Chat · Text · Japanese Leaderboard

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

Selection guide

Japanese model ranking guide

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

qwen3.5-max-previewgemini-3-progemini-3.1-pro-previewgpt-5.4-highgemini-3-flash
Current DirectoryChat · Text · Japanese
Models228
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / JapanesePublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
qwen3.5-max-preview
Alibaba
100.0
174
-
-
2
gemini-3-pro
Google
99.6
406
1.05M
¥14.4 / ¥86.4Input/Output
3
gemini-3.1-pro-preview
Google
99.1
351
1.05M
¥14.4 / ¥86.4Input/Output
4
gpt-5.4-high
Openai
98.7
241
1.05M
¥18 / ¥108Input/Output
5
gemini-3-flash
Google
98.2
272
1.05M
¥3.6 / ¥21.6Input/Output
6
claude-opus-4-6-thinking
Anthropic
97.8
274
1M
¥36 / ¥180Input/Output
7
gpt-5.4
Openai
97.4
229
1.05M
¥18 / ¥108Input/Output
8
claude-opus-4-6
Anthropic
96.9
276
1M
¥36 / ¥180Input/Output
9
gemini-2.5-pro
Google
96.5
1.8K
1.05M
¥9 / ¥72Input/Output
10
kimi-k2.6
Moonshot
96.0
139
262K
¥6.84 / ¥28.8Input/Output
11
gpt-5.1-high
Openai
95.6
369
400K
¥9 / ¥72Input/Output
12
claude-opus-4-7
Anthropic
95.2
192
1M
¥36 / ¥180Input/Output
13
qwen3.5-397b-a17b
Alibaba
94.7
247
262K
¥3.1 / ¥18.6Input/Output
14
kimi-k2.5-thinking
Moonshot
94.3
287
262K
¥4.32 / ¥21.6Input/Output
15
deepseek-v4-pro
Deepseek
93.8
142
1M
¥3.13 / ¥6.26Input/Output
16
gpt-5.2-chat-latest-20260210
Openai
93.4
225
400K
¥12.6 / ¥101Input/Output
17
gemini-3-flash (thinking-minimal)
Google
93.0
400
1.05M
¥3.6 / ¥21.6Input/Output
18
claude-opus-4-5-20251101-thinking-32k
Anthropic
92.5
311
200K
¥108 / ¥540Input/Output
19
gpt-5.2-high
Openai
92.1
365
400K
¥12.6 / ¥101Input/Output
20
gpt-5.1
Openai
91.6
383
400K
¥9 / ¥72Input/Output
21
qwen3.6-plus
Alibaba
91.2
130
1M
¥3.6 / ¥21.6Input/Output
22
grok-4.20-beta1
Xai
90.7
189
2M
¥14.4 / ¥43.2Input/Output
23
grok-4.20-beta-0309-reasoning
Xai
90.3
225
2M
¥14.4 / ¥43.2Input/Output
24
gpt-4.5-preview-2025-02-27
Openai
89.9
271
8.19K
¥216 / ¥432Input/Output
25
glm-4.5
Zai
89.4
707
131K
¥4.32 / ¥15.8Input/Output
26
gpt-5.5-instant
Openai
89.0
202
400K
¥9 / ¥72Input/Output
27
gemini-3.1-flash-lite-preview
Google
88.5
278
1.05M
¥1.8 / ¥10.8Input/Output
28
deepseek-v4-flash-thinking
Deepseek
88.1
141
1M
¥1.01 / ¥2.02Input/Output
29
claude-opus-4-5-20251101
Anthropic
87.7
530
200K
¥36 / ¥180Input/Output
30
chatgpt-4o-latest-20250326
Openai
87.2
1.2K
128K
¥18 / ¥72Input/Output
31
claude-opus-4-7-thinking
Anthropic
86.8
146
1M
¥36 / ¥180Input/Output
32
gemini-2.5-flash-preview-09-2025
Google
86.3
303
1M
¥2.16 / ¥18Input/Output
33
o3-2025-04-16
Openai
85.9
1.3K
200K
