Chat · Text · Coding Leaderboard

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

Selection guide

Coding model ranking guide

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

claude-opus-4-6-thinkingclaude-opus-4-6claude-opus-4-7-thinkingclaude-opus-4-7claude-opus-4-5-20251101-thinking-32k
Current DirectoryChat · Text · Coding
Models355
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / CodingPublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
claude-opus-4-6-thinking
Anthropic
100.0
8.3K
1M
¥36 / ¥180Input/Output
2
claude-opus-4-6
Anthropic
99.7
9.6K
1M
¥36 / ¥180Input/Output
3
claude-opus-4-7-thinking
Anthropic
99.4
5.6K
1M
¥36 / ¥180Input/Output
4
claude-opus-4-7
Anthropic
99.2
5.9K
1M
¥36 / ¥180Input/Output
5
claude-opus-4-5-20251101-thinking-32k
Anthropic
98.9
7.6K
200K
¥108 / ¥540Input/Output
6
glm-5.1
Zai
98.6
3.8K
200K
¥0 / ¥0Input/Output
7
mimo-v2.5-pro
Xiaomi
98.3
4.3K
1.05M
¥7.2 / ¥21.6Input/Output
8
gpt-5.5-high
Openai
98.0
4.5K
1.05M
¥36 / ¥216Input/Output
9
claude-sonnet-4-6
Anthropic
97.7
7.2K
1M
¥21.6 / ¥108Input/Output
10
qwen3.7-max-preview
Alibaba
97.5
1.1K
1M
¥18 / ¥54Input/Output
11
claude-opus-4-5-20251101
Anthropic
97.2
15.7K
200K
¥36 / ¥180Input/Output
12
gpt-5.4-high
Openai
96.9
7.2K
1.05M
¥18 / ¥108Input/Output
13
gemini-3.5-flash
Google
96.6
2.6K
1.05M
¥10.8 / ¥64.8Input/Output
14
ernie-5.1
Baidu
96.3
3.9K
119K
¥5.4 / ¥21.6Input/Output
15
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
96.0
17.8K
200K
¥21.6 / ¥108Input/Output
16
gemini-3.1-pro-preview
Google
95.8
11.3K
1.05M
¥14.4 / ¥86.4Input/Output
17
qwen3.5-max-preview
Alibaba
95.5
5.5K
-
-
18
claude-sonnet-4-5-20250929
Anthropic
95.2
17.6K
200K
¥21.6 / ¥108Input/Output
19
kimi-k2.6
Moonshot
94.9
4.2K
262K
¥6.84 / ¥28.8Input/Output
20
amazon-nova-experimental-chat-26-02-10
Amazon
94.6
841
-
-
21
kimi-k2.5-instant
Moonshot
94.4
1.8K
262K
¥4.32 / ¥21.6Input/Output
22
gemini-3-pro
Google
94.1
8.6K
1.05M
¥14.4 / ¥86.4Input/Output
23
gpt-5.4
Openai
93.8
7.9K
1.05M
¥18 / ¥108Input/Output
24
gpt-5.5
Openai
93.5
4.7K
1.05M
¥36 / ¥216Input/Output
25
claude-opus-4-1-20250805-thinking-16k
Anthropic
93.2
9.8K
200K
¥108 / ¥540Input/Output
26
muse-spark
Meta
92.9
3.3K
-
-
27
mimo-v2-pro
Xiaomi
92.7
6.2K
1.05M
¥7.2 / ¥21.6Input/Output
28
kimi-k2.5-thinking
Moonshot
92.4
9.5K
262K
¥4.32 / ¥21.6Input/Output
29
longcat-flash-chat-2602-exp
Meituan
92.1
6.5K
128K
¥1.08 / ¥10.8Input/Output
30
claude-opus-4-1-20250805
Anthropic
91.8
15.5K
200K
¥108 / ¥540Input/Output
31
dola-seed-2.0-pro
Bytedance
91.5
10K
-
-
32
mimo-v2.5
Xiaomi
91.2
4.6K
1.05M
¥2.88 / ¥14.4Input/Output
33
longcat-flash-chat
Meituan
91.0
2.2K
128K
¥1.08 / ¥10.8Input/Output
34
qwen3.5-397b-a17b
Alibaba
90.7
8.6K
262K
¥3.1 / ¥18.6Input/Output
35
deepseek-v4-pro
Deepseek
90.4
4.9K
1M
¥3.13 / ¥6.26Input/Output
36
qwen3.6-plus
Alibaba
90.1
5.4K
1M
¥3.6 / ¥21.6Input/Output
37
qwen3.6-max-preview
Alibaba
