Chat · Text · Russian Leaderboard

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

Selection guide

Russian model ranking guide

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

gemini-3.5-flashclaude-opus-4-6gemini-3.1-pro-previewgemini-3-proclaude-opus-4-6-thinking
Current DirectoryChat · Text · Russian
Models323
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / RussianPublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
gemini-3.5-flash
Google
100.0
903
1.05M
¥10.8 / ¥64.8Input/Output
2
claude-opus-4-6
Anthropic
99.7
4K
1M
¥36 / ¥180Input/Output
3
gemini-3.1-pro-preview
Google
99.4
4.7K
1.05M
¥14.4 / ¥86.4Input/Output
4
gemini-3-pro
Google
99.1
4K
1.05M
¥14.4 / ¥86.4Input/Output
5
claude-opus-4-6-thinking
Anthropic
98.8
3.7K
1M
¥36 / ¥180Input/Output
6
claude-opus-4-7-thinking
Anthropic
98.4
2K
1M
¥36 / ¥180Input/Output
7
gpt-5.4-high
Openai
98.1
3.2K
1.05M
¥18 / ¥108Input/Output
8
claude-opus-4-7
Anthropic
97.8
2.2K
1M
¥36 / ¥180Input/Output
9
qwen3.7-max-preview
Alibaba
97.5
381
1M
¥18 / ¥54Input/Output
10
gemini-3-flash
Google
97.2
3.3K
1.05M
¥3.6 / ¥21.6Input/Output
11
gpt-5.5-high
Openai
96.9
1.8K
1.05M
¥36 / ¥216Input/Output
12
qwen3.5-max-preview
Alibaba
96.6
2.1K
-
-
13
gpt-5.5
Openai
96.3
1.7K
1.05M
¥36 / ¥216Input/Output
14
muse-spark
Meta
96.0
1.3K
-
-
15
grok-4.20-beta-0309-reasoning
Xai
95.7
3.2K
2M
¥14.4 / ¥43.2Input/Output
16
ernie-5.1
Baidu
95.3
1.6K
119K
¥5.4 / ¥21.6Input/Output
17
gpt-5.4
Openai
95.0
3.3K
1.05M
¥18 / ¥108Input/Output
18
gemma-4-31b
Google
94.7
646
262K
¥3.24 / ¥7.2Input/Output
19
gemini-2.5-pro
Google
94.4
9.8K
1.05M
¥9 / ¥72Input/Output
20
glm-5.1
Zai
94.1
1.6K
200K
¥0 / ¥0Input/Output
21
grok-4.20-multi-agent-beta-0309
Xai
93.8
3.2K
2M
¥14.4 / ¥43.2Input/Output
22
gemini-3-flash (thinking-minimal)
Google
93.5
5.8K
1.05M
¥3.6 / ¥21.6Input/Output
23
mimo-v2.5-pro
Xiaomi
93.2
1.8K
1.05M
¥7.2 / ¥21.6Input/Output
24
dola-seed-2.0-pro
Bytedance
92.9
4.2K
-
-
25
grok-4.20-beta1
Xai
92.5
2.6K
2M
¥14.4 / ¥43.2Input/Output
26
claude-opus-4-5-20251101
Anthropic
92.2
7K
200K
¥36 / ¥180Input/Output
27
ernie-5.0-0110
Baidu
91.9
3.8K
128K
¥7.92 / ¥14.4Input/Output
28
deepseek-v4-pro-thinking
Deepseek
91.6
1.8K
1M
¥3.13 / ¥6.26Input/Output
29
qwen3.6-max-preview
Alibaba
91.3
472
246K
¥9.5 / ¥56.9Input/Output
30
kimi-k2.6
Moonshot
91.0
1.8K
262K
¥6.84 / ¥28.8Input/Output
31
gemma-4-26b-a4b
Google
90.7
679
262K
¥0.94 / ¥2.88Input/Output
32
deepseek-v4-pro
Deepseek
90.4
1.9K
1M
¥3.13 / ¥6.26Input/Output
33
gpt-5.2-chat-latest-20260210
Openai
90.1
3.5K
400K
¥12.6 / ¥101Input/Output
34
ernie-5.0-preview-1203
Baidu
89.8
956
128K
¥7.92 / ¥14.4Input/Output
35
gpt-5.1-high
Openai
89.4
4.1K
400K
¥9 / ¥72Input/Output
36