¥14.4 / ¥57.6Input/Output
34
gpt-5-chat
Openai
85.5
466
400K
¥9 / ¥72Input/Output
35
qwen3-next-80b-a3b-instruct
Alibaba
85.0
268
131K
¥1.04 / ¥4.13Input/Output
36
grok-4.1
Xai
84.6
586
200K
¥14.4 / ¥72Input/Output
37
gemini-2.5-flash
Google
84.1
1.8K
1.05M
¥2.16 / ¥18Input/Output
38
qwen3-max-preview
Alibaba
83.7
372
262K
¥6.2 / ¥24.8Input/Output
39
gpt-5-high
Openai
83.3
817
400K
¥9 / ¥72Input/Output
40
grok-3-preview-02-24
Xai
82.8
777
1M
¥9 / ¥18Input/Output
41
glm-4.6
Zai
82.4
310
205K
¥4.32 / ¥15.8Input/Output
42
glm-5
Zai
81.9
184
205K
¥7.2 / ¥23Input/Output
43
longcat-flash-chat-2602-exp
Meituan
81.5
189
128K
¥1.08 / ¥10.8Input/Output
44
claude-sonnet-4-5-20250929
Anthropic
81.1
624
200K
¥21.6 / ¥108Input/Output
45
qwen3-235b-a22b-instruct-2507
Alibaba
80.6
1.2K
128K
¥2.09 / ¥8.23Input/Output
46
grok-4-0709
Xai
80.2
860
256K
¥21.6 / ¥108Input/Output
47
gpt-5.4-mini-high
Openai
79.7
157
400K
¥5.4 / ¥32.4Input/Output
48
mistral-large-3
Mistral
79.3
323
262K
¥3.6 / ¥10.8Input/Output
49
gpt-5.2
Openai
78.9
325
400K
¥12.6 / ¥101Input/Output
50
dola-seed-2.0-pro
Bytedance
78.4
321
-
-
51
mimo-v2-pro
Xiaomi
78.0
143
1.05M
¥7.2 / ¥21.6Input/Output
52
qwen3-235b-a22b-thinking-2507
Alibaba
77.5
403
131K
¥2.07 / ¥8.26Input/Output
53
deepseek-r1-0528
Deepseek
77.1
549
164K
¥3.6 / ¥15.5Input/Output
54
qwen3-vl-235b-a22b-instruct
Alibaba
76.7
151
128K
¥2.16 / ¥8.64Input/Output
55
deepseek-v4-flash
Deepseek
76.2
135
1M
¥1.01 / ¥2.02Input/Output
56
grok-4.20-multi-agent-beta-0309
Xai
75.8
182
2M
¥14.4 / ¥43.2Input/Output
57
deepseek-v3.2-thinking
Deepseek
75.3
311
128K
¥2.09 / ¥3.1Input/Output
58
ernie-5.0-0110
Baidu
74.9
330
128K
¥7.92 / ¥14.4Input/Output
59
grok-4.1-thinking
Xai
74.4
529
200K
¥14.4 / ¥72Input/Output
60
claude-opus-4-1-20250805-thinking-16k
Anthropic
74.0
560
200K
¥108 / ¥540Input/Output
61
qwen3.5-flash
Alibaba
73.6
210
1M
¥1.24 / ¥12.4Input/Output
62
mistral-medium-2508
Mistral
73.1
974
262K
¥2.88 / ¥14.4Input/Output
63
claude-sonnet-4-6
Anthropic
72.7
201
1M
¥21.6 / ¥108Input/Output
64
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
72.2
641
200K
¥21.6 / ¥108Input/Output
65
qwen3-235b-a22b-no-thinking
Alibaba
71.8
794
131K
¥2.07 / ¥8.26Input/Output
66
claude-opus-4-1-20250805
Anthropic
71.4
1K
200K
¥108 / ¥540Input/Output
67
deepseek-v3.1
Deepseek
70.9
308
128K
¥1.44 / ¥5.04Input/Output
68
qwen3.5-27b
Alibaba
70.5
192
262K
¥2.16 / ¥17.3Input/Output
69
deepseek-v3.1-thinking
Deepseek
70.0
234
128K
¥1.44 / ¥5.04Input/Output
70
amazon-nova-experimental-chat-11-10
Amazon
69.6
170
-
-
71
deepseek-v3.2
Deepseek
69.2
397
128K
¥2.09 / ¥3.1Input/Output
72
qwen3.5-122b-a10b
Alibaba
68.7
214
