Chat · Text · Overall Leaderboard

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

Selection guide

Overall model ranking guide

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

claude-opus-4-6-thinkingclaude-opus-4-6claude-opus-4-7-thinkinggemini-3.5-flashgemini-3.1-pro-preview
Current DirectoryChat · Text · Overall
Models360
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / OverallPublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
claude-opus-4-6-thinking
Anthropic
100.0
34.2K
1M
¥36 / ¥180Input/Output
2
claude-opus-4-6
Anthropic
99.7
36.5K
1M
¥36 / ¥180Input/Output
3
claude-opus-4-7-thinking
Anthropic
99.4
20K
1M
¥36 / ¥180Input/Output
4
gemini-3.5-flash
Google
99.2
9K
1.05M
¥10.8 / ¥64.8Input/Output
5
gemini-3.1-pro-preview
Google
98.9
43.7K
1.05M
¥14.4 / ¥86.4Input/Output
6
claude-opus-4-7
Anthropic
98.6
20.7K
1M
¥36 / ¥180Input/Output
7
gemini-3-pro
Google
98.3
41.3K
1.05M
¥14.4 / ¥86.4Input/Output
8
qwen3.7-max-preview
Alibaba
98.1
3.8K
1M
¥18 / ¥54Input/Output
9
muse-spark
Meta
97.8
12.2K
-
-
10
gpt-5.4-high
Openai
97.5
28.2K
1.05M
¥18 / ¥108Input/Output
11
qwen3.5-max-preview
Alibaba
97.2
20.2K
-
-
12
ernie-5.1
Baidu
96.9
14.7K
119K
¥5.4 / ¥21.6Input/Output
13
glm-5.1
Zai
96.7
14K
200K
¥0 / ¥0Input/Output
14
gpt-5.5-high
Openai
96.4
16.6K
1.05M
¥36 / ¥216Input/Output
15
gemini-3-flash
Google
96.1
30.7K
1.05M
¥3.6 / ¥21.6Input/Output
16
gpt-5.5
Openai
95.8
16.9K
1.05M
¥36 / ¥216Input/Output
17
mimo-v2.5-pro
Xiaomi
95.5
15.7K
1.05M
¥7.2 / ¥21.6Input/Output
18
gemini-2.5-pro
Google
95.3
122.6K
1.05M
¥9 / ¥72Input/Output
19
gpt-5.4
Openai
95.0
29.7K
1.05M
¥18 / ¥108Input/Output
20
kimi-k2.6
Moonshot
94.7
15.8K
262K
¥6.84 / ¥28.8Input/Output
21
claude-sonnet-4-6
Anthropic
94.4
27.5K
1M
¥21.6 / ¥108Input/Output
22
grok-4.20-beta-0309-reasoning
Xai
94.2
29.1K
2M
¥14.4 / ¥43.2Input/Output
23
grok-4.20-multi-agent-beta-0309
Xai
93.9
28.6K
2M
¥14.4 / ¥43.2Input/Output
24
claude-opus-4-5-20251101
Anthropic
93.6
66.1K
200K
¥36 / ¥180Input/Output
25
dola-seed-2.0-pro
Bytedance
93.3
37.7K
-
-
26
amazon-nova-experimental-chat-26-02-10
Amazon
93.0
3.4K
-
-
27
deepseek-v4-pro-thinking
Deepseek
92.8
15.9K
1M
¥3.13 / ¥6.26Input/Output
28
claude-opus-4-5-20251101-thinking-32k
Anthropic
92.5
37.1K
200K
¥108 / ¥540Input/Output
29
gemini-3-flash (thinking-minimal)
Google
92.2
52.9K
1.05M
¥3.6 / ¥21.6Input/Output
30
ernie-5.0-0110
Baidu
91.9
34.2K
128K
¥7.92 / ¥14.4Input/Output
31
deepseek-v4-pro
Deepseek
91.6
16.9K
1M
¥3.13 / ¥6.26Input/Output
32
grok-4.20-beta1
Xai
91.4
24.5K
2M
¥14.4 / ¥43.2Input/Output
33
glm-5
Zai
91.1
21.9K
205K
¥7.2 / ¥23Input/Output
34
kimi-k2.5-thinking
Moonshot
90.8
36.8K
262K
¥4.32 / ¥21.6Input/Output
35
qwen3.6-max-preview
Alibaba
90.5
4.6K
246K
¥9.5 / ¥56.9Input/Output
36
gemma-4-31b
Google
90.3
5.9K
262K
¥3.24 / ¥7.2Input/Output
37
ernie-5.0-preview-1203
Baidu
90.0
9.8K
128K
¥7.92 / ¥14.4Input/Output
38
gpt-5.1-high
Openai
89.7
40.9K
400K
¥9 / ¥72Input/Output
39
qwen3.5-397b-a17b
