Chat · Text · Korean Leaderboard

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

Selection guide

Korean model ranking guide

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

gemini-3.5-flashgemini-3.1-pro-previewgpt-5.5-highmimo-v2.5-promuse-spark
Current DirectoryChat · Text · Korean
Models240
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / KoreanPublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
gemini-3.5-flash
Google
100.0
192
1.05M
¥10.8 / ¥64.8Input/Output
2
gemini-3.1-pro-preview
Google
99.6
795
1.05M
¥14.4 / ¥86.4Input/Output
3
gpt-5.5-high
Openai
99.2
219
1.05M
¥36 / ¥216Input/Output
4
mimo-v2.5-pro
Xiaomi
98.7
254
1.05M
¥7.2 / ¥21.6Input/Output
5
muse-spark
Meta
98.3
239
-
-
6
gemini-3-pro
Google
97.9
664
1.05M
¥14.4 / ¥86.4Input/Output
7
claude-opus-4-6
Anthropic
97.5
661
1M
¥36 / ¥180Input/Output
8
claude-opus-4-7-thinking
Anthropic
97.1
388
1M
¥36 / ¥180Input/Output
9
claude-opus-4-7
Anthropic
96.7
377
1M
¥36 / ¥180Input/Output
10
gemini-3-flash
Google
96.2
533
1.05M
¥3.6 / ¥21.6Input/Output
11
gpt-5.4-high
Openai
95.8
496
1.05M
¥18 / ¥108Input/Output
12
gpt-5.4
Openai
95.4
530
1.05M
¥18 / ¥108Input/Output
13
gemini-2.5-pro
Google
95.0
2.4K
1.05M
¥9 / ¥72Input/Output
14
kimi-k2.6
Moonshot
94.6
312
262K
¥6.84 / ¥28.8Input/Output
15
gemini-3-flash (thinking-minimal)
Google
94.1
803
1.05M
¥3.6 / ¥21.6Input/Output
16
claude-opus-4-6-thinking
Anthropic
93.7
561
1M
¥36 / ¥180Input/Output
17
qwen3.5-max-preview
Alibaba
93.3
370
-
-
18
dola-seed-2.0-pro
Bytedance
92.9
637
-
-
19
ernie-5.1
Baidu
92.5
237
119K
¥5.4 / ¥21.6Input/Output
20
claude-opus-4-5-20251101
Anthropic
92.1
1K
200K
¥36 / ¥180Input/Output
21
grok-4.20-beta-0309-reasoning
Xai
91.6
455
2M
¥14.4 / ¥43.2Input/Output
22
glm-5
Zai
91.2
416
205K
¥7.2 / ¥23Input/Output
23
claude-sonnet-4-6
Anthropic
90.8
425
1M
¥21.6 / ¥108Input/Output
24
gpt-5.5
Openai
90.4
221
1.05M
¥36 / ¥216Input/Output
25
glm-5.1
Zai
90.0
284
200K
¥0 / ¥0Input/Output
26
deepseek-v4-pro-thinking
Deepseek
89.5
276
1M
¥3.13 / ¥6.26Input/Output
27
grok-4.20-beta1
Xai
89.1
424
2M
¥14.4 / ¥43.2Input/Output
28
grok-4.20-multi-agent-beta-0309
Xai
88.7
472
2M
¥14.4 / ¥43.2Input/Output
29
grok-4.1
Xai
88.3
1.1K
200K
¥14.4 / ¥72Input/Output
30
gemini-3.1-flash-lite-preview
Google
87.9
646
1.05M
¥1.8 / ¥10.8Input/Output
31
glm-4.7
Zai
87.4
159
205K
¥0 / ¥0Input/Output
32