89.8
1.3K
246K
¥9.5 / ¥56.9Input/Output
38
gemini-3-flash
Google
89.5
6.4K
1.05M
¥3.6 / ¥21.6Input/Output
39
grok-4.20-multi-agent-beta-0309
Xai
89.3
7.6K
2M
¥14.4 / ¥43.2Input/Output
40
grok-4.20-beta-0309-reasoning
Xai
89.0
7.7K
2M
¥14.4 / ¥43.2Input/Output
41
ernie-5.0-0110
Baidu
88.7
8.2K
128K
¥7.92 / ¥14.4Input/Output
42
qwen3-max-preview
Alibaba
88.4
5.4K
262K
¥6.2 / ¥24.8Input/Output
43
glm-5
Zai
88.1
5.4K
205K
¥7.2 / ¥23Input/Output
44
deepseek-v4-pro-thinking
Deepseek
87.9
4.5K
1M
¥3.13 / ¥6.26Input/Output
45
glm-4.7
Zai
87.6
2.4K
205K
¥0 / ¥0Input/Output
46
gemma-4-31b
Google
87.3
1.4K
262K
¥3.24 / ¥7.2Input/Output
47
kimi-k2-thinking-turbo
Moonshot
87.0
14.1K
262K
¥17.3 / ¥72Input/Output
48
deepseek-v3.2-thinking
Deepseek
86.7
8.2K
128K
¥2.09 / ¥3.1Input/Output
49
gpt-5.1-high
Openai
86.4
8.2K
400K
¥9 / ¥72Input/Output
50
gemini-2.5-pro
Google
86.2
25.8K
1.05M
¥9 / ¥72Input/Output
51
claude-haiku-4-5-20251001
Anthropic
85.9
18.3K
200K
¥7.2 / ¥36Input/Output
52
deepseek-v4-flash
Deepseek
85.6
4.8K
1M
¥1.01 / ¥2.02Input/Output
53
glm-4.6
Zai
85.3
7.5K
205K
¥4.32 / ¥15.8Input/Output
54
gpt-5.2-chat-latest-20260210
Openai
85.0
8.3K
400K
¥12.6 / ¥101Input/Output
55
minimax-m2.7
Minimax
84.7
6.6K
205K
¥0 / ¥0Input/Output
56
deepseek-v3.2
Deepseek
84.5
10.2K
128K
¥2.09 / ¥3.1Input/Output
57
grok-4.20-beta1
Xai
84.2
6.2K
2M
¥14.4 / ¥43.2Input/Output
58
grok-4.1-thinking
Xai
83.9
14.3K
200K
¥14.4 / ¥72Input/Output
59
amazon-nova-experimental-chat-26-01-10
Amazon
83.6
736
-
-
60
qwen3-235b-a22b-instruct-2507
Alibaba
83.3
20.6K
128K
¥2.09 / ¥8.23Input/Output
61
mistral-large-3
Mistral
83.1
9.6K
262K
¥3.6 / ¥10.8Input/Output
62
gemma-4-26b-a4b
Google
82.8
1.4K
262K
¥0.94 / ¥2.88Input/Output
63
gpt-5.2-high
Openai
82.5
11K
400K
¥12.6 / ¥101Input/Output
64
grok-4.1
Xai
82.2
14.8K
200K
¥14.4 / ¥72Input/Output
65
claude-opus-4-20250514-thinking-16k
Anthropic
81.9
6.7K
200K
¥108 / ¥540Input/Output
66
mimo-v2-omni
Xiaomi
81.6
848
262K
¥2.88 / ¥14.4Input/Output
67
qwen3-next-80b-a3b-instruct
Alibaba
81.4
4.8K
131K
¥1.04 / ¥4.13Input/Output
68
gpt-5.4-mini-high
Openai
81.1
6.9K
400K
¥5.4 / ¥32.4Input/Output
69
gemini-3-flash (thinking-minimal)
Google
80.8
12.8K
1.05M
¥3.6 / ¥21.6Input/Output
70
mimo-v2-flash (non-thinking)
Xiaomi
80.5
11.2K
262K
¥0.72 / ¥2.16Input/Output
71
qwen3-vl-235b-a22b-instruct
Alibaba
80.2
2.3K
128K
¥2.16 / ¥8.64Input/Output
72
qwen3-max-2025-09-23
Alibaba
79.9
2K
258K
¥6.19 / ¥24.7Input/Output
73
deepseek-v4-flash-thinking
Deepseek
79.7
4.7K
1M
¥1.01 / ¥2.02Input/Output
74
deepseek-v3.2-exp-thinking
Deepseek
79.4
1.9K
128K
¥0 / ¥0Input/Output
75
gpt-5.1
Openai
79.1
9.1K
400K
¥9 / ¥72Input/Output
76
gpt-5.5-instant
Openai
78.8
7.2K
400K
¥9 / ¥72Input/Output
77
mistral-medium-2508
Mistral
78.5
20.4K
262K
¥2.88 / ¥14.4Input/Output
78
gpt-5-high
Openai
78.2
6.4K
400K
¥9 / ¥72Input/Output
79
deepseek-v3.2-exp
Deepseek
78.0
2.5K
128K
¥0 / ¥0Input/Output