Alibaba
89.4
32K
262K
¥3.1 / ¥18.6Input/Output
40
glm-4.6
Zai
89.1
35.7K
205K
¥4.32 / ¥15.8Input/Output
41
gpt-5.2-chat-latest-20260210
Openai
88.9
32.3K
400K
¥12.6 / ¥101Input/Output
42
qwen3-max-preview
Alibaba
88.6
27.7K
262K
¥6.2 / ¥24.8Input/Output
43
grok-4.1-thinking
Xai
88.3
63.6K
200K
¥14.4 / ¥72Input/Output
44
qwen3.6-plus
Alibaba
88.0
18.2K
1M
¥3.6 / ¥21.6Input/Output
45
claude-sonnet-4-5-20250929
Anthropic
87.7
76.1K
200K
¥21.6 / ¥108Input/Output
46
grok-4.1
Xai
87.5
65.7K
200K
¥14.4 / ¥72Input/Output
47
glm-4.7
Zai
87.2
12.1K
205K
¥0 / ¥0Input/Output
48
mimo-v2-pro
Xiaomi
86.9
22.6K
1.05M
¥7.2 / ¥21.6Input/Output
49
gemma-4-26b-a4b
Google
86.6
5.8K
262K
¥0.94 / ¥2.88Input/Output
50
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
86.4
77.8K
200K
¥21.6 / ¥108Input/Output
51
ernie-5.0-preview-1022
Baidu
86.1
4.7K
128K
¥7.92 / ¥14.4Input/Output
52
mistral-large-3
Mistral
85.8
42.6K
262K
¥3.6 / ¥10.8Input/Output
53
glm-4.5
Zai
85.5
24.3K
131K
¥4.32 / ¥15.8Input/Output
54
chatgpt-4o-latest-20250326
Openai
85.2
82.5K
128K
¥18 / ¥72Input/Output
55
deepseek-v4-flash
Deepseek
85.0
16.7K
1M
¥1.01 / ¥2.02Input/Output
56
deepseek-r1-0528
Deepseek
84.7
18.5K
164K
¥3.6 / ¥15.5Input/Output
57
mimo-v2.5
Xiaomi
84.4
16K
1.05M
¥2.88 / ¥14.4Input/Output
58
mistral-medium-2508
Mistral
84.1
92K
262K
¥2.88 / ¥14.4Input/Output
59
longcat-flash-chat-2602-exp
Meituan
83.8
23.7K
128K
¥1.08 / ¥10.8Input/Output
60
grok-3-preview-02-24
Xai
83.6
32.9K
1M
¥9 / ¥18Input/Output
61
deepseek-v3.2-exp-thinking
Deepseek
83.3
9.1K
128K
¥0 / ¥0Input/Output
62
deepseek-v3.2
Deepseek
83.0
46.2K
128K
¥2.09 / ¥3.1Input/Output
63
deepseek-v3.2-exp
Deepseek
82.7
11.9K
128K
¥0 / ¥0Input/Output
64
deepseek-v4-flash-thinking
Deepseek
82.5
16.5K
1M
¥1.01 / ¥2.02Input/Output
65
gpt-5.1
Openai
82.2
43.5K
400K
¥9 / ¥72Input/Output
66
longcat-flash-chat
Meituan
81.9
11.4K
128K
¥1.08 / ¥10.8Input/Output
67
qwen3-vl-235b-a22b-instruct
Alibaba
81.6
11.5K
128K
¥2.16 / ¥8.64Input/Output
68
kimi-k2.5-instant
Moonshot
81.3
8.2K
262K
¥4.32 / ¥21.6Input/Output
69
gpt-5.5-instant
Openai
81.1
24.9K
400K
¥9 / ¥72Input/Output
70
amazon-nova-experimental-chat-12-10
Amazon
80.8
3.7K
-
-
71
deepseek-v3.1-terminus-thinking
Deepseek
80.5
3.5K
128K
¥1.8 / ¥5.04Input/Output
72
deepseek-v3.1
Deepseek
80.2
15K
128K
¥1.44 / ¥5.04Input/Output
73
deepseek-v3.2-thinking
Deepseek
79.9
40.1K
128K
¥2.09 / ¥3.1Input/Output
74
qwen3-235b-a22b-instruct-2507
Alibaba
79.7
95.5K
128K
¥2.09 / ¥8.23Input/Output
75
qwen3-next-80b-a3b-instruct
Alibaba
79.4
22.9K
131K
¥1.04 / ¥4.13Input/Output
76
claude-opus-4-1-20250805-thinking-16k
Anthropic
79.1
49.8K
200K
¥108 / ¥540Input/Output
77
deepseek-v3.1-terminus
Deepseek
78.8
3.7K
128K
¥1.8 / ¥5.04Input/Output
78
qwen3.5-122b-a10b
Alibaba
78.6
26.7K
262K
¥2.88 / ¥23Input/Output
79
gemini-2.5-flash
Google
78.3
122.5K
1.05M
¥2.16 / ¥18Input/Output
80
claude-opus-4-1-20250805
Anthropic
78.0
77.4K
200K
¥108 / ¥540Input/Output
81
gpt-4.5-preview-2025-02-27