kimi-k2.5-thinking
Moonshot
87.0
627
262K
¥4.32 / ¥21.6Input/Output
33
ernie-5.0-0110
Baidu
86.6
583
128K
¥7.92 / ¥14.4Input/Output
34
chatgpt-4o-latest-20250326
Openai
86.2
1.3K
128K
¥18 / ¥72Input/Output
35
deepseek-v4-pro
Deepseek
85.8
343
1M
¥3.13 / ¥6.26Input/Output
36
qwen3-vl-235b-a22b-instruct
Alibaba
85.4
308
128K
¥2.16 / ¥8.64Input/Output
37
hunyuan-t1-20250711
Tencent
84.9
179
131K
¥0 / ¥0Input/Output
38
grok-4.1-thinking
Xai
84.5
1K
200K
¥14.4 / ¥72Input/Output
39
mimo-v2-pro
Xiaomi
84.1
421
1.05M
¥7.2 / ¥21.6Input/Output
40
gpt-5.1-high
Openai
83.7
618
400K
¥9 / ¥72Input/Output
41
o1-2024-12-17
Openai
83.3
396
128K
¥108 / ¥432Input/Output
42
claude-sonnet-4-5-20250929
Anthropic
82.8
1.2K
200K
¥21.6 / ¥108Input/Output
43
qwen3-max-preview
Alibaba
82.4
668
262K
¥6.2 / ¥24.8Input/Output
44
gpt-5.5-instant
Openai
82.0
397
400K
¥9 / ¥72Input/Output
45
gpt-5.2-chat-latest-20260210
Openai
81.6
483
400K
¥12.6 / ¥101Input/Output
46
gpt-5.1
Openai
81.2
671
400K
¥9 / ¥72Input/Output
47
qwen3-235b-a22b-instruct-2507
Alibaba
80.8
1.7K
128K
¥2.09 / ¥8.23Input/Output
48
qwen3.6-plus
Alibaba
80.3
334
1M
¥3.6 / ¥21.6Input/Output
49
qwen3.5-397b-a17b
Alibaba
79.9
484
262K
¥3.1 / ¥18.6Input/Output
50
gpt-4.5-preview-2025-02-27
Openai
79.5
215
8.19K
¥216 / ¥432Input/Output
51
gemini-2.5-flash-preview-09-2025
Google
79.1
654
1M
¥2.16 / ¥18Input/Output
52
gemini-2.5-flash
Google
78.7
2.2K
1.05M
¥2.16 / ¥18Input/Output
53
glm-4.6
Zai
78.2
570
205K
¥4.32 / ¥15.8Input/Output
54
amazon-nova-experimental-chat-11-10
Amazon
77.8
370
-
-
55
mistral-large-3
Mistral
77.4
648
262K
¥3.6 / ¥10.8Input/Output
56
claude-opus-4-1-20250805-thinking-16k
Anthropic
77.0
1.1K
200K
¥108 / ¥540Input/Output
57
kimi-k2.5-instant
Moonshot
76.6
126
262K
¥4.32 / ¥21.6Input/Output
58
mimo-v2.5
Xiaomi
76.2
259
1.05M
¥2.88 / ¥14.4Input/Output
59
glm-4.5
Zai
75.7
606
131K
¥4.32 / ¥15.8Input/Output
60
mistral-medium-2508
Mistral
75.3
1.8K
262K
¥2.88 / ¥14.4Input/Output
61
gpt-5.2-high
Openai
74.9
719
400K
¥12.6 / ¥101Input/Output
62
claude-opus-4-5-20251101-thinking-32k
Anthropic
74.5
550
200K
¥108 / ¥540Input/Output
63
deepseek-v3.2
Deepseek
74.1
737
128K
¥2.09 / ¥3.1Input/Output
64
gpt-5.2
Openai
73.6
724
400K
¥12.6 / ¥101Input/Output
65
ernie-5.0-preview-1203
Baidu
73.2
150
128K
¥7.92 / ¥14.4Input/Output
66
grok-3-preview-02-24
Xai
72.8
492
1M
¥9 / ¥18Input/Output
67
