq-32b
Alibaba
52.9
13.7K
131K
¥2.07 / ¥6.2Input/Output
171
olmo-3.1-32b-instruct
Allenai
52.6
5.5K
200K
¥14.4 / ¥57.6Input/Output
172
gemma-3-12b-it
Google
52.4
2.3K
128K
¥1.96 / ¥1.96Input/Output
173
deepseek-v3
Deepseek
52.1
12.9K
128K
¥0 / ¥0Input/Output
174
claude-sonnet-4-20250514
Anthropic
51.8
19.5K
200K
¥21.6 / ¥108Input/Output
175
step-2-16k-exp-202412
Stepfun
51.5
2.8K
16.4K
¥37.5 / ¥118Input/Output
176
llama-3.1-nemotron-ultra-253b-v1
Nvidia
51.3
1.5K
128K
¥4.32 / ¥13Input/Output
177
olmo-3-32b-think
Allenai
51.0
2.8K
128K
¥2.16 / ¥3.24Input/Output
178
command-a-03-2025
Cohere
50.7
28.5K
256K
¥18 / ¥72Input/Output
179
glm-4-plus-0111
Zai
50.4
3.5K
128K
¥72 / ¥72Input/Output
180
o1-mini
Openai
50.1
27.4K
128K
¥7.92 / ¥31.7Input/Output
181
qwen-plus-0125
Alibaba
49.9
3.4K
1M
¥0.83 / ¥2.07Input/Output
182
olmo-3.1-32b-think
Allenai
49.6
3.8K
200K
¥14.4 / ¥57.6Input/Output
183
qwen3-30b-a3b
Alibaba
49.3
13.4K
128K
¥0.79 / ¥7.78Input/Output
184
o3-mini
Openai
49.0
30.4K
200K
¥7.92 / ¥31.7Input/Output
185
hunyuan-turbos-20250226
Tencent
48.7
1.3K
131K
¥0 / ¥0Input/Output
186
gemini-2.0-flash-lite-preview-02-05
Google
48.5
14.9K
1.05M
¥0.54 / ¥2.16Input/Output
187
yi-lightning
-
48.2
13.7K
12K
¥1.44 / ¥1.44Input/Output
188
hunyuan-turbo-0110
Tencent
47.9
1.3K
-
-
189
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
47.6
20.3K
-
-
190
gpt-5-nano-high
Openai
47.4
4K
400K
¥0.36 / ¥2.88Input/Output
191
gemini-1.5-pro-002
Google
47.1
30.1K
-
-
192
qwen2.5-plus-1127
Alibaba
46.8
5.8K
-
-
193
granite-4.1-8b
Ibm
46.5
1.7K
131K
¥0.36 / ¥0.72Input/Output
194
grok-2-2024-08-13
Xai
46.2
34.4K
1M
¥9 / ¥18Input/Output
195
gemma-3n-e4b-it
Google
46.0
11K
128K
¥0 / ¥0Input/Output
196
llama-3.1-nemotron-70b-instruct
Nvidia
45.7
3.7K
128K
¥0 / ¥0Input/Output
197
gpt-4o-2024-05-13
Openai
45.4
60.2K
128K
¥36 / ¥108Input/Output
198
llama-3.1-405b-instruct-bf16
Meta
45.1
23.3K
128K
¥0 / ¥0Input/Output
199
claude-3-7-sonnet-20250219
Anthropic
44.8
23.5K
200K
¥21.6 / ¥108Input/Output
200
deepseek-v2.5-1210
Deepseek
44.6
3.8K
1M
¥1.01 / ¥2.02Input/Output
201
llama-3.1-405b-instruct-fp8
Meta
44.3
32.4K
128K
¥0 / ¥0Input/Output
202
claude-3-5-sonnet-20241022
Anthropic
44.0
46.5K
200K
¥21.6 / ¥108Input/Output
203
molmo-2-8b
Allenai
43.7
376
-
-
204
athene-v2-chat
-
43.5
13.7K
-
-
205
