Chat · Text · Spanish Leaderboard

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

Selection guide

Spanish model ranking guide

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

claude-opus-4-6-thinkingclaude-opus-4-6gemini-3.1-pro-previewclaude-opus-4-7-thinkingernie-5.0-preview-1203
Current DirectoryChat · Text · Spanish
Models248
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / SpanishPublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
claude-opus-4-6-thinking
Anthropic
100.0
1.1K
1M
¥36 / ¥180Input/Output
2
claude-opus-4-6
Anthropic
99.6
1.2K
1M
¥36 / ¥180Input/Output
3
gemini-3.1-pro-preview
Google
99.2
1.5K
1.05M
¥14.4 / ¥86.4Input/Output
4
claude-opus-4-7-thinking
Anthropic
98.8
681
1M
¥36 / ¥180Input/Output
5
ernie-5.0-preview-1203
Baidu
98.4
217
128K
¥7.92 / ¥14.4Input/Output
6
mimo-v2.5-pro
Xiaomi
98.0
511
1.05M
¥7.2 / ¥21.6Input/Output
7
gpt-5.5-high
Openai
97.6
456
1.05M
¥36 / ¥216Input/Output
8
gemini-3.5-flash
Google
97.2
333
1.05M
¥10.8 / ¥64.8Input/Output
9
gemini-2.5-pro
Google
96.8
2.9K
1.05M
¥9 / ¥72Input/Output
10
gemini-3-pro
Google
96.4
1K
1.05M
¥14.4 / ¥86.4Input/Output
11
ernie-5.1
Baidu
96.0
475
119K
¥5.4 / ¥21.6Input/Output
12
muse-spark
Meta
95.5
431
-
-
13
kimi-k2.5-thinking
Moonshot
95.1
1.2K
262K
¥4.32 / ¥21.6Input/Output
14
qwen3.5-max-preview
Alibaba
94.7
673
-
-
15
dola-seed-2.0-pro
Bytedance
94.3
1.2K
-
-
16
mimo-v2-pro
Xiaomi
93.9
692
1.05M
¥7.2 / ¥21.6Input/Output
17
claude-sonnet-4-6
Anthropic
93.5
861
1M
¥21.6 / ¥108Input/Output
18
claude-opus-4-7
Anthropic
93.1
732
1M
¥36 / ¥180Input/Output
19
glm-5.1
Zai
92.7
464
200K
¥0 / ¥0Input/Output
20
qwen3-max-preview
Alibaba
92.3
752
262K
¥6.2 / ¥24.8Input/Output
21
gemini-3-flash
Google
91.9
834
1.05M
¥3.6 / ¥21.6Input/Output
22
gpt-5.4
Openai
91.5
843
1.05M
¥18 / ¥108Input/Output
23
gpt-5.5
Openai
91.1
526
1.05M
¥36 / ¥216Input/Output
24
gpt-5.4-high
Openai
90.7
929
1.05M
¥18 / ¥108Input/Output
25
gemma-4-31b
Google
90.3
224
262K
¥3.24 / ¥7.2Input/Output
26
claude-sonnet-4-5-20250929
Anthropic
89.9
2K
200K
¥21.6 / ¥108Input/Output
27
qwen3.5-397b-a17b
Alibaba
89.5
1K
262K
¥3.1 / ¥18.6Input/Output
28
kimi-k2.6
Moonshot
89.1
569
262K
¥6.84 / ¥28.8Input/Output
29
claude-opus-4-5-20251101-thinking-32k
Anthropic
88.7
984
200K
¥108 / ¥540Input/Output
30
claude-opus-4-5-20251101
Anthropic
88.3
1.8K
200K
¥36 / ¥180Input/Output
31
glm-4.5
Zai
87.9
623
131K
¥4.32 / ¥15.8Input/Output
32
qwen3.6-max-preview
Alibaba
87.4
224
246K
¥9.5 / ¥56.9Input/Output
33
qwen3-next-80b-a3b-instruct
Alibaba
87.0
615
131K
¥1.04 / ¥4.13Input/Output
34
mistral-large-3
Mistral
86.6
1.1K
262K
¥3.6 / ¥10.8Input/Output
35
ernie-5.0-0110
Baidu
86.2
1.1K
128K
¥7.92 / ¥14.4Input/Output
36
kimi-k2.5-instant
Moonshot
85.8
261
262K