longcat-flash-chat-2602-exp
Meituan
72.4
397
128K
¥1.08 / ¥10.8Input/Output
68
o3-2025-04-16
Openai
72.0
1.1K
200K
¥14.4 / ¥57.6Input/Output
69
deepseek-v4-flash
Deepseek
71.5
265
1M
¥1.01 / ¥2.02Input/Output
70
grok-4.3
Xai
71.1
203
1M
¥9 / ¥18Input/Output
71
gpt-5.4-mini-high
Openai
70.7
427
400K
¥5.4 / ¥32.4Input/Output
72
gpt-5-high
Openai
70.3
806
400K
¥9 / ¥72Input/Output
73
grok-4-0709
Xai
69.9
808
256K
¥21.6 / ¥108Input/Output
74
deepseek-v4-flash-thinking
Deepseek
69.5
324
1M
¥1.01 / ¥2.02Input/Output
75
qwen3-vl-235b-a22b-thinking
Alibaba
69.0
212
131K
¥2.06 / ¥8.26Input/Output
76
claude-opus-4-1-20250805
Anthropic
68.6
1.5K
200K
¥108 / ¥540Input/Output
77
deepseek-v3.2-exp
Deepseek
68.2
192
128K
¥0 / ¥0Input/Output
78
grok-4-1-fast-reasoning
Xai
67.8
814
2M
¥1.44 / ¥3.6Input/Output
79
hunyuan-turbos-20250416
Tencent
67.4
129
131K
¥0 / ¥0Input/Output
80
qwen3.5-27b
Alibaba
66.9
409
262K
¥2.16 / ¥17.3Input/Output
81
longcat-flash-chat
Meituan
66.5
287
128K
¥1.08 / ¥10.8Input/Output
82
qwen3-235b-a22b-thinking-2507
Alibaba
66.1
199
131K
¥2.07 / ¥8.26Input/Output
83
qwen3-235b-a22b-no-thinking
Alibaba
65.7
705
131K
¥2.07 / ¥8.26Input/Output
84
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
65.3
1.2K
200K
¥21.6 / ¥108Input/Output
85
qwen3.5-flash
Alibaba
64.9
529
1M
¥1.24 / ¥12.4Input/Output
86
qwen3-next-80b-a3b-instruct
Alibaba
64.4
484
131K
¥1.04 / ¥4.13Input/Output
87
gemini-2.5-flash-lite-preview-06-17-thinking
Google
64.0
696
65.5K
¥0.72 / ¥2.88Input/Output
88
gpt-5-chat
Openai
63.6
783
400K
¥9 / ¥72Input/Output
89
mimo-v2-flash (non-thinking)
Xiaomi
63.2
691
262K
¥0.72 / ¥2.16Input/Output
90
qwen3.5-122b-a10b
Alibaba
62.8
414
262K
¥2.88 / ¥23Input/Output
91
deepseek-v3.2-thinking
Deepseek
62.3
624
128K
¥2.09 / ¥3.1Input/Output
92
qwen3.5-35b-a3b
Alibaba
61.9
449
262K
¥1.8 / ¥14.4Input/Output
93
qwen3-max-2025-09-23
Alibaba
61.5
250
258K
¥6.19 / ¥24.7Input/Output
94
deepseek-r1-0528
Deepseek
61.1
298
164K
¥3.6 / ¥15.5Input/Output
95
grok-4-fast-reasoning
Xai
60.7
341
2M
¥1.44 / ¥3.6Input/Output
96
gpt-5.3-chat-latest
Openai
60.3
512
128K
¥12.6 / ¥101Input/Output
97
gpt-4.1-2025-04-14
Openai
59.8
1K
1.05M
¥14.4 / ¥57.6Input/Output
98
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
59.4
761
1.05M
¥0.72 / ¥2.88Input/Output
99
step-3.5-flash
Stepfun
59.0
580
256K
¥0.69 / ¥2.07Input/Output
100
grok-4-fast-chat