glm-5
Zai
89.1
2.3K
205K
¥7.2 / ¥23Input/Output
37
claude-opus-4-5-20251101-thinking-32k
Anthropic
88.8
3.9K
200K
¥108 / ¥540Input/Output
38
claude-sonnet-4-6
Anthropic
88.5
3K
1M
¥21.6 / ¥108Input/Output
39
deepseek-v3.1-terminus-thinking
Deepseek
88.2
236
128K
¥1.8 / ¥5.04Input/Output
40
claude-sonnet-4-5-20250929
Anthropic
87.9
7.3K
200K
¥21.6 / ¥108Input/Output
41
grok-4.1-thinking
Xai
87.6
6.5K
200K
¥14.4 / ¥72Input/Output
42
qwen3.5-397b-a17b
Alibaba
87.3
3.4K
262K
¥3.1 / ¥18.6Input/Output
43
qwen3.6-plus
Alibaba
87.0
2K
1M
¥3.6 / ¥21.6Input/Output
44
kimi-k2.5-thinking
Moonshot
86.6
4.2K
262K
¥4.32 / ¥21.6Input/Output
45
gpt-5.5-instant
Openai
86.3
2.7K
400K
¥9 / ¥72Input/Output
46
chatgpt-4o-latest-20250326
Openai
86.0
6.4K
128K
¥18 / ¥72Input/Output
47
grok-4.1
Xai
85.7
6.3K
200K
¥14.4 / ¥72Input/Output
48
glm-4.7
Zai
85.4
1.4K
205K
¥0 / ¥0Input/Output
49
mimo-v2-pro
Xiaomi
85.1
2.6K
1.05M
¥7.2 / ¥21.6Input/Output
50
deepseek-v4-flash-thinking
Deepseek
84.8
1.9K
1M
¥1.01 / ¥2.02Input/Output
51
deepseek-v3.1-terminus
Deepseek
84.5
261
128K
¥1.8 / ¥5.04Input/Output
52
gpt-5.1
Openai
84.2
4.3K
400K
¥9 / ¥72Input/Output
53
deepseek-v4-flash
Deepseek
83.9
1.9K
1M
¥1.01 / ¥2.02Input/Output
54
deepseek-r1-0528
Deepseek
83.5
1.3K
164K
¥3.6 / ¥15.5Input/Output
55
grok-4.3
Xai
83.2
1.7K
1M
¥9 / ¥18Input/Output
56
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
82.9
7.4K
200K
¥21.6 / ¥108Input/Output
57
deepseek-v3.2
Deepseek
82.6
4.8K
128K
¥2.09 / ¥3.1Input/Output
58
amazon-nova-experimental-chat-26-02-10
Amazon
82.3
379
-
-
59
claude-opus-4-1-20250805
Anthropic
82.0
5.7K
200K
¥108 / ¥540Input/Output
60
gpt-5.4-mini-high
Openai
81.7
2.8K
400K
¥5.4 / ¥32.4Input/Output
61
qwen3-max-preview
Alibaba
81.4
1.4K
262K
¥6.2 / ¥24.8Input/Output
62
gpt-5.2
Openai
81.1
5K
400K
¥12.6 / ¥101Input/Output
63
glm-4.6
Zai
80.7
2.8K
205K
¥4.32 / ¥15.8Input/Output
64
qwen3-max-2025-09-23
Alibaba
80.4
573
258K
¥6.19 / ¥24.7Input/Output
65
gpt-4.5-preview-2025-02-27
Openai
80.1
1.4K
8.19K
¥216 / ¥432Input/Output
66
gemini-2.5-flash
Google
79.8
10K
1.05M
¥2.16 / ¥18Input/Output
67
gemini-3.1-flash-lite-preview
Google
79.5
3.9K
1.05M
¥1.8 / ¥10.8Input/Output
68
grok-3-preview-02-24
Xai
79.2
2.5K
1M
¥9 / ¥18Input/Output
69
glm-4.5
Zai
78.9
1.3K
131K
¥4.32 / ¥15.8Input/Output
70
mistral-medium-2508
Mistral
78.6
7.7K
262K
¥2.88 / ¥14.4Input/Output
71
grok-4-0709
Xai
78.3
2.2K
256K
¥21.6 / ¥108Input/Output
72
claude-opus-4-1-20250805-thinking-16k
Anthropic
78.0
3.3K
200K
¥108 / ¥540Input/Output
73
qwen3-235b-a22b-instruct-2507
Alibaba
77.6
8.3K
128K
¥2.09 / ¥8.23Input/Output
74
gpt-5.2-high
Openai
77.3
5.2K
400K
¥12.6 / ¥101Input/Output
75
mimo-v2-omni
Xiaomi
77.0
360
262K