80
step-3.5-flash
Stepfun
77.7
8.4K
256K
¥0.69 / ¥2.07Input/Output
81
glm-4.5
Zai
77.4
4.8K
131K
¥4.32 / ¥15.8Input/Output
82
grok-3-preview-02-24
Xai
77.1
5.4K
1M
¥9 / ¥18Input/Output
83
gpt-5.2
Openai
76.8
11.4K
400K
¥12.6 / ¥101Input/Output
84
amazon-nova-experimental-chat-11-10
Amazon
76.6
5.3K
-
-
85
qwen3.5-122b-a10b
Alibaba
76.3
7K
262K
¥2.88 / ¥23Input/Output
86
hunyuan-hy3-preview
Tencent
76.0
1.6K
256K
¥0 / ¥0Input/Output
87
grok-4-fast-chat
Xai
75.7
1.2K
2M
¥1.44 / ¥3.6Input/Output
88
deepseek-v3.1-terminus-thinking
Deepseek
75.4
636
128K
¥1.8 / ¥5.04Input/Output
89
amazon-nova-experimental-chat-12-10
Amazon
75.1
704
-
-
90
qwen3-vl-235b-a22b-thinking
Alibaba
74.9
1.6K
131K
¥2.06 / ¥8.26Input/Output
91
deepseek-r1-0528
Deepseek
74.6
2.7K
164K
¥3.6 / ¥15.5Input/Output
92
grok-4.3
Xai
74.3
4.4K
1M
¥9 / ¥18Input/Output
93
ernie-5.0-preview-1203
Baidu
74.0
2K
128K
¥7.92 / ¥14.4Input/Output
94
qwen3-235b-a22b-thinking-2507
Alibaba
73.7
1.6K
131K
¥2.07 / ¥8.26Input/Output
95
gemini-2.5-flash
Google
73.4
25.2K
1.05M
¥2.16 / ¥18Input/Output
96
qwen3.5-27b
Alibaba
73.2
6.9K
262K
¥2.16 / ¥17.3Input/Output
97
minimax-m2.1-preview
Minimax
72.9
3.4K
205K
¥0 / ¥0Input/Output
98
hunyuan-vision-1.5-thinking
Tencent
72.6
437
-
-
99
deepseek-v3.1-thinking
Deepseek
72.3
1.9K
128K
¥1.44 / ¥5.04Input/Output
100
grok-4-fast-reasoning
Xai
72.0
4K
2M
¥1.44 / ¥3.6Input/Output
101
mimo-v2-flash (thinking)
Xiaomi
71.8
2.4K
262K
¥0.72 / ¥2.16Input/Output
102
qwen3-30b-a3b-instruct-2507
Alibaba
71.5
4.7K
262K
¥2.16 / ¥3.6Input/Output
103
chatgpt-4o-latest-20250326
Openai
71.2
15.9K
128K
¥18 / ¥72Input/Output
104
deepseek-v3.1
Deepseek
70.9
2.6K
128K
¥1.44 / ¥5.04Input/Output
105
ernie-5.0-preview-1022
Baidu
70.6
916
128K
¥7.92 / ¥14.4Input/Output
106
claude-sonnet-4-20250514-thinking-32k
Anthropic
70.3
6.4K
200K
¥21.6 / ¥108Input/Output
107
amazon-nova-experimental-chat-10-20
Amazon
70.1
2.3K
-
-
108
qwen3-coder-480b-a35b-instruct
Alibaba
69.8
4.8K
262K
¥6.2 / ¥24.8Input/Output
109
grok-4-1-fast-reasoning
Xai
69.5
12.7K
2M
¥1.44 / ¥3.6Input/Output
110
qwen3.5-35b-a3b
Alibaba
69.2
7.2K
262K
¥1.8 / ¥14.4Input/Output
111
grok-4-0709
Xai
68.9
8.2K
256K
¥21.6 / ¥108Input/Output
112
qwen3.5-flash
Alibaba
68.6
8.2K
1M
¥1.24 / ¥12.4Input/Output
113
o3-2025-04-16
Openai
68.4
11.8K
200K
¥14.4 / ¥57.6Input/Output
114
gpt-5-mini-high
Openai
68.1
5.5K
400K
¥1.8 / ¥14.4Input/Output
115
deepseek-v3.1-terminus
Deepseek
67.8
778
128K
¥1.8 / ¥5.04Input/Output
116
gpt-5.3-chat-latest
Openai
67.5
7.9K
128K
¥12.6 / ¥101Input/Output
117
nvidia-nemotron-3-super-120b-a12b
Nvidia
67.2
1.7K
262K
¥1.44 / ¥5.76Input/Output
118
gpt-5.4-nano-high
Openai
66.9
6.9K
400K
¥1.44 / ¥9Input/Output
119
gemini-2.5-flash-preview-09-2025
Google
66.7
6.8K
1M
¥2.16 / ¥18Input/Output
120
claude-opus-4-20250514
Anthropic
66.4
7.9K
200K
¥108 / ¥540Input/Output
121
gpt-5-chat
Openai
66.1
6K
400K
¥9 / ¥72Input/Output