Xai
58.6
201
2M
¥1.44 / ¥3.6Input/Output
101
deepseek-v3.2-exp-thinking
Deepseek
58.2
195
128K
¥0 / ¥0Input/Output
102
grok-3-mini-high
Xai
57.7
307
128K
¥0 / ¥0Input/Output
103
deepseek-v3.1-thinking
Deepseek
57.3
357
128K
¥1.44 / ¥5.04Input/Output
104
ling-flash-2.0
Ant Group
56.9
217
131K
¥1.01 / ¥4.1Input/Output
105
amazon-nova-experimental-chat-10-20
Amazon
56.5
167
-
-
106
deepseek-v3.1
Deepseek
56.1
472
128K
¥1.44 / ¥5.04Input/Output
107
kimi-k2-thinking-turbo
Moonshot
55.6
940
262K
¥17.3 / ¥72Input/Output
108
deepseek-r1
Deepseek
55.2
215
164K
¥5.04 / ¥18Input/Output
109
claude-haiku-4-5-20251001
Anthropic
54.8
1.1K
200K
¥7.2 / ¥36Input/Output
110
qwen3-30b-a3b-instruct-2507
Alibaba
54.4
566
262K
¥2.16 / ¥3.6Input/Output
111
gemini-2.0-flash-lite-preview-02-05
Google
54.0
353
1.05M
¥0.54 / ¥2.16Input/Output
112
o4-mini-2025-04-16
Openai
53.6
938
200K
¥7.92 / ¥31.7Input/Output
113
deepseek-v3-0324
Deepseek
53.1
924
75K
¥1.44 / ¥5.76Input/Output
114
qwen3-235b-a22b
Alibaba
52.7
472
131K
¥2.07 / ¥8.26Input/Output
115
claude-opus-4-20250514-thinking-16k
Anthropic
52.3
724
200K
¥108 / ¥540Input/Output
116
o3-mini-high
Openai
51.9
241
200K
¥7.92 / ¥31.7Input/Output
117
kimi-k2-0905-preview
Moonshot
51.5
292
262K
¥4.32 / ¥18Input/Output
118
gemini-2.0-flash-001
Google
51.0
662
1.05M
¥1.08 / ¥4.32Input/Output
119
qwen3-next-80b-a3b-thinking
Alibaba
50.6
332
131K
¥1.04 / ¥10.3Input/Output
120
gemma-3-27b-it
Google
50.2
866
128K
¥2.15 / ¥2.15Input/Output
121
minimax-m2.7
Minimax
49.8
399
205K
¥0 / ¥0Input/Output
122
grok-3-mini-beta
Xai
49.4
411
1M
¥9 / ¥18Input/Output
123
qwen3-coder-480b-a35b-instruct
Alibaba
49.0
593
262K
¥6.2 / ¥24.8Input/Output
124
qwen2.5-max
Alibaba
48.5
470
32K
¥11.5 / ¥46Input/Output
125
gpt-5-mini-high
Openai
48.1
639
400K
¥1.8 / ¥14.4Input/Output
126
claude-opus-4-20250514
Anthropic
47.7
963
200K
¥108 / ¥540Input/Output
127
mistral-medium-2505
Mistral
47.3
606
262K
¥2.88 / ¥14.4Input/Output
128
glm-4.5-air
Zai
46.9
636
131K
¥0 / ¥0Input/Output
129
trinity-large-thinking
-
46.4
441
262K
¥1.8 / ¥6.48Input/Output
130
gemini-1.5-pro-002
Google
46.0
773
-
-
131
gpt-4.1-mini-2025-04-14
Openai
45.6
781
1.05M
¥2.88 / ¥11.5Input/Output
132
gpt-5.4-nano-high
Openai
45.2
411
400K
¥1.44 / ¥9Input/Output
133
o1-preview
Openai
44.8
493
128K
¥108 / ¥432Input/Output
134
claude-sonnet-4-20250514
Anthropic
44.4
895