262K
¥2.88 / ¥23Input/Output
73
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
68.3
414
1.05M
¥0.72 / ¥2.88Input/Output
74
kimi-k2-thinking-turbo
Moonshot
67.8
468
262K
¥17.3 / ¥72Input/Output
75
gpt-5.4-nano-high
Openai
67.4
169
400K
¥1.44 / ¥9Input/Output
76
gpt-5.3-chat-latest
Openai
67.0
221
128K
¥12.6 / ¥101Input/Output
77
grok-4-fast-reasoning
Xai
66.5
177
2M
¥1.44 / ¥3.6Input/Output
78
gemini-2.5-flash-lite-preview-06-17-thinking
Google
66.1
727
65.5K
¥0.72 / ¥2.88Input/Output
79
grok-4-1-fast-reasoning
Xai
65.6
355
2M
¥1.44 / ¥3.6Input/Output
80
o1-2024-12-17
Openai
65.2
581
128K
¥108 / ¥432Input/Output
81
kimi-k2-0905-preview
Moonshot
64.8
182
262K
¥4.32 / ¥18Input/Output
82
gpt-5-mini-high
Openai
64.3
404
400K
¥1.8 / ¥14.4Input/Output
83
glm-4.5-air
Zai
63.9
785
131K
¥0 / ¥0Input/Output
84
trinity-large-thinking
-
63.4
191
262K
¥1.8 / ¥6.48Input/Output
85
step-3.5-flash
Stepfun
63.0
291
256K
¥0.69 / ¥2.07Input/Output
86
mimo-v2-flash (non-thinking)
Xiaomi
62.6
365
262K
¥0.72 / ¥2.16Input/Output
87
qwen3.5-35b-a3b
Alibaba
62.1
208
262K
¥1.8 / ¥14.4Input/Output
88
grok-3-mini-beta
Xai
61.7
591
1M
¥9 / ¥18Input/Output
89
qwen3-30b-a3b-instruct-2507
Alibaba
61.2
704
262K
¥2.16 / ¥3.6Input/Output
90
claude-opus-4-20250514-thinking-16k
Anthropic
60.8
755
200K
¥108 / ¥540Input/Output
91
hunyuan-turbos-20250416
Tencent
60.4
316
131K
¥0 / ¥0Input/Output
92
claude-opus-4-20250514
Anthropic
59.9
974
200K
¥108 / ¥540Input/Output
93
kimi-k2-0711-preview
Moonshot
59.5
829
131K
¥4.32 / ¥18Input/Output
94
deepseek-v3.2-exp
Deepseek
59.0
120
128K
¥0 / ¥0Input/Output
95
deepseek-v3-0324
Deepseek
58.6
961
75K
¥1.44 / ¥5.76Input/Output
96
deepseek-r1
Deepseek
58.1
468
164K
¥5.04 / ¥18Input/Output
97
gpt-oss-120b
Openai
57.7
502
131K
¥1.08 / ¥4.32Input/Output
98
claude-haiku-4-5-20251001
Anthropic
57.3
630
200K
¥7.2 / ¥36Input/Output
99
grok-3-mini-high
Xai
56.8
419
128K
¥0 / ¥0Input/Output
100
gpt-4.1-2025-04-14
Openai
56.4
1K
1.05M
¥14.4 / ¥57.6Input/Output
101
mistral-medium-2505
Mistral
55.9
802
262K
¥2.88 / ¥14.4Input/Output
102
longcat-flash-chat
Meituan
55.5
163
128K
¥1.08 / ¥10.8Input/Output
103
qwen3-235b-a22b
Alibaba
55.1
646
131K
¥2.07 / ¥8.26Input/Output
104
trinity-large-preview
-
54.6
180
262K
¥1.8 / ¥6.48Input/Output
105
qwen3-coder-480b-a35b-instruct
Alibaba
54.2
850
262K
¥6.2 / ¥24.8Input/Output
106
gemini-2.0-flash-lite-preview-02-05
Google
53.7
542
1.05M
¥0.54 / ¥2.16Input/Output
107
o4-mini-2025-04-16
Openai
53.3
983
200K
¥7.92 / ¥31.7Input/Output
108
qwen2.5-max
Alibaba
52.9
691
32K
¥11.5 / ¥46Input/Output
109
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia
52.4
383
131K