Openai
77.7
14.5K
8.19K
¥216 / ¥432Input/Output
82
gpt-5.2-high
Openai
77.4
46.1K
400K
¥12.6 / ¥101Input/Output
83
deepseek-v3.1-thinking
Deepseek
77.2
11.7K
128K
¥1.44 / ¥5.04Input/Output
84
gemini-3.1-flash-lite-preview
Google
76.9
35.1K
1.05M
¥1.8 / ¥10.8Input/Output
85
amazon-nova-experimental-chat-11-10
Amazon
76.6
25.4K
-
-
86
gpt-5.4-mini-high
Openai
76.3
26.4K
400K
¥5.4 / ¥32.4Input/Output
87
kimi-k2-thinking-turbo
Moonshot
76.0
60.2K
262K
¥17.3 / ¥72Input/Output
88
qwen3-235b-a22b-thinking-2507
Alibaba
75.8
9K
131K
¥2.07 / ¥8.26Input/Output
89
qwen3-max-2025-09-23
Alibaba
75.5
9.2K
258K
¥6.19 / ¥24.7Input/Output
90
mimo-v2-flash (non-thinking)
Xiaomi
75.2
44.6K
262K
¥0.72 / ¥2.16Input/Output
91
gpt-5.2
Openai
74.9
46.5K
400K
¥12.6 / ¥101Input/Output
92
grok-4-0709
Xai
74.7
41.4K
256K
¥21.6 / ¥108Input/Output
93
o3-2025-04-16
Openai
74.4
59.8K
200K
¥14.4 / ¥57.6Input/Output
94
grok-4-fast-chat
Xai
74.1
6.8K
2M
¥1.44 / ¥3.6Input/Output
95
grok-4.3
Xai
73.8
15.8K
1M
¥9 / ¥18Input/Output
96
grok-4-1-fast-reasoning
Xai
73.5
54.6K
2M
¥1.44 / ¥3.6Input/Output
97
hunyuan-hy3-preview
Tencent
73.3
5.8K
256K
¥0 / ¥0Input/Output
98
qwen3.5-27b
Alibaba
73.0
25.8K
262K
¥2.16 / ¥17.3Input/Output
99
gemini-2.5-flash-preview-09-2025
Google
72.7
32.9K
1M
¥2.16 / ¥18Input/Output
100
hunyuan-vision-1.5-thinking
Tencent
72.4
2.2K
-
-
101
gpt-5-high
Openai
72.1
31.9K
400K
¥9 / ¥72Input/Output
102
gpt-5-chat
Openai
71.9
31.6K
400K
¥9 / ¥72Input/Output
103
step-3.5-flash
Stepfun
71.6
34.5K
256K
¥0.69 / ¥2.07Input/Output
104
mimo-v2-omni
Xiaomi
71.3
3K
262K
¥2.88 / ¥14.4Input/Output
105
qwen3-vl-235b-a22b-thinking
Alibaba
71.0
7.9K
131K
¥2.06 / ¥8.26Input/Output
106
minimax-m2.7
Minimax
70.8
23.3K
205K
¥0 / ¥0Input/Output
107
hunyuan-t1-20250711
Tencent
70.5
4.7K
131K
¥0 / ¥0Input/Output
108
amazon-nova-experimental-chat-26-01-10
Amazon
70.2
3.4K
-
-
109
grok-4-fast-reasoning
Xai
69.9
18.7K
2M
¥1.44 / ¥3.6Input/Output
110
qwen3.5-flash
Alibaba
69.6
29.6K
1M
¥1.24 / ¥12.4Input/Output
111
qwen3.5-35b-a3b
Alibaba
69.4
27.3K
262K
¥1.8 / ¥14.4Input/Output
112
mimo-v2-flash (thinking)
Xiaomi
69.1
11K
262K
¥0.72 / ¥2.16Input/Output
113
amazon-nova-experimental-chat-10-20
Amazon
68.8
11.5K
-
-
114
qwen3-235b-a22b-no-thinking
Alibaba
68.5
38.2K
131K
¥2.07 / ¥8.26Input/Output
115
claude-haiku-4-5-20251001
Anthropic
68.2
78.1K
200K
¥7.2 / ¥36Input/Output
116
minimax-m2.1-preview
Minimax
68.0
17.1K
205K
¥0 / ¥0Input/Output
117
gpt-5.3-chat-latest
Openai
67.7
30.9K
128K
¥12.6 / ¥101Input/Output
118
qwen3-30b-a3b-instruct-2507
Alibaba
67.4
23.7K
262K
¥2.16 / ¥3.6Input/Output
119
glm-4.5-air
Zai
67.1
31.1K
131K
¥0 / ¥0Input/Output
120
gpt-4.1-2025-04-14
Openai
66.9
51K
1.05M
¥14.4 / ¥57.6Input/Output
121
kimi-k2-0905-preview
Moonshot
66.6
11.8K
262K
¥4.32 / ¥18Input/Output
122
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
66.3
47.2K
1.05M
¥0.72 / ¥2.88Input/Output
123
nvidia-nemotron-3-super-120b-a12b
Nvidia
66.0
7.5K
262K