122
gemini-3.1-flash-lite-preview
Google
65.8
9.1K
1.05M
¥1.8 / ¥10.8Input/Output
123
kimi-k2-0905-preview
Moonshot
65.5
2.2K
262K
¥4.32 / ¥18Input/Output
124
qwen3-235b-a22b-no-thinking
Alibaba
65.3
7K
131K
¥2.07 / ¥8.26Input/Output
125
gpt-4.5-preview-2025-02-27
Openai
65.0
1.9K
8.19K
¥216 / ¥432Input/Output
126
glm-4.5-air
Zai
64.7
6.1K
131K
¥0 / ¥0Input/Output
127
glm-4.6v
Zai
64.4
536
128K
¥2.16 / ¥6.48Input/Output
128
mercury-2
Inception Ai
64.1
768
128K
¥1.8 / ¥5.4Input/Output
129
qwen3-next-80b-a3b-thinking
Alibaba
63.8
2.7K
131K
¥1.04 / ¥10.3Input/Output
130
ling-flash-2.0
Ant Group
63.6
1.5K
131K
¥1.01 / ¥4.1Input/Output
131
gpt-4.1-2025-04-14
Openai
63.3
9.3K
1.05M
¥14.4 / ¥57.6Input/Output
132
nova-2-lite
Amazon
63.0
2.5K
128K
¥2.38 / ¥19.8Input/Output
133
hunyuan-t1-20250711
Tencent
62.7
805
131K
¥0 / ¥0Input/Output
134
mistral-medium-2505
Mistral
62.4
5.9K
262K
¥2.88 / ¥14.4Input/Output
135
qwen3-235b-a22b
Alibaba
62.1
4.3K
131K
¥2.07 / ¥8.26Input/Output
136
glm-4.7-flash
Zai
61.9
2.7K
200K
¥0 / ¥0Input/Output
137
gpt-oss-120b
Openai
61.6
6.5K
131K
¥1.08 / ¥4.32Input/Output
138
claude-sonnet-4-20250514
Anthropic
61.3
7.4K
200K
¥21.6 / ¥108Input/Output
139
minimax-m2.5
Minimax
61.0
9.3K
205K
¥0 / ¥0Input/Output
140
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
60.7
3.3K
131K
¥0 / ¥0Input/Output
141
o3-mini-high
Openai
60.5
2.6K
200K
¥7.92 / ¥31.7Input/Output
142
kimi-k2-0711-preview
Moonshot
60.2
5.2K
131K
¥4.32 / ¥18Input/Output
143
trinity-large-preview
-
59.9
6.9K
262K
¥1.8 / ¥6.48Input/Output
144
grok-3-mini-high
Xai
59.6
3.3K
128K
¥0 / ¥0Input/Output
145
minimax-m2
Minimax
59.3
1.5K
197K
¥0 / ¥0Input/Output
146
gemini-2.5-flash-lite-preview-06-17-thinking
Google
59.0
6K
65.5K
¥0.72 / ¥2.88Input/Output
147
deepseek-r1
Deepseek
58.8
2.3K
164K
¥5.04 / ¥18Input/Output
148
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
58.5
9.7K
1.05M
¥0.72 / ¥2.88Input/Output
149
deepseek-v3-0324
Deepseek
58.2
8.4K
75K
¥1.44 / ¥5.76Input/Output
150
o4-mini-2025-04-16
Openai
57.9
8.7K
200K
¥7.92 / ¥31.7Input/Output
151
intellect-3
-
57.6
973
131K
¥1.44 / ¥7.92Input/Output
152
gpt-4.1-mini-2025-04-14
Openai
57.3
6.9K
1.05M
¥2.88 / ¥11.5Input/Output
153
o1-2024-12-17
Openai
57.1
4K
128K
¥108 / ¥432Input/Output
154
o1-preview
Openai
56.8
5.1K
128K
¥108 / ¥432Input/Output
155
amazon-nova-experimental-chat-10-09
Amazon
56.5
552
-
-
156
grok-3-mini-beta
Xai
56.2
4.3K
1M
¥9 / ¥18Input/Output
157
ring-flash-2.0
Ant Group
55.9
1.5K
131K
¥1.01 / ¥4.1Input/Output
158
step-3
Stepfun
55.6
1.2K
65.5K
¥1.8 / ¥4.68Input/Output
159
mistral-small-2506
Mistral
55.4
3.4K
262K
¥2.88 / ¥14.4Input/Output
160
o1-mini
Openai
55.1
8.5K
128K
¥7.92 / ¥31.7Input/Output
161
trinity-large-thinking
-
54.8
6.4K
262K
¥1.8 / ¥6.48Input/Output
162
o3-mini
Openai
54.5
9.5K
200K
¥7.92 / ¥31.7Input/Output
163
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
54.2
6.2K
-