¥2.88 / ¥2.88Input/Output
110
o1-preview
Openai
52.0
674
128K
¥108 / ¥432Input/Output
111
gemini-2.0-flash-001
Google
51.5
961
1.05M
¥1.08 / ¥4.32Input/Output
112
gemini-1.5-pro-002
Google
51.1
1.2K
-
-
113
claude-sonnet-4-20250514
Anthropic
50.7
875
200K
¥21.6 / ¥108Input/Output
114
claude-sonnet-4-20250514-thinking-32k
Anthropic
50.2
736
200K
¥21.6 / ¥108Input/Output
115
command-a-03-2025
Cohere
49.8
1.1K
256K
¥18 / ¥72Input/Output
116
minimax-m2.1-preview
Minimax
49.3
146
205K
¥0 / ¥0Input/Output
117
gemma-3-27b-it
Google
48.9
951
128K
¥2.15 / ¥2.15Input/Output
118
o3-mini-high
Openai
48.5
374
200K
¥7.92 / ¥31.7Input/Output
119
gpt-4.1-mini-2025-04-14
Openai
48.0
909
1.05M
¥2.88 / ¥11.5Input/Output
120
qwen3-next-80b-a3b-thinking
Alibaba
47.6
180
131K
¥1.04 / ¥10.3Input/Output
121
mistral-small-2506
Mistral
47.1
463
262K
¥2.88 / ¥14.4Input/Output
122
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
46.7
934
-
-
123
gemma-3n-e4b-it
Google
46.3
674
128K
¥0 / ¥0Input/Output
124
claude-3-7-sonnet-20250219
Anthropic
45.8
920
200K
¥21.6 / ¥108Input/Output
125
deepseek-v3
Deepseek
45.4
534
128K
¥0 / ¥0Input/Output
126
o3-mini
Openai
44.9
1.3K
200K
¥7.92 / ¥31.7Input/Output
127
qwq-32b
Alibaba
44.5
571
131K
¥2.07 / ¥6.2Input/Output
128
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
44.1
127
131K
¥0 / ¥0Input/Output
129
gpt-4o-2024-05-13
Openai
43.6
2.7K
128K
¥36 / ¥108Input/Output
130
gemini-1.5-flash-002
Google
43.2
753
2M
¥0.54 / ¥2.2Input/Output
131
qwen3-30b-a3b
Alibaba
42.7
665
128K
¥0.79 / ¥7.78Input/Output
132
qwen-plus-0125
Alibaba
42.3
206
1M
¥0.83 / ¥2.07Input/Output
133
gpt-oss-20b
Openai
41.9
233
131K
¥0.32 / ¥1.3Input/Output
134
o1-mini
Openai
41.4
1.1K
128K
¥7.92 / ¥31.7Input/Output
135
grok-2-2024-08-13
Xai
41.0
1.5K
1M
¥9 / ¥18Input/Output
136
gemini-advanced-0514
Google
40.5
1.2K
-
-
137
gemini-1.5-pro-001
Google
40.1
1.9K
-
-
138
gpt-4o-2024-08-06
Openai
39.6
1.1K
128K
¥18 / ¥72Input/Output
139
claude-3-5-sonnet-20241022
Anthropic
39.2
2K
200K
¥21.6 / ¥108Input/Output
140
claude-3-5-sonnet-20240620
Anthropic
38.8
2.1K
200K
¥21.6 / ¥108Input/Output
141
yi-lightning
-
38.3
565
12K
¥1.44 / ¥1.44Input/Output
142
deepseek-v2.5-1210
Deepseek
37.9
161
1M
¥1.01 / ¥2.02Input/Output
143
minimax-m2.7
Minimax
37.4
184
205K
¥0 / ¥0Input/Output
144
glm-4-plus-0111
Zai
37.0
201
128K
¥72 / ¥72Input/Output
145
gpt-4o-mini-2024-07-18
Openai
36.6
1.8K
128K
¥1.08 / ¥4.32Input/Output
146
athene-v2-chat
-
36.1
584
-
-
147
grok-2-mini-2024-08-13
Xai
35.7
1.2K
1M
¥9 / ¥18Input/Output
148
minimax-m1
Minimax
35.2
773
1M
¥0.95 / ¥9.03Input/Output
149
mistral-small-3.1-24b-instruct-2503
Mistral
34.8