¥1.44 / ¥5.76Input/Output
124
hunyuan-turbos-20250416
Tencent
65.7
10.7K
131K
¥0 / ¥0Input/Output
125
claude-opus-4-20250514-thinking-16k
Anthropic
65.5
36.9K
200K
¥108 / ¥540Input/Output
126
deepseek-v3-0324
Deepseek
65.2
45.5K
75K
¥1.44 / ¥5.76Input/Output
127
glm-4.6v
Zai
64.9
2.8K
128K
¥2.16 / ¥6.48Input/Output
128
gpt-5-mini-high
Openai
64.6
27K
400K
¥1.8 / ¥14.4Input/Output
129
gpt-5.4-nano-high
Openai
64.3
25.6K
400K
¥1.44 / ¥9Input/Output
130
deepseek-r1
Deepseek
64.1
18.5K
164K
¥5.04 / ¥18Input/Output
131
kimi-k2-0711-preview
Moonshot
63.8
27.6K
131K
¥4.32 / ¥18Input/Output
132
mistral-medium-2505
Mistral
63.5
33.2K
262K
¥2.88 / ¥14.4Input/Output
133
gemini-2.5-flash-lite-preview-06-17-thinking
Google
63.2
32.9K
65.5K
¥0.72 / ¥2.88Input/Output
134
qwen3-next-80b-a3b-thinking
Alibaba
63.0
13.7K
131K
¥1.04 / ¥10.3Input/Output
135
grok-3-mini-high
Xai
62.7
17K
128K
¥0 / ¥0Input/Output
136
qwen2.5-max
Alibaba
62.4
32.6K
32K
¥11.5 / ¥46Input/Output
137
o1-2024-12-17
Openai
62.1
27.8K
128K
¥108 / ¥432Input/Output
138
qwen3-235b-a22b
Alibaba
61.8
26.3K
131K
¥2.07 / ¥8.26Input/Output
139
gpt-oss-120b
Openai
61.6
30.6K
131K
¥1.08 / ¥4.32Input/Output
140
claude-opus-4-20250514
Anthropic
61.3
44.2K
200K
¥108 / ¥540Input/Output
141
amazon-nova-experimental-chat-10-09
Amazon
61.0
2.8K
-
-
142
nova-2-lite
Amazon
60.7
12.2K
128K
¥2.38 / ¥19.8Input/Output
143
ling-flash-2.0
Ant Group
60.4
7K
131K
¥1.01 / ¥4.1Input/Output
144
grok-3-mini-beta
Xai
60.2
22.7K
1M
¥9 / ¥18Input/Output
145
minimax-m2.5
Minimax
59.9
36.3K
205K
¥0 / ¥0Input/Output
146
gemma-3-27b-it
Google
59.6
47.5K
128K
¥2.15 / ¥2.15Input/Output
147
mercury-2
Inception Ai
59.3
3.1K
128K
¥1.8 / ¥5.4Input/Output
148
qwen3-coder-480b-a35b-instruct
Alibaba
59.1
25.7K
262K
¥6.2 / ¥24.8Input/Output
149
intellect-3
-
58.8
5.3K
131K
¥1.44 / ¥7.92Input/Output
150
gemini-2.0-flash-001
Google
58.5
43.8K
1.05M
¥1.08 / ¥4.32Input/Output
151
glm-4.7-flash
Zai
58.2
11.7K
200K
¥0 / ¥0Input/Output
152
o1-preview
Openai
57.9
31.1K
128K
¥108 / ¥432Input/Output
153
o4-mini-2025-04-16
Openai
57.7
45.5K
200K
¥7.92 / ¥31.7Input/Output
154
step-3
Stepfun
57.4
6.5K
65.5K
¥1.8 / ¥4.68Input/Output
155
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
57.1
15.5K
131K
¥0 / ¥0Input/Output
156
claude-sonnet-4-20250514-thinking-32k
Anthropic
56.8
35.1K
200K
¥21.6 / ¥108Input/Output
157
trinity-large-thinking
-
56.5
23.9K
262K
¥1.8 / ¥6.48Input/Output
158
minimax-m1
Minimax
56.3
35.2K
1M
¥0.95 / ¥9.03Input/Output
159
minimax-m2
Minimax
56.0
6.9K
197K
¥0 / ¥0Input/Output
160
gpt-4.1-mini-2025-04-14
Openai
55.7
39.3K
1.05M
¥2.88 / ¥11.5Input/Output
161
qwen3-32b
Alibaba
55.4
3.9K
131K
¥2.07 / ¥8.26Input/Output
162
mistral-small-2506
Mistral
55.2
17.7K
262K
¥2.88 / ¥14.4Input/Output
163
claude-sonnet-4-20250514
Anthropic
54.9
40.3K
200K
¥21.6 / ¥108Input/Output
164
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia
54.6
3.3K
131K
¥2.88 / ¥2.88Input/Output
165
trinity-large-preview
-
54.3