-
164
hunyuan-turbos-20250416
Tencent
54.0
1.8K
131K
¥0 / ¥0Input/Output
165
qwen2.5-max
Alibaba
53.7
5.1K
32K
¥11.5 / ¥46Input/Output
166
minimax-m1
Minimax
53.4
6.5K
1M
¥0.95 / ¥9.03Input/Output
167
qwen3-32b
Alibaba
53.1
513
131K
¥2.07 / ¥8.26Input/Output
168
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia
52.8
659
131K
¥2.88 / ¥2.88Input/Output
169
gemini-2.0-flash-001
Google
52.5
7K
1.05M
¥1.08 / ¥4.32Input/Output
170
gpt-5-nano-high
Openai
52.3
1.7K
400K
¥0.36 / ¥2.88Input/Output
171
glm-4.5v
Zai
52.0
991
64K
¥4.32 / ¥13Input/Output
172
olmo-3.1-32b-instruct
Allenai
51.7
2.5K
200K
¥14.4 / ¥57.6Input/Output
173
hunyuan-turbos-20250226
Tencent
51.4
275
131K
¥0 / ¥0Input/Output
174
claude-3-5-sonnet-20241022
Anthropic
51.1
15K
200K
¥21.6 / ¥108Input/Output
175
step-1o-turbo-202506
Stepfun
50.8
1.5K
-
-
176
claude-3-7-sonnet-20250219
Anthropic
50.6
7.1K
200K
¥21.6 / ¥108Input/Output
177
qwen3-30b-a3b
Alibaba
50.3
4.5K
128K
¥0.79 / ¥7.78Input/Output
178
qwq-32b
Alibaba
50.0
4K
131K
¥2.07 / ¥6.2Input/Output
179
command-a-03-2025
Cohere
49.7
10.2K
256K
¥18 / ¥72Input/Output
180
qwen-plus-0125
Alibaba
49.4
893
1M
¥0.83 / ¥2.07Input/Output
181
mercury
Inception Ai
49.2
394
128K
¥1.8 / ¥5.4Input/Output
182
deepseek-v3
Deepseek
48.9
3.3K
128K
¥0 / ¥0Input/Output
183
gemma-3-27b-it
Google
48.6
8.1K
128K
¥2.15 / ¥2.15Input/Output
184
gemini-2.0-flash-lite-preview-02-05
Google
48.3
3.5K
1.05M
¥0.54 / ¥2.16Input/Output
185
olmo-3-32b-think
Allenai
48.0
1.1K
128K
¥2.16 / ¥3.24Input/Output
186
hunyuan-turbo-0110
Tencent
47.7
299
-
-
187
magistral-medium-2506
Mistral
47.5
2.3K
128K
¥14.4 / ¥36Input/Output
188
step-2-16k-exp-202412
Stepfun
47.2
737
16.4K
¥37.5 / ¥118Input/Output
189
qwen2.5-plus-1127
Alibaba
46.9
1.6K
-
-
190
granite-4.1-8b
Ibm
46.6
944
131K
¥0.36 / ¥0.72Input/Output
191
yi-lightning
-
46.3
4.3K
12K
¥1.44 / ¥1.44Input/Output
192
athene-v2-chat
-
46.0
4K
-
-
193
llama-3.1-nemotron-ultra-253b-v1
Nvidia
45.8
367
128K
¥4.32 / ¥13Input/Output
194
mistral-small-3.1-24b-instruct-2503
Mistral
45.5
6.1K
262K
¥2.88 / ¥14.4Input/Output
195
deepseek-v2.5-1210
Deepseek
45.2
1.1K
1M
¥1.01 / ¥2.02Input/Output
196
gpt-oss-20b
Openai
44.9
2.2K
131K
¥0.32 / ¥1.3Input/Output
197
hunyuan-large-2025-02-10
Tencent
44.6
519
-
-
198
claude-3-5-sonnet-20240620
Anthropic
44.4
13.6K
200K
¥21.6 / ¥108Input/Output
199
hunyuan-large-vision
Tencent
44.1
964
-
-
200
gpt-4.1-nano-2025-04-14
Openai
43.8
807
1.05M
¥14.4 / ¥57.6Input/Output
201
llama-4-maverick-17b-128e-instruct
Meta
43.5
7K
1M
¥1.8 / ¥6.26Input/Output
202
deepseek-v2.5
Deepseek
43.2
4.3K
1M
¥1.01 / ¥2.02Input/Output
203
gpt-4o-2024-05-13
Openai
42.9
19.5K
128K
¥36 / ¥108Input/Output
204
llama-3.3-nemotron-49b-super-v1
Nvidia
42.7
286
131K
¥0 / ¥0Input/Output
205
gemini-1.5-pro-002
Google
42.4
9.2K
-
-
206
qwen2.5-72b-instruct
Alibaba
42.1
6.7K
131K
¥4.13 / ¥12.4Input/Output
207
llama-3.1-405b-instruct-bf16
Meta