714
262K
¥2.88 / ¥14.4Input/Output
150
llama-4-scout-17b-16e-instruct
Meta
34.4
715
128K
¥1.44 / ¥5.62Input/Output
151
gpt-4-1106-preview
Openai
33.9
1.4K
8.19K
¥216 / ¥432Input/Output
152
llama-3.1-405b-instruct-bf16
Meta
33.5
846
128K
¥0 / ¥0Input/Output
153
glm-4-plus
Zai
33.0
485
128K
¥54 / ¥54Input/Output
154
qwen2.5-plus-1127
Alibaba
32.6
300
-
-
155
qwen-max-0919
Alibaba
32.2
312
131K
¥2.48 / ¥9.91Input/Output
156
claude-3-opus-20240229
Anthropic
31.7
3.7K
200K
¥108 / ¥540Input/Output
157
llama-4-maverick-17b-128e-instruct
Meta
31.3
862
1M
¥1.8 / ¥6.26Input/Output
158
amazon-nova-pro-v1.0
Amazon
30.8
511
300K
¥5.76 / ¥23Input/Output
159
gpt-4.1-nano-2025-04-14
Openai
30.4
160
1.05M
¥14.4 / ¥57.6Input/Output
160
gpt-4-0125-preview
Openai
30.0
1.5K
8.19K
¥216 / ¥432Input/Output
161
gpt-4-turbo-2024-04-09
Openai
29.5
2.1K
128K
¥72 / ¥216Input/Output
162
deepseek-v2.5
Deepseek
29.1
479
1M
¥1.01 / ¥2.02Input/Output
163
mistral-large-2407
Mistral
28.6
1.2K
131K
¥14.4 / ¥43.2Input/Output
164
gemini-1.5-flash-001
Google
28.2
1.5K
2M
¥0.54 / ¥2.2Input/Output
165
qwen2.5-72b-instruct
Alibaba
27.8
788
131K
¥4.13 / ¥12.4Input/Output
166
gemma-2-27b-it
Google
27.3
1.8K
8.19K
¥0.58 / ¥0.58Input/Output
167
magistral-medium-2506
Mistral
26.9
295
128K
¥14.4 / ¥36Input/Output
168
claude-3-5-haiku-20241022
Anthropic
26.4
1.4K
200K
¥5.76 / ¥28.8Input/Output
169
llama-3.1-405b-instruct-fp8
Meta
26.0
1.6K
128K
¥0 / ¥0Input/Output
170
mistral-large-2411
Mistral
25.6
629
128K
¥14.4 / ¥43.2Input/Output
171
minimax-m2.5
Minimax
25.1
277
205K
¥0 / ¥0Input/Output
172
command-r-plus-08-2024
Cohere
24.7
210
128K
¥18 / ¥72Input/Output
173
c4ai-aya-expanse-32b
Cohere
24.2
670
-
-
174
phi-4
Microsoft
23.8
500
128K
¥0.9 / ¥3.6Input/Output
175
command-r-plus
Cohere
23.3
1.5K
128K
¥18 / ¥72Input/Output
176
amazon-nova-micro-v1.0
Amazon
22.9
443
128K
¥0.25 / ¥1.01Input/Output
177
amazon-nova-lite-v1.0
Amazon
22.5
403
300K
¥0.43 / ¥1.73Input/Output
178
gemini-1.5-flash-8b-001
Google
22.0
691
2M
¥0.54 / ¥2.2Input/Output
179
llama-3.3-70b-instruct
Meta
21.6
1.1K
128K
¥0 / ¥0Input/Output
180
gemma-2-9b-it
Google
21.1
1.3K
8.19K
¥1.44 / ¥1.44Input/Output
181
command-r-08-2024
Cohere
20.7
254
128K
¥18 / ¥72Input/Output
182
gemma-2-9b-it-simpo
-
20.3
291
8.19K
¥1.44 / ¥1.44Input/Output
183
athene-70b-0725
-
19.8
676
-
-
184
gpt-4-0314
Openai
19.4
619
8.19K
¥216 / ¥432Input/Output
185
llama-3.1-70b-instruct
Meta
18.9
1.4K
131K
¥2.88 / ¥2.88Input/Output
186
claude-3-sonnet-20240229
Anthropic
18.5
1.8K
200K
¥21.6 / ¥108Input/Output
187
nemotron-4-340b-instruct
Nvidia
18.1
434
-
-
188
deepseek-coder-v2
Deepseek
17.6
345
1M
¥1.01 / ¥2.02Input/Output