hunyuan-large-2025-02-10
Tencent
43.2
2.3K
-
-
206
mercury
Inception Ai
42.9
943
128K
¥1.8 / ¥5.4Input/Output
207
llama-3.3-70b-instruct
Meta
42.6
30.2K
128K
¥0 / ¥0Input/Output
208
llama-4-scout-17b-16e-instruct
Meta
42.3
14.4K
128K
¥1.44 / ¥5.62Input/Output
209
llama-4-maverick-17b-128e-instruct
Meta
42.1
20.4K
1M
¥1.8 / ¥6.26Input/Output
210
gpt-4.1-nano-2025-04-14
Openai
41.8
3.5K
1.05M
¥14.4 / ¥57.6Input/Output
211
gpt-oss-20b
Openai
41.5
5.1K
131K
¥0.32 / ¥1.3Input/Output
212
gpt-4o-mini-2024-07-18
Openai
41.2
37.8K
128K
¥1.08 / ¥4.32Input/Output
213
gemma-3-4b-it
Google
40.9
2.6K
128K
¥1.44 / ¥1.44Input/Output
214
mistral-small-3.1-24b-instruct-2503
Mistral
40.7
15.9K
262K
¥2.88 / ¥14.4Input/Output
215
grok-2-mini-2024-08-13
Xai
40.4
28.4K
1M
¥9 / ¥18Input/Output
216
gpt-4o-2024-08-06
Openai
40.1
25.3K
128K
¥18 / ¥72Input/Output
217
glm-4-plus
Zai
39.8
13.2K
128K
¥54 / ¥54Input/Output
218
llama-3.1-70b-instruct
Meta
39.6
29.7K
131K
¥2.88 / ¥2.88Input/Output
219
qwen-max-0919
Alibaba
39.3
8.3K
131K
¥2.48 / ¥9.91Input/Output
220
gpt-4-turbo-2024-04-09
Openai
39.0
55.1K
128K
¥72 / ¥216Input/Output
221
mistral-large-2407
Mistral
38.7
24.9K
131K
¥14.4 / ¥43.2Input/Output
222
gemini-1.5-flash-002
Google
38.4
18.4K
2M
¥0.54 / ¥2.2Input/Output
223
athene-70b-0725
-
38.2
11.3K
-
-
224
claude-3-5-sonnet-20240620
Anthropic
37.9
44.4K
200K
¥21.6 / ¥108Input/Output
225
deepseek-v2.5
Deepseek
37.6
12.8K
1M
¥1.01 / ¥2.02Input/Output
226
mistral-large-2411
Mistral
37.3
16.3K
128K
¥14.4 / ¥43.2Input/Output
227
hunyuan-large-vision
Tencent
37.0
2.8K
-
-
228
qwen2.5-72b-instruct
Alibaba
36.8
20.6K
131K
¥4.13 / ¥12.4Input/Output
229
gemini-advanced-0514
Google
36.5
26.3K
-
-
230
hunyuan-standard-2025-02-10
Tencent
36.2
2.3K
-
-
231
gemini-1.5-pro-001
Google
35.9
42.5K
-
-
232
llama-3-70b-instruct
Meta
35.7
90.6K
8.19K
¥3.67 / ¥5.33Input/Output
233
gpt-4-1106-preview
Openai
35.4
64.7K
8.19K
¥216 / ¥432Input/Output
234
magistral-medium-2506
Mistral
35.1
5K
128K
¥14.4 / ¥36Input/Output
235
gpt-4-0125-preview
Openai
34.8
55K
8.19K
¥216 / ¥432Input/Output
236
amazon-nova-pro-v1.0
Amazon
34.5
14.2K
300K
¥5.76 / ¥23Input/Output
237
llama-3.1-tulu-3-70b
Allenai
34.3
1.6K
-
-
238
claude-3-5-haiku-20241022
Anthropic
34.0
37.4K
200K
¥5.76 / ¥28.8Input/Output
239
llama-3.1-nemotron-51b-instruct
Nvidia