¥2.88 / ¥14.4Input/Output
76
mistral-large-3
Mistral
76.7
4.3K
262K
¥3.6 / ¥10.8Input/Output
77
amazon-nova-experimental-chat-12-10
Amazon
76.4
382
-
-
78
o3-2025-04-16
Openai
76.1
3.8K
200K
¥14.4 / ¥57.6Input/Output
79
hunyuan-hy3-preview
Tencent
75.8
562
256K
¥0 / ¥0Input/Output
80
deepseek-v3.2-exp
Deepseek
75.5
845
128K
¥0 / ¥0Input/Output
81
kimi-k2.5-instant
Moonshot
75.2
865
262K
¥4.32 / ¥21.6Input/Output
82
deepseek-v3.2-exp-thinking
Deepseek
74.8
503
128K
¥0 / ¥0Input/Output
83
gpt-5-chat
Openai
74.5
1.6K
400K
¥9 / ¥72Input/Output
84
qwen3-vl-235b-a22b-instruct
Alibaba
74.2
717
128K
¥2.16 / ¥8.64Input/Output
85
deepseek-v3.1-thinking
Deepseek
73.9
604
128K
¥1.44 / ¥5.04Input/Output
86
deepseek-v3.1
Deepseek
73.6
790
128K
¥1.44 / ¥5.04Input/Output
87
deepseek-v3.2-thinking
Deepseek
73.3
4.4K
128K
¥2.09 / ¥3.1Input/Output
88
qwen3-next-80b-a3b-instruct
Alibaba
73.0
1.2K
131K
¥1.04 / ¥4.13Input/Output
89
gpt-5-high
Openai
72.7
1.7K
400K
¥9 / ¥72Input/Output
90
gpt-5.3-chat-latest
Openai
72.4
3.3K
128K
¥12.6 / ¥101Input/Output
91
ernie-5.0-preview-1022
Baidu
72.0
259
128K
¥7.92 / ¥14.4Input/Output
92
qwen3-235b-a22b-thinking-2507
Alibaba
71.7
438
131K
¥2.07 / ¥8.26Input/Output
93
gemini-2.5-flash-preview-09-2025
Google
71.4
2.3K
1M
¥2.16 / ¥18Input/Output
94
amazon-nova-experimental-chat-11-10
Amazon
71.1
2.7K
-
-
95
mimo-v2.5
Xiaomi
70.8
1.8K
1.05M
¥2.88 / ¥14.4Input/Output
96
amazon-nova-experimental-chat-26-01-10
Amazon
70.5
342
-
-
97
qwen3.5-122b-a10b
Alibaba
70.2
2.8K
262K
¥2.88 / ¥23Input/Output
98
qwen3-235b-a22b-no-thinking
Alibaba
69.9
2.4K
131K
¥2.07 / ¥8.26Input/Output
99
grok-4-fast-reasoning
Xai
69.6
1K
2M
¥1.44 / ¥3.6Input/Output
100
kimi-k2-thinking-turbo
Moonshot
69.3
6.1K
262K
¥17.3 / ¥72Input/Output
101
claude-opus-4-20250514-thinking-16k
Anthropic
68.9
2.1K
200K
¥108 / ¥540Input/Output
102
qwen3.5-27b
Alibaba
68.6
2.7K
262K
¥2.16 / ¥17.3Input/Output
103
mimo-v2-flash (non-thinking)
Xiaomi
68.3
5K
262K
¥0.72 / ¥2.16Input/Output
104
longcat-flash-chat
Meituan
68.0
692
128K
¥1.08 / ¥10.8Input/Output
105
minimax-m2.1-preview
Minimax
67.7
1.9K
205K
¥0 / ¥0Input/Output
106
hunyuan-t1-20250711
Tencent
67.4
259
131K
¥0 / ¥0Input/Output
107
step-3.5-flash
Stepfun
67.1
4K
256K
¥0.69 / ¥2.07Input/Output
108
longcat-flash-chat-2602-exp
Meituan
66.8
2.5K
128K
¥1.08 / ¥10.8Input/Output
109
qwen3.5-flash
Alibaba
66.5
3.4K
1M
¥1.24 / ¥12.4Input/Output
110
grok-4-fast-chat
Xai
66.1
408
2M
¥1.44 / ¥3.6Input/Output
111
claude-opus-4-20250514
Anthropic
65.8
2.8K
200K
¥108 / ¥540Input/Output
112
grok-4-1-fast-reasoning
Xai
65.5
5.7K
2M
¥1.44 / ¥3.6Input/Output
113
qwen3.5-35b-a3b
Alibaba
65.2
2.9K
262K
¥1.8 / ¥14.4Input/Output
114
gpt-4.1-2025-04-14
Openai
64.9