¥4.32 / ¥21.6Input/Output
37
claude-opus-4-1-20250805-thinking-16k
Anthropic
85.4
1.1K
200K
¥108 / ¥540Input/Output
38
claude-opus-4-1-20250805
Anthropic
85.0
2K
200K
¥108 / ¥540Input/Output
39
longcat-flash-chat
Meituan
84.6
364
128K
¥1.08 / ¥10.8Input/Output
40
grok-4.20-beta1
Xai
84.2
768
2M
¥14.4 / ¥43.2Input/Output
41
deepseek-v4-pro
Deepseek
83.8
504
1M
¥3.13 / ¥6.26Input/Output
42
grok-4.20-beta-0309-reasoning
Xai
83.4
902
2M
¥14.4 / ¥43.2Input/Output
43
deepseek-v3.2-exp
Deepseek
83.0
301
128K
¥0 / ¥0Input/Output
44
qwen3.6-plus
Alibaba
82.6
637
1M
¥3.6 / ¥21.6Input/Output
45
deepseek-v4-flash
Deepseek
82.2
482
1M
¥1.01 / ¥2.02Input/Output
46
grok-4.1-thinking
Xai
81.8
1.6K
200K
¥14.4 / ¥72Input/Output
47
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
81.4
2.1K
200K
¥21.6 / ¥108Input/Output
48
glm-4.6
Zai
81.0
881
205K
¥4.32 / ¥15.8Input/Output
49
chatgpt-4o-latest-20250326
Openai
80.6
1.7K
128K
¥18 / ¥72Input/Output
50
gpt-5.1-high
Openai
80.2
965
400K
¥9 / ¥72Input/Output
51
glm-5
Zai
79.8
781
205K
¥7.2 / ¥23Input/Output
52
gpt-5.2-chat-latest-20260210
Openai
79.4
954
400K
¥12.6 / ¥101Input/Output
53
amazon-nova-experimental-chat-11-10
Amazon
78.9
614
-
-
54
grok-4.20-multi-agent-beta-0309
Xai
78.5
826
2M
¥14.4 / ¥43.2Input/Output
55
deepseek-v4-pro-thinking
Deepseek
78.1
480
1M
¥3.13 / ¥6.26Input/Output
56
gemini-3.1-flash-lite-preview
Google
77.7
1.1K
1.05M
¥1.8 / ¥10.8Input/Output
57
mistral-medium-2508
Mistral
77.3
2.4K
262K
¥2.88 / ¥14.4Input/Output
58
qwen3.5-122b-a10b
Alibaba
76.9
778
262K
¥2.88 / ¥23Input/Output
59
qwen3-235b-a22b-instruct-2507
Alibaba
76.5
2.5K
128K
¥2.09 / ¥8.23Input/Output
60
gpt-5.5-instant
Openai
76.1
727
400K
¥9 / ¥72Input/Output
61
gemini-3-flash (thinking-minimal)
Google
75.7
1.5K
1.05M
¥3.6 / ¥21.6Input/Output
62
gpt-5.1
Openai
75.3
1.1K
400K
¥9 / ¥72Input/Output
63
deepseek-v4-flash-thinking
Deepseek
74.9
453
1M
¥1.01 / ¥2.02Input/Output
64
grok-4.1
Xai
74.5
1.6K
200K
¥14.4 / ¥72Input/Output
65
grok-4-fast-chat
Xai
74.1
244
2M
¥1.44 / ¥3.6Input/Output
66
deepseek-v3.2
Deepseek
73.7
1.2K
128K
¥2.09 / ¥3.1Input/Output
67
gemini-2.5-flash
Google
73.3
2.9K
1.05M
¥2.16 / ¥18Input/Output
68
claude-haiku-4-5-20251001
Anthropic
72.9
2K
200K
¥7.2 / ¥36Input/Output
69
mimo-v2-flash (non-thinking)
Xiaomi
72.5
1.2K
262K
¥0.72 / ¥2.16Input/Output
70
step-3.5-flash
Stepfun
72.1
1.1K
256K
¥0.69 / ¥2.07Input/Output
71
glm-4.7
Zai
71.7
315
205K
¥0 / ¥0Input/Output
72
nvidia-nemotron-3-super-120b-a12b
Nvidia
71.3
314
262K
¥1.44 / ¥5.76Input/Output
73
minimax-m2.7
Minimax
70.9
737
205K
¥0 / ¥0Input/Output
74
grok-3-preview-02-24
Xai
70.4
345
1M
¥9 / ¥18Input/Output
75
longcat-flash-chat-2602-exp
Meituan
70.0
686
128K
¥1.08 / ¥10.8Input/Output
76
mimo-v2.5
Xiaomi
69.6
492