28.3K
262K
¥1.8 / ¥6.48Input/Output
166
o3-mini-high
Openai
54.0
18.6K
200K
¥7.92 / ¥31.7Input/Output
167
step-1o-turbo-202506
Stepfun
53.8
9K
-
-
168
gemma-3-12b-it
Google
53.5
3.8K
128K
¥1.96 / ¥1.96Input/Output
169
glm-4.5v
Zai
53.2
5K
64K
¥4.32 / ¥13Input/Output
170
deepseek-v3
Deepseek
52.9
21.8K
128K
¥0 / ¥0Input/Output
171
ring-flash-2.0
Ant Group
52.6
7.1K
131K
¥1.01 / ¥4.1Input/Output
172
command-a-03-2025
Cohere
52.4
56.3K
256K
¥18 / ¥72Input/Output
173
glm-4-plus-0111
Zai
52.1
5.8K
128K
¥72 / ¥72Input/Output
174
gemini-2.0-flash-lite-preview-02-05
Google
51.8
25K
1.05M
¥0.54 / ¥2.16Input/Output
175
qwq-32b
Alibaba
51.5
25.4K
131K
¥2.07 / ¥6.2Input/Output
176
qwen-plus-0125
Alibaba
51.3
5.8K
1M
¥0.83 / ¥2.07Input/Output
177
step-2-16k-exp-202412
Stepfun
51.0
4.8K
16.4K
¥37.5 / ¥118Input/Output
178
gpt-5-nano-high
Openai
50.7
8.3K
400K
¥0.36 / ¥2.88Input/Output
179
hunyuan-turbos-20250226
Tencent
50.4
2.2K
131K
¥0 / ¥0Input/Output
180
llama-3.1-nemotron-ultra-253b-v1
Nvidia
50.1
2.5K
128K
¥4.32 / ¥13Input/Output
181
gemini-1.5-pro-002
Google
49.9
55.6K
-
-
182
o3-mini
Openai
49.6
57.3K
200K
¥7.92 / ¥31.7Input/Output
183
o1-mini
Openai
49.3
52K
128K
¥7.92 / ¥31.7Input/Output
184
qwen3-30b-a3b
Alibaba
49.0
26.5K
128K
¥0.79 / ¥7.78Input/Output
185
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
48.7
38.8K
-
-
186
olmo-3.1-32b-instruct
Allenai
48.5
12.2K
200K
¥14.4 / ¥57.6Input/Output
187
hunyuan-turbo-0110
Tencent
48.2
2.3K
-
-
188
llama-3.3-nemotron-49b-super-v1
Nvidia
47.9
2.2K
131K
¥0 / ¥0Input/Output
189
gemma-3n-e4b-it
Google
47.6
22.6K
128K
¥0 / ¥0Input/Output
190
grok-2-2024-08-13
Xai
47.4
63.5K
1M
¥9 / ¥18Input/Output
191
yi-lightning
-
47.1
27.3K
12K
¥1.44 / ¥1.44Input/Output
192
gpt-4o-2024-05-13
Openai
46.8
112.9K
128K
¥36 / ¥108Input/Output
193
claude-3-7-sonnet-20250219
Anthropic
46.5
43.2K
200K
¥21.6 / ¥108Input/Output
194
qwen2.5-plus-1127
Alibaba
46.2
10.2K
-
-
195
olmo-3-32b-think
Allenai
46.0
5.9K
128K
¥2.16 / ¥3.24Input/Output
196
claude-3-5-sonnet-20241022
Anthropic
45.7
88.4K
200K
¥21.6 / ¥108Input/Output
197
granite-4.1-8b
Ibm
45.4
3.6K
131K
¥0.36 / ¥0.72Input/Output
198
molmo-2-8b
Allenai
45.1
805
-
-
199
deepseek-v2.5-1210
Deepseek
44.8
6.8K
1M
¥1.01 / ¥2.02Input/Output
200
athene-v2-chat
-
44.6
24.7K
-
-
201
gemma-3-4b-it
Google
44.3
4.2K
128K
¥1.44 / ¥1.44Input/Output
202
glm-4-plus
Zai
44.0
26.1K
128K
¥54 / ¥54Input/Output
203
hunyuan-large-2025-02-10
Tencent
43.7
3.7K
-
-
204
llama-4-maverick-17b-128e-instruct
Meta
43.5
40K
1M
¥1.8 / ¥6.26Input/Output
205
gpt-oss-20b
Openai
43.2
10.6K
131K
¥0.32 / ¥1.3Input/Output
206
gemini-1.5-flash-002
Google
42.9
34.9K
2M
¥0.54 / ¥2.2Input/Output
207
gpt-4o-mini-2024-07-18
Openai
42.6
68.7K
128K
¥1.08 / ¥4.32Input/Output
208
gpt-4.1-nano-2025-04-14
Openai
42.3
6.1K
1.05M
¥14.4 / ¥57.6Input/Output
209
llama-3.1-405b-instruct-bf16
Meta
42.1
41.4K
128K
¥0 / ¥0Input/Output
210
llama-3.1-nemotron-70b-instruct
Nvidia
41.8
7.1K
128K
¥0 / ¥0Input/Output