3.1K
1.05M
¥14.4 / ¥57.6Input/Output
115
minimax-m2.7
Minimax
64.6
2.7K
205K
¥0 / ¥0Input/Output
116
kimi-k2-0905-preview
Moonshot
64.3
700
262K
¥4.32 / ¥18Input/Output
117
claude-haiku-4-5-20251001
Anthropic
64.0
7.3K
200K
¥7.2 / ¥36Input/Output
118
deepseek-v3-0324
Deepseek
63.7
3.1K
75K
¥1.44 / ¥5.76Input/Output
119
mimo-v2-flash (thinking)
Xiaomi
63.4
1.3K
262K
¥0.72 / ¥2.16Input/Output
120
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
63.0
3.8K
1.05M
¥0.72 / ¥2.88Input/Output
121
hunyuan-turbos-20250416
Tencent
62.7
919
131K
¥0 / ¥0Input/Output
122
glm-4.5-air
Zai
62.4
1.5K
131K
¥0 / ¥0Input/Output
123
amazon-nova-experimental-chat-10-20
Amazon
62.1
916
-
-
124
gemini-2.5-flash-lite-preview-06-17-thinking
Google
61.8
1.8K
65.5K
¥0.72 / ¥2.88Input/Output
125
gpt-5.4-nano-high
Openai
61.5
2.7K
400K
¥1.44 / ¥9Input/Output
126
qwen3-30b-a3b-instruct-2507
Alibaba
61.2
1.2K
262K
¥2.16 / ¥3.6Input/Output
127
qwen3-coder-480b-a35b-instruct
Alibaba
60.9
1.4K
262K
¥6.2 / ¥24.8Input/Output
128
qwen3-vl-235b-a22b-thinking
Alibaba
60.6
480
131K
¥2.06 / ¥8.26Input/Output
129
gpt-5-mini-high
Openai
60.2
1.4K
400K
¥1.8 / ¥14.4Input/Output
130
mistral-medium-2505
Mistral
59.9
2.4K
262K
¥2.88 / ¥14.4Input/Output
131
claude-sonnet-4-20250514-thinking-32k
Anthropic
59.6
1.9K
200K
¥21.6 / ¥108Input/Output
132
o1-2024-12-17
Openai
59.3
3.1K
128K
¥108 / ¥432Input/Output
133
grok-3-mini-high
Xai
59.0
991
128K
¥0 / ¥0Input/Output
134
minimax-m2.5
Minimax
58.7
3.9K
205K
¥0 / ¥0Input/Output
135
deepseek-r1
Deepseek
58.4
1.9K
164K
¥5.04 / ¥18Input/Output
136
gemini-2.0-flash-001
Google
58.1
3.5K
1.05M
¥1.08 / ¥4.32Input/Output
137
kimi-k2-0711-preview
Moonshot
57.8
1.5K
131K
¥4.32 / ¥18Input/Output
138
grok-3-mini-beta
Xai
57.5
1.4K
1M
¥9 / ¥18Input/Output
139
qwen2.5-max
Alibaba
57.1
2.8K
32K
¥11.5 / ¥46Input/Output
140
gemma-3-27b-it
Google
56.8
3K
128K
¥2.15 / ¥2.15Input/Output
141
claude-sonnet-4-20250514
Anthropic
56.5
2.6K
200K
¥21.6 / ¥108Input/Output
142
glm-4.6v
Zai
56.2
285
128K
¥2.16 / ¥6.48Input/Output
143
trinity-large-thinking
-
55.9
2.5K
262K
¥1.8 / ¥6.48Input/Output
144
nova-2-lite
Amazon
55.6
1.2K
128K
¥2.38 / ¥19.8Input/Output
145
nvidia-nemotron-3-super-120b-a12b
Nvidia
55.3
806
262K
¥1.44 / ¥5.76Input/Output
146
qwen3-235b-a22b
Alibaba
55.0
1.9K
131K
¥2.07 / ¥8.26Input/Output
147
gpt-oss-120b
Openai
54.7
1.6K
131K
¥1.08 / ¥4.32Input/Output
148
qwen3-next-80b-a3b-thinking
Alibaba
54.3
750
131K
¥1.04 / ¥10.3Input/Output
149
glm-4.7-flash
Zai
54.0
1.4K
200K
¥0 / ¥0Input/Output
150
intellect-3
-
53.7
449
131K
¥1.44 / ¥7.92Input/Output
151
gemma-3-12b-it
Google
53.4
285
128K
¥1.96 / ¥1.96Input/Output
152
o4-mini-2025-04-16
Openai
53.1
2.9K
200K