200K
¥21.6 / ¥108Input/Output
135
minimax-m2.1-preview
Minimax
43.9
268
205K
¥0 / ¥0Input/Output
136
mimo-v2-flash (thinking)
Xiaomi
43.5
154
262K
¥0.72 / ¥2.16Input/Output
137
kimi-k2-0711-preview
Moonshot
43.1
618
131K
¥4.32 / ¥18Input/Output
138
glm-4.7-flash
Zai
42.7
216
200K
¥0 / ¥0Input/Output
139
command-a-03-2025
Cohere
42.3
1K
256K
¥18 / ¥72Input/Output
140
qwq-32b
Alibaba
41.8
396
131K
¥2.07 / ¥6.2Input/Output
141
gpt-oss-120b
Openai
41.4
658
131K
¥1.08 / ¥4.32Input/Output
142
nova-2-lite
Amazon
41.0
149
128K
¥2.38 / ¥19.8Input/Output
143
mistral-small-2506
Mistral
40.6
337
262K
¥2.88 / ¥14.4Input/Output
144
claude-sonnet-4-20250514-thinking-32k
Anthropic
40.2
684
200K
¥21.6 / ¥108Input/Output
145
trinity-large-preview
-
39.7
431
262K
¥1.8 / ¥6.48Input/Output
146
gpt-5-nano-high
Openai
39.3
216
400K
¥0.36 / ¥2.88Input/Output
147
step-3
Stepfun
38.9
192
65.5K
¥1.8 / ¥4.68Input/Output
148
qwen3-30b-a3b
Alibaba
38.5
440
128K
¥0.79 / ¥7.78Input/Output
149
gemma-3n-e4b-it
Google
38.1
489
128K
¥0 / ¥0Input/Output
150
o3-mini
Openai
37.7
1.1K
200K
¥7.92 / ¥31.7Input/Output
151
ring-flash-2.0
Ant Group
37.2
215
131K
¥1.01 / ¥4.1Input/Output
152
minimax-m1
Minimax
36.8
635
1M
¥0.95 / ¥9.03Input/Output
153
gpt-oss-20b
Openai
36.4
218
131K
¥0.32 / ¥1.3Input/Output
154
deepseek-v3
Deepseek
36.0
295
128K
¥0 / ¥0Input/Output
155
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
35.6
731
-
-
156
glm-4-plus
Zai
35.1
374
128K
¥54 / ¥54Input/Output
157
claude-3-7-sonnet-20250219
Anthropic
34.7
673
200K
¥21.6 / ¥108Input/Output
158
grok-2-2024-08-13
Xai
34.3
952
1M
¥9 / ¥18Input/Output
159
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
33.9
212
131K
¥0 / ¥0Input/Output
160
minimax-m2.5
Minimax
33.5
604
205K
¥0 / ¥0Input/Output
161
gpt-4o-2024-05-13
Openai
33.1
3.5K
128K
¥36 / ¥108Input/Output
162
gemini-advanced-0514
Google
32.6
1.9K
-
-
163
gemini-1.5-pro-001
Google
32.2
2.5K
-
-
164
o1-mini
Openai
31.8
716
128K
¥7.92 / ¥31.7Input/Output
165
gemini-1.5-flash-002
Google
31.4
502
2M
¥0.54 / ¥2.2Input/Output
166
gpt-4o-2024-08-06
Openai
31.0
712
128K
¥18 / ¥72Input/Output
167
llama-4-scout-17b-16e-instruct
Meta
30.5
637
128K
¥1.44 / ¥5.62Input/Output
168
deepseek-v2.5
Deepseek
30.1
344
1M
¥1.01 / ¥2.02Input/Output
169
olmo-3.1-32b-instruct
Allenai
29.7
187
200K
¥14.4 / ¥57.6Input/Output
170
mistral-small-3.1-24b-instruct-2503