211
gpt-4o-2024-08-06
Openai
41.5
45.5K
128K
¥18 / ¥72Input/Output
212
qwen-max-0919
Alibaba
41.2
16.5K
131K
¥2.48 / ¥9.91Input/Output
213
mercury
Inception Ai
40.9
2K
128K
¥1.8 / ¥5.4Input/Output
214
llama-3.1-405b-instruct-fp8
Meta
40.7
59.7K
128K
¥0 / ¥0Input/Output
215
claude-3-5-sonnet-20240620
Anthropic
40.4
82.4K
200K
¥21.6 / ¥108Input/Output
216
llama-4-scout-17b-16e-instruct
Meta
40.1
30.3K
128K
¥1.44 / ¥5.62Input/Output
217
grok-2-mini-2024-08-13
Xai
39.8
52.6K
1M
¥9 / ¥18Input/Output
218
gemini-advanced-0514
Google
39.6
50.1K
-
-
219
mistral-small-3.1-24b-instruct-2503
Mistral
39.3
33.2K
262K
¥2.88 / ¥14.4Input/Output
220
llama-3.3-70b-instruct
Meta
39.0
54.7K
128K
¥0 / ¥0Input/Output
221
hunyuan-standard-2025-02-10
Tencent
38.7
3.9K
-
-
222
gemini-1.5-pro-001
Google
38.4
79.1K
-
-
223
gpt-4-turbo-2024-04-09
Openai
38.2
98.1K
128K
¥72 / ¥216Input/Output
224
deepseek-v2.5
Deepseek
37.9
24.6K
1M
¥1.01 / ¥2.02Input/Output
225
olmo-3.1-32b-think
Allenai
37.6
8.5K
200K
¥14.4 / ¥57.6Input/Output
226
qwen2.5-72b-instruct
Alibaba
37.3
39.4K
131K
¥4.13 / ¥12.4Input/Output
227
mistral-large-2407
Mistral
37.0
45.5K
131K
¥14.4 / ¥43.2Input/Output
228
mistral-large-2411
Mistral
36.8
28.1K
128K
¥14.4 / ¥43.2Input/Output
229
athene-70b-0725
-
36.5
19.6K
-
-
230
gpt-4-1106-preview
Openai
36.2
100.1K
8.19K
¥216 / ¥432Input/Output
231
hunyuan-large-vision
Tencent
35.9
5.4K
-
-
232
gpt-4-0125-preview
Openai
35.7
93.4K
8.19K
¥216 / ¥432Input/Output
233
claude-3-opus-20240229
Anthropic
35.4
194.9K
200K
¥108 / ¥540Input/Output
234
llama-3.1-70b-instruct
Meta
35.1
55.2K
131K
¥2.88 / ¥2.88Input/Output
235
amazon-nova-pro-v1.0
Amazon
34.8
24.7K
300K
¥5.76 / ¥23Input/Output
236
llama-3.1-tulu-3-70b
Allenai
34.5
2.8K
-
-
237
claude-3-5-haiku-20241022
Anthropic
34.3
70K
200K
¥5.76 / ¥28.8Input/Output
238
magistral-medium-2506
Mistral
34.0
11.6K
128K
¥14.4 / ¥36Input/Output
239
reka-core-20240904
-
33.7
7.3K
-
-
240
ibm-granite-h-small
Ibm
33.4
5.7K
-
-
241
gemini-1.5-flash-001
Google
33.1
62.8K
2M
¥0.54 / ¥2.2Input/Output
242
jamba-1.5-large
-
32.9
8.7K
256K
¥0 / ¥0Input/Output
243
mistral-small-24b-instruct-2501
Mistral
32.6
14.7K
262K
¥2.88 / ¥14.4Input/Output
244
gemma-2-27b-it
Google
32.3
75.8K
8.19K
¥0.58 / ¥0.58Input/Output
245
qwen2.5-coder-32b-instruct
Alibaba
32.0
5.4K
131K
¥2.07 / ¥6.2Input/Output
246
command-r-plus-08-2024
Cohere
31.8
9.9K
128K
¥18 / ¥72Input/Output
247
amazon-nova-lite-v1.0
Amazon
31.5
19.4K
300K
¥0.43 / ¥1.73Input/Output
248
llama-3.1-nemotron-51b-instruct
Nvidia
31.2
3.7K
128K
¥0 / ¥0Input/Output
249
gemma-2-9b-it-simpo
-
30.9
10.1K
8.19K
¥1.44 / ¥1.44Input/Output
250
glm-4-0520
Zai
30.6
9.8K
128K
¥108 / ¥108Input/Output
251
gemini-1.5-flash-8b-001
Google
30.4
35.6K
2M
¥0.54 / ¥2.2Input/Output
252
nemotron-4-340b-instruct
Nvidia
30.1
19.7K
-
-
253
c4ai-aya-expanse-32b
Cohere
29.8
27.1K
-
-
254
llama-3-70b-instruct
Meta
29.5
156.9K
8.19K
¥3.67 / ¥5.33Input/Output
255
claude-3-sonnet-20240229
Anthropic