¥7.92 / ¥31.7Input/Output
153
minimax-m2
Minimax
52.8
324
197K
¥0 / ¥0Input/Output
154
mistral-small-2506
Mistral
52.5
985
262K
¥2.88 / ¥14.4Input/Output
155
gemini-2.0-flash-lite-preview-02-05
Google
52.2
2.3K
1.05M
¥0.54 / ¥2.16Input/Output
156
step-1o-turbo-202506
Stepfun
51.9
544
-
-
157
minimax-m1
Minimax
51.6
1.9K
1M
¥0.95 / ¥9.03Input/Output
158
step-3
Stepfun
51.2
405
65.5K
¥1.8 / ¥4.68Input/Output
159
deepseek-v3
Deepseek
50.9
2.5K
128K
¥0 / ¥0Input/Output
160
step-2-16k-exp-202412
Stepfun
50.6
642
16.4K
¥37.5 / ¥118Input/Output
161
trinity-large-preview
-
50.3
3.1K
262K
¥1.8 / ¥6.48Input/Output
162
qwen-plus-0125
Alibaba
50.0
578
1M
¥0.83 / ¥2.07Input/Output
163
gemini-1.5-pro-002
Google
49.7
7.7K
-
-
164
gpt-4.1-mini-2025-04-14
Openai
49.4
2.6K
1.05M
¥2.88 / ¥11.5Input/Output
165
command-a-03-2025
Cohere
49.1
3.7K
256K
¥18 / ¥72Input/Output
166
o1-preview
Openai
48.8
4.5K
128K
¥108 / ¥432Input/Output
167
hunyuan-turbos-20250226
Tencent
48.4
217
131K
¥0 / ¥0Input/Output
168
glm-4-plus-0111
Zai
48.1
653
128K
¥72 / ¥72Input/Output
169
qwen3-32b
Alibaba
47.8
412
131K
¥2.07 / ¥8.26Input/Output
170
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
47.5
3K
-
-
171
claude-3-7-sonnet-20250219
Anthropic
47.2
3.2K
200K
¥21.6 / ¥108Input/Output
172
ling-flash-2.0
Ant Group
46.9
375
131K
¥1.01 / ¥4.1Input/Output
173
hunyuan-turbo-0110
Tencent
46.6
266
-
-
174
claude-3-5-sonnet-20241022
Anthropic
46.3
9.9K
200K
¥21.6 / ¥108Input/Output
175
o3-mini-high
Openai
46.0
1.7K
200K
¥7.92 / ¥31.7Input/Output
176
mercury-2
Inception Ai
45.7
360
128K
¥1.8 / ¥5.4Input/Output
177
o3-mini
Openai
45.3
4.4K
200K
¥7.92 / ¥31.7Input/Output
178
gemma-3n-e4b-it
Google
45.0
1.4K
128K
¥0 / ¥0Input/Output
179
gpt-5-nano-high
Openai
44.7
483
400K
¥0.36 / ¥2.88Input/Output
180
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
44.4
1.7K
131K
¥0 / ¥0Input/Output
181
glm-4.5v
Zai
44.1
318
64K
¥4.32 / ¥13Input/Output
182
gemma-3-4b-it
Google
43.8
307
128K
¥1.44 / ¥1.44Input/Output
183
qwq-32b
Alibaba
43.5
1.9K
131K
¥2.07 / ¥6.2Input/Output
184
qwen3-30b-a3b
Alibaba
43.2
1.9K
128K
¥0.79 / ¥7.78Input/Output
185
deepseek-v2.5-1210
Deepseek
42.9
1K
1M
¥1.01 / ¥2.02Input/Output
186
gemini-1.5-flash-002
Google
42.5
5.1K
2M
¥0.54 / ¥2.2Input/Output
187
llama-4-maverick-17b-128e-instruct
Meta
42.2
2.7K
1M
¥1.8 / ¥6.26Input/Output
188
grok-2-2024-08-13
Xai
41.9
8.7K
1M
¥9 / ¥18Input/Output
189
gpt-4o-2024-05-13
Openai
41.6
13.9K
128K
¥36 / ¥108Input/Output
190
llama-3.1-nemotron-ultra-253b-v1
Nvidia
41.3
303
128K
¥4.32 / ¥13Input/Output
191
o1-mini
Openai
41.0
7.4K
128K
¥7.92 / ¥31.7Input/Output
192
gemini-advanced-0514
Google
40.7
5.9K
-
-
193
claude-3-5-sonnet-20240620
Anthropic
40.4
10K
200K