41.8
6.2K
128K
¥0 / ¥0Input/Output
208
glm-4-plus
Zai
41.5
4.4K
128K
¥54 / ¥54Input/Output
209
gpt-4o-mini-2024-07-18
Openai
41.2
10.9K
128K
¥1.08 / ¥4.32Input/Output
210
qwen-max-0919
Alibaba
41.0
2.8K
131K
¥2.48 / ¥9.91Input/Output
211
olmo-3.1-32b-think
Allenai
40.7
1.6K
200K
¥14.4 / ¥57.6Input/Output
212
grok-2-2024-08-13
Xai
40.4
10.4K
1M
¥9 / ¥18Input/Output
213
glm-4-plus-0111
Zai
40.1
894
128K
¥72 / ¥72Input/Output
214
claude-3-5-haiku-20241022
Anthropic
39.8
11.2K
200K
¥5.76 / ¥28.8Input/Output
215
llama-4-scout-17b-16e-instruct
Meta
39.5
5.3K
128K
¥1.44 / ¥5.62Input/Output
216
llama-3.1-405b-instruct-fp8
Meta
39.3
9.7K
128K
¥0 / ¥0Input/Output
217
gpt-4o-2024-08-06
Openai
39.0
7.3K
128K
¥18 / ¥72Input/Output
218
gemma-3-12b-it
Google
38.7
543
128K
¥1.96 / ¥1.96Input/Output
219
mistral-large-2407
Mistral
38.4
7.6K
131K
¥14.4 / ¥43.2Input/Output
220
qwen2.5-coder-32b-instruct
Alibaba
38.1
873
131K
¥2.07 / ¥6.2Input/Output
221
mistral-large-2411
Mistral
37.9
4.2K
128K
¥14.4 / ¥43.2Input/Output
222
llama-3.1-nemotron-70b-instruct
Nvidia
37.6
1.3K
128K
¥0 / ¥0Input/Output
223
amazon-nova-pro-v1.0
Amazon
37.3
3.9K
300K
¥5.76 / ¥23Input/Output
224
hunyuan-standard-2025-02-10
Tencent
37.0
549
-
-
225
gemma-3n-e4b-it
Google
36.7
3.5K
128K
¥0 / ¥0Input/Output
226
grok-2-mini-2024-08-13
Xai
36.4
8.7K
1M
¥9 / ¥18Input/Output
227
llama-3.3-70b-instruct
Meta
36.2
8.7K
128K
¥0 / ¥0Input/Output
228
gpt-4-turbo-2024-04-09
Openai
35.9
17.1K
128K
¥72 / ¥216Input/Output
229
athene-70b-0725
-
35.6
3.1K
-
-
230
gemini-1.5-pro-001
Google
35.3
12.7K
-
-
231
claude-3-opus-20240229
Anthropic
35.0
33.7K
200K
¥108 / ¥540Input/Output
232
gemini-1.5-flash-002
Google
34.7
5.9K
2M
¥0.54 / ¥2.2Input/Output
233
llama-3.1-70b-instruct
Meta
34.5
9.4K
131K
¥2.88 / ¥2.88Input/Output
234
gemini-advanced-0514
Google
34.2
8.1K
-
-
235
gpt-4-1106-preview
Openai
33.9
15.6K
8.19K
¥216 / ¥432Input/Output
236
deepseek-coder-v2
Deepseek
33.6
2.7K
1M
¥1.01 / ¥2.02Input/Output
237
gpt-4-0125-preview
Openai
33.3
15.3K
8.19K
¥216 / ¥432Input/Output
238
ibm-granite-h-small
Ibm
33.1
1.3K
-
-
239
mistral-small-24b-instruct-2501
Mistral
32.8
2.1K
262K
¥2.88 / ¥14.4Input/Output
240
amazon-nova-lite-v1.0
Amazon
32.5
3.1K
300K
¥0.43 / ¥1.73Input/Output
241
gemini-1.5-flash-001
Google
32.2
10.7K
2M
¥0.54 / ¥2.2Input/Output
242
llama-3.1-tulu-3-70b
Allenai
31.9
450
-
-
243
phi-4
Microsoft
31.6
3.3K
128K
¥0.9 / ¥3.6Input/Output
244
hunyuan-standard-256k
Tencent
31.4
497
-
-
245
gemma-3-4b-it
Google
31.1
605
128K
¥1.44 / ¥1.44Input/Output
246
reka-core-20240904
-
30.8
1.2K
-
-
247
glm-4-0520
Zai
30.5
1.7K
128K
¥108 / ¥108Input/Output
248
jamba-1.5-large
-
30.2
1.4K
256K
¥0 / ¥0Input/Output
249
llama-3.1-nemotron-51b-instruct
Nvidia
29.9
665
128K
¥0 / ¥0Input/Output
250
claude-3-sonnet-20240229
Anthropic
29.7
18.9K
200K
¥21.6 / ¥108Input/Output
251
amazon-nova-micro-v1.0
Amazon
29.4
3K
128K
¥0.25 / ¥1.01Input/Output