Mistral
29.3
666
262K
¥2.88 / ¥14.4Input/Output
171
athene-v2-chat
-
28.9
349
-
-
172
llama-4-maverick-17b-128e-instruct
Meta
28.5
767
1M
¥1.8 / ¥6.26Input/Output
173
amazon-nova-pro-v1.0
Amazon
28.0
326
300K
¥5.76 / ¥23Input/Output
174
mistral-large-2411
Mistral
27.6
408
128K
¥14.4 / ¥43.2Input/Output
175
gemini-1.5-flash-001
Google
27.2
2.1K
2M
¥0.54 / ¥2.2Input/Output
176
claude-3-5-sonnet-20240620
Anthropic
26.8
1.7K
200K
¥21.6 / ¥108Input/Output
177
claude-3-5-sonnet-20241022
Anthropic
26.4
1.3K
200K
¥21.6 / ¥108Input/Output
178
gpt-4o-mini-2024-07-18
Openai
25.9
1.1K
128K
¥1.08 / ¥4.32Input/Output
179
grok-2-mini-2024-08-13
Xai
25.5
852
1M
¥9 / ¥18Input/Output
180
yi-lightning
-
25.1
425
12K
¥1.44 / ¥1.44Input/Output
181
mistral-small-24b-instruct-2501
Mistral
24.7
231
262K
¥2.88 / ¥14.4Input/Output
182
qwen2.5-72b-instruct
Alibaba
24.3
527
131K
¥4.13 / ¥12.4Input/Output
183
claude-3-opus-20240229
Anthropic
23.8
3.9K
200K
¥108 / ¥540Input/Output
184
gpt-4-turbo-2024-04-09
Openai
23.4
2.7K
128K
¥72 / ¥216Input/Output
185
llama-3.1-405b-instruct-fp8
Meta
23.0
924
128K
¥0 / ¥0Input/Output
186
gpt-4-1106-preview
Openai
22.6
1.3K
8.19K
¥216 / ¥432Input/Output
187
gemma-2-27b-it
Google
22.2
1.4K
8.19K
¥0.58 / ¥0.58Input/Output
188
gpt-4-0125-preview
Openai
21.8
1.4K
8.19K
¥216 / ¥432Input/Output
189
claude-3-5-haiku-20241022
Anthropic
21.3
1.2K
200K
¥5.76 / ¥28.8Input/Output
190
llama-3.1-405b-instruct-bf16
Meta
20.9
586
128K
¥0 / ¥0Input/Output
191
mistral-large-2407
Mistral
20.5
751
131K
¥14.4 / ¥43.2Input/Output
192
command-r-08-2024
Cohere
20.1
152
128K
¥18 / ¥72Input/Output
193
c4ai-aya-expanse-32b
Cohere
19.7
385
-
-
194
amazon-nova-lite-v1.0
Amazon
19.2
292
300K
¥0.43 / ¥1.73Input/Output
195
phi-4
Microsoft
18.8
319
128K
¥0.9 / ¥3.6Input/Output
196
athene-70b-0725
-
18.4
396
-
-
197
amazon-nova-micro-v1.0
Amazon
18.0
267
128K
¥0.25 / ¥1.01Input/Output
198
nemotron-4-340b-instruct
Nvidia
17.6
628
-
-
199
qwen-max-0919
Alibaba
17.2
285
131K
¥2.48 / ¥9.91Input/Output
200
llama-3.1-70b-instruct
Meta
16.7
873
131K
¥2.88 / ¥2.88Input/Output
201
gemini-1.5-flash-8b-001
Google
16.3
500
2M
¥0.54 / ¥2.2Input/Output
202
llama-3.3-70b-instruct
Meta
15.9
846
128K
¥0 / ¥0Input/Output
203
command-r-plus
Cohere
15.5
1.9K
128K
¥18 / ¥72Input/Output
204
gemma-2-9b-it
Google
15.1
1.1K
8.19K
¥1.44 / ¥1.44Input/Output
205
magistral-medium-2506