¥21.6 / ¥108Input/Output
194
athene-v2-chat
-
40.1
3.4K
-
-
195
claude-3-opus-20240229
Anthropic
39.8
21.1K
200K
¥108 / ¥540Input/Output
196
gemini-1.5-pro-001
Google
39.4
9.4K
-
-
197
olmo-3.1-32b-instruct
Allenai
39.1
1.4K
200K
¥14.4 / ¥57.6Input/Output
198
gpt-4o-mini-2024-07-18
Openai
38.8
8.3K
128K
¥1.08 / ¥4.32Input/Output
199
glm-4-plus
Zai
38.5
3.9K
128K
¥54 / ¥54Input/Output
200
qwen-max-0919
Alibaba
38.2
2.4K
131K
¥2.48 / ¥9.91Input/Output
201
gpt-4o-2024-08-06
Openai
37.9
5.5K
128K
¥18 / ¥72Input/Output
202
qwen2.5-plus-1127
Alibaba
37.6
1.4K
-
-
203
llama-3.3-nemotron-49b-super-v1
Nvidia
37.3
263
131K
¥0 / ¥0Input/Output
204
gpt-oss-20b
Openai
37.0
607
131K
¥0.32 / ¥1.3Input/Output
205
hunyuan-large-2025-02-10
Tencent
36.6
374
-
-
206
llama-4-scout-17b-16e-instruct
Meta
36.3
1.9K
128K
¥1.44 / ¥5.62Input/Output
207
llama-3.1-405b-instruct-fp8
Meta
36.0
7.7K
128K
¥0 / ¥0Input/Output
208
mistral-small-3.1-24b-instruct-2503
Mistral
35.7
2K
262K
¥2.88 / ¥14.4Input/Output
209
qwen2.5-72b-instruct
Alibaba
35.4
5.8K
131K
¥4.13 / ¥12.4Input/Output
210
gpt-4.1-nano-2025-04-14
Openai
35.1
702
1.05M
¥14.4 / ¥57.6Input/Output
211
grok-2-mini-2024-08-13
Xai
34.8
7.2K
1M
¥9 / ¥18Input/Output
212
gpt-4-turbo-2024-04-09
Openai
34.5
9.9K
128K
¥72 / ¥216Input/Output
213
hunyuan-standard-2025-02-10
Tencent
34.2
379
-
-
214
mistral-large-2407
Mistral
33.9
5.7K
131K
¥14.4 / ¥43.2Input/Output
215
olmo-3-32b-think
Allenai
33.5
500
128K
¥2.16 / ¥3.24Input/Output
216
llama-3.1-405b-instruct-bf16
Meta
33.2
4.9K
128K
¥0 / ¥0Input/Output
217
yi-lightning
-
32.9
4.2K
12K
¥1.44 / ¥1.44Input/Output
218
claude-3-5-haiku-20241022
Anthropic
32.6
6.2K
200K
¥5.76 / ¥28.8Input/Output
219
deepseek-v2.5
Deepseek
32.3
3.5K
1M
¥1.01 / ¥2.02Input/Output
220
mistral-large-2411
Mistral
32.0
3.3K
128K
¥14.4 / ¥43.2Input/Output
221
gpt-4-1106-preview
Openai
31.7
7.1K
8.19K
¥216 / ¥432Input/Output
222
llama-3.3-70b-instruct
Meta
31.4
5.4K
128K
¥0 / ¥0Input/Output
223
granite-4.1-8b
Ibm
31.1
400
131K
¥0.36 / ¥0.72Input/Output
224
athene-70b-0725
-
30.7
1.9K
-
-
225
reka-core-20240904
-
30.4
976
-
-
226
llama-3.1-tulu-3-70b
Allenai
30.1
366
-
-
227
hunyuan-large-vision
Tencent
29.8
358
-
-
228
gpt-4-0125-preview
Openai
29.5
8.4K
8.19K
¥216 / ¥432Input/Output
229
amazon-nova-pro-v1.0
Amazon
29.2
3K
300K
¥5.76 / ¥23Input/Output
230
gemini-1.5-flash-001
Google
28.9
7.5K
2M
¥0.54 / ¥2.2Input/Output
231
gemini-1.5-flash-8b-001
Google
28.6
5.3K
2M
¥0.54 / ¥2.2Input/Output
232
gemma-2-27b-it
Google
28.3
9.7K
8.19K
¥0.58 / ¥0.58Input/Output
233
llama-3.1-70b-instruct
Meta
28.0
7.3K
131K
¥2.88 / ¥2.88Input/Output
234
qwen2.5-coder-32b-instruct
Alibaba
27.6
822
131K
¥2.07 / ¥6.2Input/Output
235
command-r-plus-08-2024