252
gemini-1.5-flash-8b-001
Google
29.1
6.1K
2M
¥0.54 / ¥2.2Input/Output
253
gemma-2-27b-it
Google
28.8
12.1K
8.19K
¥0.58 / ¥0.58Input/Output
254
olmo-2-0325-32b-instruct
Allenai
28.5
427
-
-
255
nemotron-4-340b-instruct
Nvidia
28.2
3.3K
-
-
256
gpt-4-0314
Openai
28.0
8.3K
8.19K
¥216 / ¥432Input/Output
257
llama-3-70b-instruct
Meta
27.7
28.1K
8.19K
¥3.67 / ¥5.33Input/Output
258
ministral-8b-2410
Mistral
27.4
838
128K
¥0.72 / ¥0.72Input/Output
259
claude-3-haiku-20240307
Anthropic
27.1
20.9K
200K
¥1.8 / ¥9Input/Output
260
c4ai-aya-expanse-32b
Cohere
26.8
4.7K
-
-
261
qwen2-72b-instruct
Alibaba
26.6
6.2K
131K
¥4.13 / ¥12.4Input/Output
262
llama-3.1-8b-instruct
Meta
26.3
8.6K
131K
¥0.79 / ¥0.79Input/Output
263
gemma-2-9b-it-simpo
-
26.0
1.5K
8.19K
¥1.44 / ¥1.44Input/Output
264
reka-flash-20240904
-
25.7
1.2K
65.5K
¥0.72 / ¥1.44Input/Output
265
gpt-4-0613
Openai
25.4
13.7K
8.19K
¥216 / ¥432Input/Output
266
command-r-plus-08-2024
Cohere
25.1
1.7K
128K
¥18 / ¥72Input/Output
267
granite-3.1-8b-instruct
Ibm
24.9
478
-
-
268
qwen1.5-110b-chat
Alibaba
24.6
4.8K
-
-
269
llama-3.1-tulu-3-8b
Allenai
24.3
476
-
-
270
mistral-large-2402
Mistral
24.0
10.4K
262K
¥2.88 / ¥14.4Input/Output
271
jamba-1.5-mini
-
23.7
1.4K
256K
¥0 / ¥0Input/Output
272
gemma-2-9b-it
Google
23.4
8.9K
8.19K
¥1.44 / ¥1.44Input/Output
273
command-r-plus
Cohere
23.2
13.9K
128K
¥18 / ¥72Input/Output
274
command-r-08-2024
Cohere
22.9
1.8K
128K
¥18 / ¥72Input/Output
275
yi-1.5-34b-chat
-
22.6
3.8K
-
-
276
mixtral-8x22b-instruct-v0.1
Mistral
22.3
8.8K
64K
¥14.4 / ¥43.2Input/Output
277
qwen1.5-72b-chat
Alibaba
22.0
6.4K
-
-
278
reka-flash-21b-20240226-online
-
21.8
2.9K
-
-
279
mistral-medium
Mistral
21.5
5.1K
262K
¥2.88 / ¥14.4Input/Output
280
c4ai-aya-expanse-8b
Cohere
21.2
1.6K
-
-
281
internlm2_5-20b-chat
-
20.9
1.7K
-
-
282
qwq-32b-preview
Alibaba
20.6
566
131K
¥2.07 / ¥6.2Input/Output
283
qwen1.5-32b-chat
Alibaba
20.3
3.9K
-
-
284
reka-flash-21b-20240226
-
20.1
4.7K
-
-
285
llama-3-8b-instruct
Meta
19.8
18.4K
8.19K
¥0.29 / ¥0.29Input/Output
286
granite-3.1-2b-instruct
Ibm
19.5
508
-
-
287
starling-lm-7b-beta
-
19.2
2.9K
200K
¥5.4 / ¥18.7Input/Output
288
qwen1.5-14b-chat
Alibaba
18.9
3.2K
-
-
289
gpt-3.5-turbo-0125
Openai
18.6
11.1K
16.4K
¥3.6 / ¥10.8Input/Output
290
dbrx-instruct-preview
-
18.4
5.5K
-
-
291
phi-3-medium-4k-instruct
Microsoft
18.1
4K
4.1K
¥1.22 / ¥4.9Input/Output
292
zephyr-orpo-141b-A35b-v0.1
-
17.8
831
200K
¥108 / ¥432Input/Output
293
command-r
Cohere
17.5
9.6K
128K
¥18 / ¥72Input/Output
294
mixtral-8x7b-instruct-v0.1
Mistral
17.2
11.8K
32K
¥5.04 / ¥5.04Input/Output
295
tulu-2-dpo-70b
-
16.9
805
-
-
296
gpt-3.5-turbo-1106
Openai
16.7
2.1K
16.4K
¥7.2 / ¥14.4Input/Output
297
openchat-3.5-0106
-
16.4
2K
-
-
298
granite-3.0-8b-instruct
Ibm
16.1
1.1K
-
-
299
gemma-2-2b-it
Google
15.8
7.3K
128K
¥0 / ¥0Input/Output
300
yi-34b-chat
-
15.5
2.3K
-
-
301
gemini-pro
Google
15.3
678