29.2
109.3K
200K
¥21.6 / ¥108Input/Output
256
reka-flash-20240904
-
29.0
7.5K
65.5K
¥0.72 / ¥1.44Input/Output
257
olmo-2-0325-32b-instruct
Allenai
28.7
3.3K
-
-
258
phi-4
Microsoft
28.4
24.1K
128K
¥0.9 / ¥3.6Input/Output
259
amazon-nova-micro-v1.0
Amazon
28.1
19.4K
128K
¥0.25 / ¥1.01Input/Output
260
gemma-2-9b-it
Google
27.9
54.6K
8.19K
¥1.44 / ¥1.44Input/Output
261
gpt-4-0314
Openai
27.6
54.2K
8.19K
¥216 / ¥432Input/Output
262
command-r-plus
Cohere
27.3
77.6K
128K
¥18 / ¥72Input/Output
263
qwen2-72b-instruct
Alibaba
27.0
37.3K
131K
¥4.13 / ¥12.4Input/Output
264
hunyuan-standard-256k
Tencent
26.7
2.7K
-
-
265
claude-3-haiku-20240307
Anthropic
26.5
117.7K
200K
¥1.8 / ¥9Input/Output
266
llama-3.1-tulu-3-8b
Allenai
26.2
2.9K
-
-
267
deepseek-coder-v2
Deepseek
25.9
15.1K
1M
¥1.01 / ¥2.02Input/Output
268
ministral-8b-2410
Mistral
25.6
4.8K
128K
¥0.72 / ¥0.72Input/Output
269
command-r-08-2024
Cohere
25.3
10.1K
128K
¥18 / ¥72Input/Output
270
jamba-1.5-mini
-
25.1
8.9K
256K
¥0 / ¥0Input/Output
271
llama-3.1-8b-instruct
Meta
24.8
49.6K
131K
¥0.79 / ¥0.79Input/Output
272
gpt-4-0613
Openai
24.5
88.7K
8.19K
¥216 / ¥432Input/Output
273
c4ai-aya-expanse-8b
Cohere
24.2
9.8K
-
-
274
mistral-large-2402
Mistral
24.0
62.4K
262K
¥2.88 / ¥14.4Input/Output
275
qwen1.5-110b-chat
Alibaba
23.7
26.2K
-
-
276
yi-1.5-34b-chat
-
23.4
24.1K
-
-
277
reka-flash-21b-20240226-online
-
23.1
15.5K
-
-
278
qwen1.5-72b-chat
Alibaba
22.8
39.3K
-
-
279
llama-3-8b-instruct
Meta
22.6
104.6K
8.19K
¥0.29 / ¥0.29Input/Output
280
mistral-medium
Mistral
22.3
34.6K
262K
¥2.88 / ¥14.4Input/Output
281
reka-flash-21b-20240226
-
22.0
24.8K
-
-
282
command-r
Cohere
21.7
54K
128K
¥18 / ¥72Input/Output
283
mixtral-8x22b-instruct-v0.1
Mistral
21.4
51.4K
64K
¥14.4 / ¥43.2Input/Output
284
qwq-32b-preview
Alibaba
21.2
3.2K
131K
¥2.07 / ¥6.2Input/Output
285
internlm2_5-20b-chat
-
20.9
9.9K
-
-
286
gemma-2-2b-it
Google
20.6
46.6K
128K
¥0 / ¥0Input/Output
287
granite-3.1-8b-instruct
Ibm
20.3
3.1K
-
-
288
gemini-pro-dev-api
Google
20.1
18.4K
1.05M
¥14.4 / ¥86.4Input/Output
289
zephyr-orpo-141b-A35b-v0.1
-
19.8
4.7K
200K
¥108 / ¥432Input/Output
290
phi-3-medium-4k-instruct
Microsoft
19.5
25.1K
4.1K
¥1.22 / ¥4.9Input/Output
291
qwen1.5-32b-chat
Alibaba
19.2
21.7K
-
-
292
starling-lm-7b-beta
-
18.9
16.1K
200K
¥5.4 / ¥18.7Input/Output
293
mixtral-8x7b-instruct-v0.1
Mistral
18.7
73.5K
32K
¥5.04 / ¥5.04Input/Output
294
gemini-pro
Google
18.4
6.4K
1.05M
¥14.4 / ¥86.4Input/Output
295
yi-34b-chat
-
18.1
15.5K
-
-
296
qwen1.5-14b-chat
Alibaba
17.8
17.8K
-
-
297
granite-3.1-2b-instruct
Ibm
17.5
3.2K
-
-
298
gpt-3.5-turbo-0125
Openai
17.3
66.2K
16.4K
¥3.6 / ¥10.8Input/Output
299
tulu-2-dpo-70b
-
17.0
6.5K
-
-
300
wizardlm-70b
Microsoft
16.7
8.2K
-
-
301
dbrx-instruct-preview
-
16.4
32.2K
-
-
302
llama-2-70b-chat
Meta
16.2
38.5K
-
-
303
nous-hermes-2-mixtral-8x7b-dpo
-
15.9
3.8K
1M
¥36 / ¥180Input/Output
304
phi-3-small-8k-instruct
Microsoft
15.6
17.8K
8.19K
¥1.08 / ¥4.32Input/Output
305