Cohere
27.3
1.4K
128K
¥18 / ¥72Input/Output
236
magistral-medium-2506
Mistral
27.0
764
128K
¥14.4 / ¥36Input/Output
237
c4ai-aya-expanse-32b
Cohere
26.7
3.9K
-
-
238
llama-3.1-nemotron-70b-instruct
Nvidia
26.4
1.1K
128K
¥0 / ¥0Input/Output
239
claude-3-sonnet-20240229
Anthropic
26.1
10.8K
200K
¥21.6 / ¥108Input/Output
240
gemma-2-9b-it-simpo
-
25.8
1.1K
8.19K
¥1.44 / ¥1.44Input/Output
241
ring-flash-2.0
Ant Group
25.5
381
131K
¥1.01 / ¥4.1Input/Output
242
nemotron-4-340b-instruct
Nvidia
25.2
2.5K
-
-
243
mistral-small-24b-instruct-2501
Mistral
24.8
1.4K
262K
¥2.88 / ¥14.4Input/Output
244
amazon-nova-lite-v1.0
Amazon
24.5
2.5K
300K
¥0.43 / ¥1.73Input/Output
245
glm-4-0520
Zai
24.2
1.3K
128K
¥108 / ¥108Input/Output
246
reka-flash-20240904
-
23.9
1K
65.5K
¥0.72 / ¥1.44Input/Output
247
phi-4
Microsoft
23.6
2.6K
128K
¥0.9 / ¥3.6Input/Output
248
command-r-plus
Cohere
23.3
7.8K
128K
¥18 / ¥72Input/Output
249
claude-3-haiku-20240307
Anthropic
23.0
12K
200K
¥1.8 / ¥9Input/Output
250
gemma-2-9b-it
Google
22.7
6.7K
8.19K
¥1.44 / ¥1.44Input/Output
251
c4ai-aya-expanse-8b
Cohere
22.4
1.5K
-
-
252
jamba-1.5-large
-
22.0
998
256K
¥0 / ¥0Input/Output
253
gpt-4-0314
Openai
21.7
3.6K
8.19K
¥216 / ¥432Input/Output
254
ministral-8b-2410
Mistral
21.4
760
128K
¥0.72 / ¥0.72Input/Output
255
llama-3.1-tulu-3-8b
Allenai
21.1
418
-
-
256
olmo-3.1-32b-think
Allenai
20.8
904
200K
¥14.4 / ¥57.6Input/Output
257
deepseek-coder-v2
Deepseek
20.5
1.8K
1M
¥1.01 / ¥2.02Input/Output
258
olmo-2-0325-32b-instruct
Allenai
20.2
304
-
-
259
llama-3.1-nemotron-51b-instruct
Nvidia
19.9
605
128K
¥0 / ¥0Input/Output
260
gemini-pro-dev-api
Google
19.6
953
1.05M
¥14.4 / ¥86.4Input/Output
261
amazon-nova-micro-v1.0
Amazon
19.3
2.5K
128K
¥0.25 / ¥1.01Input/Output
262
ibm-granite-h-small
Ibm
18.9
323
-
-
263
mistral-large-2402
Mistral
18.6
5.5K
262K
¥2.88 / ¥14.4Input/Output
264
command-r-08-2024
Cohere
18.3
1.4K
128K
¥18 / ¥72Input/Output
265
gpt-4-0613
Openai
18.0
6K
8.19K
¥216 / ¥432Input/Output
266
qwen2-72b-instruct
Alibaba
17.7
4.6K
131K
¥4.13 / ¥12.4Input/Output
267
mistral-medium
Mistral
17.4
1.8K
262K
¥2.88 / ¥14.4Input/Output
268
reka-flash-21b-20240226-online
-
17.1
1.3K
-
-
269
reka-flash-21b-20240226
-
16.8
2.3K
-
-
270
llama-3-70b-instruct
Meta
16.5
15K
8.19K
¥3.67 / ¥5.33Input/Output
271
hunyuan-standard-256k
Tencent
16.1
444
-
-
272
llama-3.1-8b-instruct
Meta
15.8
6.6K
131K
¥0.79 / ¥0.79Input/Output
273
mixtral-8x22b-instruct-v0.1
Mistral
15.5
4.9K
64K
¥14.4 / ¥43.2Input/Output
274
command-r
Cohere
15.2
5.3K
128K
¥18 / ¥72Input/Output
275
jamba-1.5-mini
-
14.9
998
256K
¥0 / ¥0Input/Output
276
wizardlm-70b
Microsoft
14.6
172
-
-
277
phi-3-medium-4k-instruct
Microsoft
14.3
3K
4.1K