33.7
1.8K
128K
¥0 / ¥0Input/Output
240
jamba-1.5-large
-
33.4
4.9K
256K
¥0 / ¥0Input/Output
241
ibm-granite-h-small
Ibm
33.1
2.8K
-
-
242
claude-3-opus-20240229
Anthropic
32.9
108.4K
200K
¥108 / ¥540Input/Output
243
reka-core-20240904
-
32.6
3.9K
-
-
244
mistral-small-24b-instruct-2501
Mistral
32.3
8.7K
262K
¥2.88 / ¥14.4Input/Output
245
olmo-2-0325-32b-instruct
Allenai
32.0
2K
-
-
246
qwen2.5-coder-32b-instruct
Alibaba
31.8
2.7K
131K
¥2.07 / ¥6.2Input/Output
247
gemini-1.5-flash-001
Google
31.5
33.8K
2M
¥0.54 / ¥2.2Input/Output
248
amazon-nova-lite-v1.0
Amazon
31.2
11K
300K
¥0.43 / ¥1.73Input/Output
249
gemma-2-9b-it-simpo
-
30.9
5.8K
8.19K
¥1.44 / ¥1.44Input/Output
250
glm-4-0520
Zai
30.6
5.2K
128K
¥108 / ¥108Input/Output
251
gemma-2-27b-it
Google
30.4
41.3K
8.19K
¥0.58 / ¥0.58Input/Output
252
command-r-plus-08-2024
Cohere
30.1
5.3K
128K
¥18 / ¥72Input/Output
253
nemotron-4-340b-instruct
Nvidia
29.8
10.3K
-
-
254
gemini-1.5-flash-8b-001
Google
29.5
18.5K
2M
¥0.54 / ¥2.2Input/Output
255
phi-4
Microsoft
29.2
14.1K
128K
¥0.9 / ¥3.6Input/Output
256
c4ai-aya-expanse-32b
Cohere
29.0
14.4K
-
-
257
claude-3-sonnet-20240229
Anthropic
28.7
61K
200K
¥21.6 / ¥108Input/Output
258
jamba-1.5-mini
-
28.4
5.1K
256K
¥0 / ¥0Input/Output
259
amazon-nova-micro-v1.0
Amazon
28.1
11K
128K
¥0.25 / ¥1.01Input/Output
260
reka-flash-20240904
-
27.9
4K
65.5K
¥0.72 / ¥1.44Input/Output
261
qwen2-72b-instruct
Alibaba
27.6
19.9K
131K
¥4.13 / ¥12.4Input/Output
262
gpt-4-0314
Openai
27.3
35.5K
8.19K
¥216 / ¥432Input/Output
263
gemma-2-9b-it
Google
27.0
29.8K
8.19K
¥1.44 / ¥1.44Input/Output
264
llama-3.1-8b-instruct
Meta
26.7
26.6K
131K
¥0.79 / ¥0.79Input/Output
265
hunyuan-standard-256k
Tencent
26.5
1.3K
-
-
266
llama-3.1-tulu-3-8b
Allenai
26.2
1.6K
-
-
267
yi-1.5-34b-chat
-
25.9
12.5K
-
-
268
llama-3-8b-instruct
Meta
25.6
61.7K
8.19K
¥0.29 / ¥0.29Input/Output
269
command-r-plus
Cohere
25.3
42.4K
128K
¥18 / ¥72Input/Output
270
ministral-8b-2410
Mistral
25.1
2.3K
128K
¥0.72 / ¥0.72Input/Output
271
claude-3-haiku-20240307
Anthropic
24.8
64.5K
200K
¥1.8 / ¥9Input/Output
272
gpt-4-0613
Openai
24.5
57.5K
8.19K
¥216 / ¥432Input/Output
273
internlm2_5-20b-chat
-
24.2
5K
-
-
274
mistral-large-2402
Mistral
24.0
36.8K
262K
¥2.88 / ¥14.4Input/Output
275
qwen1.5-110b-chat
Alibaba
23.7
13.9K
-
-
276
command-r-08-2024