llama-3.2-3b-instruct
Meta
15.3
7.9K
131K
¥0.22 / ¥0.35Input/Output
306
starling-lm-7b-alpha
-
15.0
10.2K
200K
¥5.4 / ¥18.7Input/Output
307
openchat-3.5-0106
-
14.8
12.6K
-
-
308
vicuna-33b
-
14.5
22.5K
-
-
309
deepseek-llm-67b-chat
Deepseek
14.2
4.9K
1M
¥1.01 / ¥2.02Input/Output
310
snowflake-arctic-instruct
-
13.9
32.8K
-
-
311
llama2-70b-steerlm-chat
Nvidia
13.6
3.6K
-
-
312
openchat-3.5
-
13.4
8K
-
-
313
granite-3.0-8b-instruct
Ibm
13.1
6.6K
-
-
314
gpt-3.5-turbo-1106
Openai
12.8
16.6K
16.4K
¥7.2 / ¥14.4Input/Output
315
gemma-1.1-7b-it
Google
12.5
23.9K
-
-
316
openhermes-2.5-mistral-7b
-
12.3
5K
1M
¥36 / ¥180Input/Output
317
mistral-7b-instruct-v0.2
Mistral
12.0
19.4K
262K
¥2.88 / ¥14.4Input/Output
318
llama-2-13b-chat
Meta
11.7
19.2K
-
-
319
qwen1.5-7b-chat
Alibaba
11.4
4.7K
-
-
320
solar-10.7b-instruct-v1.0
-
11.1
4.2K
128K
¥0 / ¥0Input/Output
321
dolphin-2.2.1-mistral-7b
-
10.9
1.7K
262K
¥2.88 / ¥14.4Input/Output
322
phi-3-mini-4k-instruct-june-2024
Microsoft
10.6
12.3K
4.1K
¥0.94 / ¥3.74Input/Output
323
granite-3.0-2b-instruct
Ibm
10.3
6.8K
-
-
324
wizardlm-13b
Microsoft
10.0
7K
-
-
325
phi-3-mini-4k-instruct
Microsoft
9.7
20.1K
4.1K
¥0.94 / ¥3.74Input/Output
326
zephyr-7b-beta
-
9.5
11.1K
-
-
327
mpt-30b-chat
-
9.2
2.6K
-
-
328
codellama-34b-instruct
Meta
8.9
7.4K
-
-
329
zephyr-7b-alpha
-
8.6
1.8K
-
-
330
vicuna-13b
-
8.4
19.4K
-
-
331
codellama-70b-instruct
Meta
8.1
1.1K
-
-
332
gemma-7b-it
Google
7.8
8.9K
-
-
333
llama-3.2-1b-instruct
Meta
7.5
8K
16.4K
¥0.07 / ¥0.08Input/Output
334
falcon-180b-chat
-
7.2
1.3K
-
-
335
llama-2-7b-chat
Meta
7.0
14.1K
128K
¥4.03 / ¥48Input/Output
336
guanaco-33b
-
6.7
2.9K
200K
¥14.4 / ¥57.6Input/Output
337
qwen-14b-chat
Alibaba
6.4
5K
32.8K
¥1.04 / ¥3.1Input/Output
338
phi-3-mini-128k-instruct
Microsoft
6.1
20.7K
128K
¥0.94 / ¥3.74Input/Output
339
smollm2-1.7b-instruct
-
5.8
2.2K
-
-
340
stripedhyena-nous-7b
-
5.6
5.2K
-
-
341
olmo-7b-instruct
Allenai
5.3
6.3K
-
-
342
vicuna-7b
-
5.0
6.9K
-
-
343
palm-2
Google
4.7
8.6K
-
-
344
mistral-7b-instruct
Mistral
4.5
9K
262K
¥2.88 / ¥14.4Input/Output
345
gemma-1.1-2b-it
Google
4.2
10.9K
-
-
346
gemma-2b-it
Google
3.9
4.8K
-
-
347
qwen1.5-4b-chat
Alibaba
3.6
7.6K
-
-
348
koala-13b
-
3.3
7K
-
-
349
chatglm3-6b
-
3.1
4.7K
200K
¥5.4 / ¥18.7Input/Output
350
gpt4all-13b-snoozy
-
2.8
1.7K
1M
¥36 / ¥216Input/Output
351
mpt-7b-chat
-
2.5
3.9K
-
-
352
RWKV-4-Raven-14B
-
2.2
4.8K
-
-
353
chatglm2-6b
-
1.9
2.7K
200K
¥5.4 / ¥18.7Input/Output
354
alpaca-13b
-
1.7
5.7K
-
-
355
chatglm-6b
-
1.4
4.9K
200K
¥5.4 / ¥18.7Input/Output
356
oasst-pythia-12b
-
1.1
6.3K
-
-
357
fastchat-t5-3b
-
0.8
4.2K
-
-
358
stablelm-tuned-alpha-7b
-
0.6
3.3K
-
-
359
dolly-v2-12b
-
0.3
3.4K
-
-
360
llama-13b
Meta
0.0
2.4K
-
-
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 34.2K 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

总榜排行榜看什么指标?

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。

总榜模型应该怎么选?

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。