¥1.22 / ¥4.9Input/Output
278
gpt-3.5-turbo-0125
Openai
14.0
5.4K
16.4K
¥3.6 / ¥10.8Input/Output
279
qwen1.5-110b-chat
Alibaba
13.7
2.9K
-
-
280
gemma-2-2b-it
Google
13.4
6K
128K
¥0 / ¥0Input/Output
281
zephyr-orpo-141b-A35b-v0.1
-
13.0
407
200K
¥108 / ¥432Input/Output
282
qwq-32b-preview
Alibaba
12.7
527
131K
¥2.07 / ¥6.2Input/Output
283
phi-3-small-8k-instruct
Microsoft
12.4
2.2K
8.19K
¥1.08 / ¥4.32Input/Output
284
llama-3-8b-instruct
Meta
12.1
10K
8.19K
¥0.29 / ¥0.29Input/Output
285
internlm2_5-20b-chat
-
11.8
1.4K
-
-
286
openchat-3.5
-
11.5
187
-
-
287
qwen1.5-72b-chat
Alibaba
11.2
2.7K
-
-
288
snowflake-arctic-instruct
-
10.9
2.8K
-
-
289
starling-lm-7b-beta
-
10.6
1.4K
200K
¥5.4 / ¥18.7Input/Output
290
starling-lm-7b-alpha
-
10.2
410
200K
¥5.4 / ¥18.7Input/Output
291
granite-3.1-8b-instruct
Ibm
9.9
467
-
-
292
yi-1.5-34b-chat
-
9.6
3.2K
-
-
293
mixtral-8x7b-instruct-v0.1
Mistral
9.3
5.2K
32K
¥5.04 / ¥5.04Input/Output
294
openchat-3.5-0106
-
9.0
790
-
-
295
llama-2-70b-chat
Meta
8.7
2K
-
-
296
vicuna-33b
-
8.4
703
-
-
297
dbrx-instruct-preview
-
8.1
3K
-
-
298
gpt-3.5-turbo-1106
Openai
7.8
400
16.4K
¥7.2 / ¥14.4Input/Output
299
qwen1.5-32b-chat
Alibaba
7.5
2.2K
-
-
300
granite-3.1-2b-instruct
Ibm
7.1
464
-
-
301
zephyr-7b-beta
-
6.8
202
-
-
302
granite-3.0-8b-instruct
Ibm
6.5
954
-
-
303
llama-2-13b-chat
Meta
6.2
783
-
-
304
yi-34b-chat
-
5.9
789
-
-
305
gemma-1.1-7b-it
Google
5.6
2.7K
-
-
306
qwen1.5-14b-chat
Alibaba
5.3
1.7K
-
-
307
granite-3.0-2b-instruct
Ibm
5.0
1.1K
-
-
308
vicuna-13b
-
4.7
448
-
-
309
phi-3-mini-4k-instruct
Microsoft
4.3
2.8K
4.1K
¥0.94 / ¥3.74Input/Output
310
phi-3-mini-4k-instruct-june-2024
Microsoft
4.0
1.4K
4.1K
¥0.94 / ¥3.74Input/Output
311
mistral-7b-instruct-v0.2
Mistral
3.7
1.2K
262K
¥2.88 / ¥14.4Input/Output
312
qwen1.5-7b-chat
Alibaba
3.4
296
-
-
313
phi-3-mini-128k-instruct
Microsoft
3.1
1.8K
128K
¥0.94 / ¥3.74Input/Output
314
mistral-7b-instruct
Mistral
2.8
175
262K
¥2.88 / ¥14.4Input/Output
315
llama-2-7b-chat
Meta
2.5
580
128K
¥4.03 / ¥48Input/Output
316
gemma-7b-it
Google
2.2
629
-
-
317
gemma-1.1-2b-it
Google
1.9
1.2K
-
-
318
smollm2-1.7b-instruct
-
1.6
410
-
-
319
qwen1.5-4b-chat
Alibaba
1.2
564
-
-
320
llama-3.2-3b-instruct
Meta
0.9
933
131K
¥0.22 / ¥0.35Input/Output
321
olmo-7b-instruct
Allenai
0.6
497
-
-
322
llama-3.2-1b-instruct
Meta
0.3
953
16.4K
¥0.07 / ¥0.08Input/Output
323
gemma-2b-it
Google
0.0
300
-
-
Top model analysis

gemini-3.5-flash why it ranks first

gemini-3.5-flash ranks first with a percent score of 100.0 and 903 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

俄语排行榜看什么指标?

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。

俄语模型应该怎么选?

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。