Cohere
23.4
5.4K
128K
¥18 / ¥72Input/Output
277
deepseek-coder-v2
Deepseek
23.1
8.1K
1M
¥1.01 / ¥2.02Input/Output
278
c4ai-aya-expanse-8b
Cohere
22.8
5.5K
-
-
279
mistral-medium
Mistral
22.6
23.8K
262K
¥2.88 / ¥14.4Input/Output
280
granite-3.1-8b-instruct
Ibm
22.3
1.7K
-
-
281
mixtral-8x22b-instruct-v0.1
Mistral
22.0
29.9K
64K
¥14.4 / ¥43.2Input/Output
282
qwen1.5-72b-chat
Alibaba
21.7
25K
-
-
283
qwq-32b-preview
Alibaba
21.4
1.8K
131K
¥2.07 / ¥6.2Input/Output
284
gemma-2-2b-it
Google
21.2
25.7K
128K
¥0 / ¥0Input/Output
285
reka-flash-21b-20240226-online
-
20.9
8.9K
-
-
286
llama-3.2-3b-instruct
Meta
20.6
4.2K
131K
¥0.22 / ¥0.35Input/Output
287
reka-flash-21b-20240226
-
20.3
14.4K
-
-
288
zephyr-orpo-141b-A35b-v0.1
-
20.1
2.7K
200K
¥108 / ¥432Input/Output
289
command-r
Cohere
19.8
29.6K
128K
¥18 / ¥72Input/Output
290
granite-3.1-2b-instruct
Ibm
19.5
1.7K
-
-
291
phi-3-medium-4k-instruct
Microsoft
19.2
13.3K
4.1K
¥1.22 / ¥4.9Input/Output
292
mixtral-8x7b-instruct-v0.1
Mistral
18.9
46.3K
32K
¥5.04 / ¥5.04Input/Output
293
starling-lm-7b-beta
-
18.7
9.1K
200K
¥5.4 / ¥18.7Input/Output
294
gemini-pro-dev-api
Google
18.4
12.5K
1.05M
¥14.4 / ¥86.4Input/Output
295
qwen1.5-32b-chat
Alibaba
18.1
11.9K
-
-
296
yi-34b-chat
-
17.8
10.6K
-
-
297
llama-2-70b-chat
Meta
17.5
26K
-
-
298
dbrx-instruct-preview
-
17.3
18.1K
-
-
299
gemini-pro
Google
17.0
5.1K
1.05M
¥14.4 / ¥86.4Input/Output
300
phi-3-small-8k-instruct
Microsoft
16.7
9.1K
8.19K
¥1.08 / ¥4.32Input/Output
301
wizardlm-70b
Microsoft
16.4
6.4K
-
-
302
tulu-2-dpo-70b
-
16.2
5K
-
-
303
granite-3.0-8b-instruct
Ibm
15.9
3.3K
-
-
304
qwen1.5-14b-chat
Alibaba
15.6
9.5K
-
-
305
nous-hermes-2-mixtral-8x7b-dpo
-
15.3
3K
1M
¥36 / ¥180Input/Output
306
gpt-3.5-turbo-0125
Openai
15.0
40K
16.4K
¥3.6 / ¥10.8Input/Output
307
starling-lm-7b-alpha
-
14.8
7.2K
200K
¥5.4 / ¥18.7Input/Output
308
vicuna-33b
-
14.5
16.7K
-
-
309
mistral-7b-instruct-v0.2
Mistral
14.2
12.7K
262K
¥2.88 / ¥14.4Input/Output
310
openchat-3.5-0106
-
13.9
8.2K
-
-
311
phi-3-mini-4k-instruct-june-2024
Microsoft
13.6
6.7K
4.1K
¥0.94 / ¥3.74Input/Output
312
deepseek-llm-67b-chat
Deepseek
13.4
3.8K
1M
¥1.01 / ¥2.02Input/Output
313
openhermes-2.5-mistral-7b
-
13.1
3.9K
1M
¥36 / ¥180Input/Output
314
gemma-1.1-7b-it
Google
12.8
12.7K
-
-
315
snowflake-arctic-instruct
-
12.5
20.4K