1.05M
¥14.4 / ¥86.4Input/Output
302
qwen1.5-7b-chat
Alibaba
15.0
772
-
-
303
gemini-pro-dev-api
Google
14.7
2.7K
1.05M
¥14.4 / ¥86.4Input/Output
304
phi-3-small-8k-instruct
Microsoft
14.4
3.2K
8.19K
¥1.08 / ¥4.32Input/Output
305
llama-3.2-3b-instruct
Meta
14.1
1.4K
131K
¥0.22 / ¥0.35Input/Output
306
starling-lm-7b-alpha
-
13.8
1.4K
200K
¥5.4 / ¥18.7Input/Output
307
deepseek-llm-67b-chat
Deepseek
13.6
649
1M
¥1.01 / ¥2.02Input/Output
308
phi-3-mini-4k-instruct-june-2024
Microsoft
13.3
1.8K
4.1K
¥0.94 / ¥3.74Input/Output
309
phi-3-mini-4k-instruct
Microsoft
13.0
3.4K
4.1K
¥0.94 / ¥3.74Input/Output
310
granite-3.0-2b-instruct
Ibm
12.7
1.1K
-
-
311
snowflake-arctic-instruct
-
12.4
5.7K
-
-
312
gemma-1.1-7b-it
Google
12.1
4.3K
-
-
313
mistral-7b-instruct-v0.2
Mistral
11.9
3.1K
262K
¥2.88 / ¥14.4Input/Output
314
wizardlm-70b
Microsoft
11.6
988
-
-
315
nous-hermes-2-mixtral-8x7b-dpo
-
11.3
575
1M
¥36 / ¥180Input/Output
316
llama-2-70b-chat
Meta
11.0
5.7K
-
-
317
vicuna-33b
-
10.7
2.9K
-
-
318
openchat-3.5
-
10.5
971
-
-
319
qwen-14b-chat
Alibaba
10.2
599
32.8K
¥1.04 / ¥3.1Input/Output
320
llama-3.2-1b-instruct
Meta
9.9
1.3K
16.4K
¥0.07 / ¥0.08Input/Output
321
solar-10.7b-instruct-v1.0
-
9.6
482
128K
¥0 / ¥0Input/Output
322
openhermes-2.5-mistral-7b
-
9.3
589
1M
¥36 / ¥180Input/Output
323
llama-2-13b-chat
Meta
9.0
2.6K
-
-
324
zephyr-7b-alpha
-
8.8
201
-
-
325
gemma-7b-it
Google
8.5
1.4K
-
-
326
smollm2-1.7b-instruct
-
8.2
352
-
-
327
codellama-34b-instruct
Meta
7.9
853
-
-
328
zephyr-7b-beta
-
7.6
1.3K
-
-
329
vicuna-13b
-
7.3
2.4K
-
-
330
phi-3-mini-128k-instruct
Microsoft
7.1
3.9K
128K
¥0.94 / ¥3.74Input/Output
331
mpt-30b-chat
-
6.8
258
-
-
332
wizardlm-13b
Microsoft
6.5
735
-
-
333
gemma-1.1-2b-it
Google
6.2
2K
-
-
334
llama2-70b-steerlm-chat
Nvidia
5.9
467
-
-
335
mistral-7b-instruct
Mistral
5.6
1K
262K
¥2.88 / ¥14.4Input/Output
336
olmo-7b-instruct
Allenai
5.4
772
-
-
337
vicuna-7b
-
5.1
726
-
-
338
gemma-2b-it
Google
4.8
742
-
-
339
llama-2-7b-chat
Meta
4.5
2K
128K
¥4.03 / ¥48Input/Output
340
stripedhyena-nous-7b
-
4.2
704
-
-
341
qwen1.5-4b-chat
Alibaba
4.0
1.3K
-
-
342
guanaco-33b
-
3.7
263
200K
¥14.4 / ¥57.6Input/Output
343
palm-2
Google
3.4
917
-
-
344
chatglm3-6b
-
3.1
535
200K
¥5.4 / ¥18.7Input/Output
345
koala-13b
-
2.8
747
-
-
346
RWKV-4-Raven-14B
-
2.5
505
-
-
347
chatglm-6b
-
2.3
551
200K
¥5.4 / ¥18.7Input/Output
348
mpt-7b-chat
-
2.0
397
-
-
349
chatglm2-6b
-
1.7
293
200K
¥5.4 / ¥18.7Input/Output
350
oasst-pythia-12b
-
1.4
714
-
-
351
stablelm-tuned-alpha-7b
-
1.1
363
-
-
352
alpaca-13b
-
0.8
626
-
-
353
dolly-v2-12b
-
0.6
396
-
-
354
fastchat-t5-3b
-
0.3
428
-
-
355
llama-13b
Meta
0.0
304
-
-
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 8.3K 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

代码能力排行榜看什么指标?

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。

代码能力模型应该怎么选?

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。