189
c4ai-aya-expanse-8b
Cohere
17.2
231
-
-
190
jamba-1.5-large
-
16.7
242
256K
¥0 / ¥0Input/Output
191
gpt-4-0613
Openai
16.3
1.2K
8.19K
¥216 / ¥432Input/Output
192
mistral-small-24b-instruct-2501
Mistral
15.9
269
262K
¥2.88 / ¥14.4Input/Output
193
qwen2-72b-instruct
Alibaba
15.4
901
131K
¥4.13 / ¥12.4Input/Output
194
claude-3-haiku-20240307
Anthropic
15.0
2.1K
200K
¥1.8 / ¥9Input/Output
195
command-r
Cohere
14.5
856
128K
¥18 / ¥72Input/Output
196
gemma-2-2b-it
Google
14.1
1.2K
128K
¥0 / ¥0Input/Output
197
reka-flash-21b-20240226-online
-
13.7
274
-
-
198
qwen1.5-110b-chat
Alibaba
13.2
599
-
-
199
qwen1.5-72b-chat
Alibaba
12.8
495
-
-
200
llama-3.1-8b-instruct
Meta
12.3
1.2K
131K
¥0.79 / ¥0.79Input/Output
201
reka-flash-21b-20240226
-
11.9
440
-
-
202
gpt-3.5-turbo-0125
Openai
11.5
965
16.4K
¥3.6 / ¥10.8Input/Output
203
phi-3-medium-4k-instruct
Microsoft
11.0
683
4.1K
¥1.22 / ¥4.9Input/Output
204
mixtral-8x22b-instruct-v0.1
Mistral
10.6
972
64K
¥14.4 / ¥43.2Input/Output
205
qwen1.5-32b-chat
Alibaba
10.1
324
-
-
206
gemini-pro-dev-api
Google
9.7
173
1.05M
¥14.4 / ¥86.4Input/Output
207
yi-1.5-34b-chat
-
9.3
506
-
-
208
qwen1.5-14b-chat
Alibaba
8.8
217
-
-
209
jamba-1.5-mini
-
8.4
270
256K
¥0 / ¥0Input/Output
210
llama-3-70b-instruct
Meta
7.9
3.3K
8.19K
¥3.67 / ¥5.33Input/Output
211
mistral-medium
Mistral
7.5
337
262K
¥2.88 / ¥14.4Input/Output
212
mistral-large-2402
Mistral
7.0
945
262K
¥2.88 / ¥14.4Input/Output
213
starling-lm-7b-beta
-
6.6
181
200K
¥5.4 / ¥18.7Input/Output
214
yi-34b-chat
-
6.2
197
-
-
215
dbrx-instruct-preview
-
5.7
426
-
-
216
gemma-1.1-7b-it
Google
5.3
449
-
-
217
snowflake-arctic-instruct
-
4.8
667
-
-
218
llama-3-8b-instruct
Meta
4.4
2K
8.19K
¥0.29 / ¥0.29Input/Output
219
phi-3-small-8k-instruct
Microsoft
4.0
390
8.19K
¥1.08 / ¥4.32Input/Output
220
vicuna-33b
-
3.5
195
-
-
221
phi-3-mini-4k-instruct-june-2024
Microsoft
3.1
354
4.1K
¥0.94 / ¥3.74Input/Output
222
phi-3-mini-4k-instruct
Microsoft
2.6
384
4.1K
¥0.94 / ¥3.74Input/Output
223
mixtral-8x7b-instruct-v0.1
Mistral
2.2
960
32K
¥5.04 / ¥5.04Input/Output
224
llama-2-70b-chat
Meta
1.8
341
-
-
225
vicuna-13b
-
1.3
125
-
-
226
phi-3-mini-128k-instruct
Microsoft
0.9
385
128K
¥0.94 / ¥3.74Input/Output
227
llama-2-13b-chat
Meta
0.4
175
-
-
228
mistral-7b-instruct-v0.2
Mistral
0.0
167
262K
¥2.88 / ¥14.4Input/Output
Top model analysis

qwen3.5-max-preview why it ranks first

qwen3.5-max-preview ranks first with a percent score of 100.0 and 174 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

日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。

日语模型应该怎么选?

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。