-
-
316
llama-2-13b-chat
Meta
12.3
13.9K
-
-
317
llama2-70b-steerlm-chat
Nvidia
12.0
2.8K
-
-
318
granite-3.0-2b-instruct
Ibm
11.7
3.3K
-
-
319
openchat-3.5
-
11.4
6.2K
-
-
320
solar-10.7b-instruct-v1.0
-
11.1
3.3K
128K
¥0 / ¥0Input/Output
321
phi-3-mini-4k-instruct
Microsoft
10.9
10.3K
4.1K
¥0.94 / ¥3.74Input/Output
322
llama-3.2-1b-instruct
Meta
10.6
4.3K
16.4K
¥0.07 / ¥0.08Input/Output
323
gpt-3.5-turbo-1106
Openai
10.3
12.9K
16.4K
¥7.2 / ¥14.4Input/Output
324
dolphin-2.2.1-mistral-7b
-
10.0
1.3K
262K
¥2.88 / ¥14.4Input/Output
325
zephyr-7b-beta
-
9.7
8.8K
-
-
326
qwen1.5-7b-chat
Alibaba
9.5
3.2K
-
-
327
mpt-30b-chat
-
9.2
2.1K
-
-
328
wizardlm-13b
Microsoft
8.9
5.5K
-
-
329
codellama-70b-instruct
Meta
8.6
695
-
-
330
llama-2-7b-chat
Meta
8.4
10.3K
128K
¥4.03 / ¥48Input/Output
331
smollm2-1.7b-instruct
-
8.1
1.1K
-
-
332
codellama-34b-instruct
Meta
7.8
5.8K
-
-
333
zephyr-7b-alpha
-
7.5
1.4K
-
-
334
gemma-7b-it
Google
7.2
5.7K
-
-
335
guanaco-33b
-
7.0
2.4K
200K
¥14.4 / ¥57.6Input/Output
336
phi-3-mini-128k-instruct
Microsoft
6.7
12.6K
128K
¥0.94 / ¥3.74Input/Output
337
falcon-180b-chat
-
6.4
1K
-
-
338
vicuna-13b
-
6.1
14.8K
-
-
339
stripedhyena-nous-7b
-
5.8
4K
-
-
340
qwen-14b-chat
Alibaba
5.6
3.8K
32.8K
¥1.04 / ¥3.1Input/Output
341
olmo-7b-instruct
Allenai
5.3
4K
-
-
342
palm-2
Google
5.0
6.9K
-
-
343
mistral-7b-instruct
Mistral
4.7
7.1K
262K
¥2.88 / ¥14.4Input/Output
344
vicuna-7b
-
4.5
5.6K
-
-
345
gemma-1.1-2b-it
Google
4.2
5.9K
-
-
346
gemma-2b-it
Google
3.9
3K
-
-
347
koala-13b
-
3.6
5.7K
-
-
348
qwen1.5-4b-chat
Alibaba
3.3
4.8K
-
-
349
chatglm3-6b
-
3.1
3.6K
200K
¥5.4 / ¥18.7Input/Output
350
gpt4all-13b-snoozy
-
2.8
1.4K
1M
¥36 / ¥216Input/Output
351
mpt-7b-chat
-
2.5
3.3K
-
-
352
chatglm2-6b
-
2.2
2.1K
200K
¥5.4 / ¥18.7Input/Output
353
RWKV-4-Raven-14B
-
1.9
4K
-
-
354
alpaca-13b
-
1.7
4.8K
-
-
355
oasst-pythia-12b
-
1.4
5.2K
-
-
356
chatglm-6b
-
1.1
4.1K
200K
¥5.4 / ¥18.7Input/Output
357
fastchat-t5-3b
-
0.8
3.4K
-
-
358
stablelm-tuned-alpha-7b
-
0.6
2.7K
-
-
359
dolly-v2-12b
-
0.3
2.8K
-
-
360
llama-13b
Meta
0.0
2K
-
-
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 15.7K 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

英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。

英文模型应该怎么选?

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。