Mistral
14.6
178
128K
¥14.4 / ¥36Input/Output
206
claude-3-sonnet-20240229
Anthropic
14.2
2.1K
200K
¥21.6 / ¥108Input/Output
207
claude-3-haiku-20240307
Anthropic
13.8
2.4K
200K
¥1.8 / ¥9Input/Output
208
reka-flash-21b-20240226-online
-
13.4
309
-
-
209
deepseek-coder-v2
Deepseek
13.0
399
1M
¥1.01 / ¥2.02Input/Output
210
command-r
Cohere
12.6
1.2K
128K
¥18 / ¥72Input/Output
211
gpt-4-0314
Openai
12.1
429
8.19K
¥216 / ¥432Input/Output
212
qwen2-72b-instruct
Alibaba
11.7
1.2K
131K
¥4.13 / ¥12.4Input/Output
213
reka-flash-21b-20240226
-
11.3
629
-
-
214
gpt-4-0613
Openai
10.9
1.2K
8.19K
¥216 / ¥432Input/Output
215
mixtral-8x22b-instruct-v0.1
Mistral
10.5
1.2K
64K
¥14.4 / ¥43.2Input/Output
216
gemma-2-2b-it
Google
10.0
717
128K
¥0 / ¥0Input/Output
217
llama-3.1-8b-instruct
Meta
9.6
802
131K
¥0.79 / ¥0.79Input/Output
218
qwen1.5-72b-chat
Alibaba
9.2
552
-
-
219
qwen1.5-110b-chat
Alibaba
8.8
1.4K
-
-
220
glm-4-0520
Zai
8.4
302
128K
¥108 / ¥108Input/Output
221
mistral-medium
Mistral
7.9
268
262K
¥2.88 / ¥14.4Input/Output
222
gpt-3.5-turbo-0125
Openai
7.5
1.2K
16.4K
¥3.6 / ¥10.8Input/Output
223
mistral-large-2402
Mistral
7.1
1.1K
262K
¥2.88 / ¥14.4Input/Output
224
llama-3-70b-instruct
Meta
6.7
5.4K
8.19K
¥3.67 / ¥5.33Input/Output
225
qwen1.5-32b-chat
Alibaba
6.3
395
-
-
226
yi-1.5-34b-chat
-
5.9
804
-
-
227
llama-3-8b-instruct
Meta
5.4
2.4K
8.19K
¥0.29 / ¥0.29Input/Output
228
dbrx-instruct-preview
-
5.0
442
-
-
229
gemma-1.1-7b-it
Google
4.6
770
-
-
230
mixtral-8x7b-instruct-v0.1
Mistral
4.2
778
32K
¥5.04 / ¥5.04Input/Output
231
llama-2-70b-chat
Meta
3.8
243
-
-
232
yi-34b-chat
-
3.3
227
-
-
233
phi-3-medium-4k-instruct
Microsoft
2.9
732
4.1K
¥1.22 / ¥4.9Input/Output
234
llama-2-13b-chat
Meta
2.5
172
-
-
235
snowflake-arctic-instruct
-
2.1
547
-
-
236
phi-3-mini-4k-instruct
Microsoft
1.7
860
4.1K
¥0.94 / ¥3.74Input/Output
237
gemma-1.1-2b-it
Google
1.3
386
-
-
238
phi-3-small-8k-instruct
Microsoft
0.8
726
8.19K
¥1.08 / ¥4.32Input/Output
239
phi-3-mini-4k-instruct-june-2024
Microsoft
0.4
292
4.1K
¥0.94 / ¥3.74Input/Output
240
phi-3-mini-128k-instruct
Microsoft
0.0
260
128K
¥0.94 / ¥3.74Input/Output
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 192 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

韩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。

韩语模型应该怎么选?

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。