1.05M
¥2.88 / ¥14.4Input/Output
77
grok-4-0709
Xai
69.2
912
256K
¥21.6 / ¥108Input/Output
78
grok-4-1-fast-reasoning
Xai
68.8
1.4K
2M
¥1.44 / ¥3.6Input/Output
79
qwen3.5-flash
Alibaba
68.4
960
1M
¥1.24 / ¥12.4Input/Output
80
gpt-5.2-high
Openai
68.0
1.2K
400K
¥12.6 / ¥101Input/Output
81
deepseek-v3.1
Deepseek
67.6
362
128K
¥1.44 / ¥5.04Input/Output
82
deepseek-v3.2-thinking
Deepseek
67.2
1.1K
128K
¥2.09 / ¥3.1Input/Output
83
grok-4-fast-reasoning
Xai
66.8
521
2M
¥1.44 / ¥3.6Input/Output
84
kimi-k2-thinking-turbo
Moonshot
66.4
1.6K
262K
¥17.3 / ¥72Input/Output
85
qwen3.5-27b
Alibaba
66.0
776
262K
¥2.16 / ¥17.3Input/Output
86
gpt-5.4-mini-high
Openai
65.6
736
400K
¥5.4 / ¥32.4Input/Output
87
qwen3-vl-235b-a22b-instruct
Alibaba
65.2
406
128K
¥2.16 / ¥8.64Input/Output
88
deepseek-v3.1-thinking
Deepseek
64.8
353
128K
¥1.44 / ¥5.04Input/Output
89
deepseek-r1-0528
Deepseek
64.4
230
164K
¥3.6 / ¥15.5Input/Output
90
qwen3-235b-a22b-no-thinking
Alibaba
64.0
677
131K
¥2.07 / ¥8.26Input/Output
91
ling-flash-2.0
Ant Group
63.6
241
131K
¥1.01 / ¥4.1Input/Output
92
minimax-m2.1-preview
Minimax
63.2
410
205K
¥0 / ¥0Input/Output
93
gpt-5.2
Openai
62.8
1.3K
400K
¥12.6 / ¥101Input/Output
94
grok-4.3
Xai
62.3
435
1M
¥9 / ¥18Input/Output
95
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
61.9
1.3K
1.05M
¥0.72 / ¥2.88Input/Output
96
gemini-2.5-flash-preview-09-2025
Google
61.5
850
1M
¥2.16 / ¥18Input/Output
97
qwen3-max-2025-09-23
Alibaba
61.1
388
258K
¥6.19 / ¥24.7Input/Output
98
hunyuan-hy3-preview
Tencent
60.7
170
256K
¥0 / ¥0Input/Output
99
qwen3.5-35b-a3b
Alibaba
60.3
810
262K
¥1.8 / ¥14.4Input/Output
100
qwen3-30b-a3b-instruct-2507
Alibaba
59.9
633
262K
¥2.16 / ¥3.6Input/Output
101
qwen3-235b-a22b-thinking-2507
Alibaba
59.5
154
131K
¥2.07 / ¥8.26Input/Output
102
gpt-5-chat
Openai
59.1
770
400K
¥9 / ¥72Input/Output
103
mimo-v2-flash (thinking)
Xiaomi
58.7
321
262K
¥0.72 / ¥2.16Input/Output
104
deepseek-v3.2-exp-thinking
Deepseek
58.3
279
128K
¥0 / ¥0Input/Output
105
qwen3-vl-235b-a22b-thinking
Alibaba
57.9
331
131K
¥2.06 / ¥8.26Input/Output
106
gpt-oss-120b
Openai
57.5
759
131K
¥1.08 / ¥4.32Input/Output
107
grok-3-mini-beta
Xai
57.1
399
1M
¥9 / ¥18Input/Output
108
o3-2025-04-16
Openai
56.7
1.1K
200K
¥14.4 / ¥57.6Input/Output
109
ring-flash-2.0
Ant Group
56.3
273
131K
¥1.01 / ¥4.1Input/Output
110
kimi-k2-0905-preview
Moonshot
55.9
332
262K
¥4.32 / ¥18Input/Output
111
step-3
Stepfun
55.5
194
65.5K
¥1.8 / ¥4.68Input/Output
112
gpt-5-high
Openai
55.1
817
400K
¥9 / ¥72Input/Output
113
claude-opus-4-20250514-thinking-16k
Anthropic
54.7
766
200K
¥108 / ¥540Input/Output
114
qwen2.5-max
Alibaba
54.3
249
32K
¥11.5 / ¥46Input/Output
115
deepseek-r1
Deepseek
53.8
114
164K
¥5.04 / ¥18Input/Output
116
glm-4.5-air
Zai
53.4
724
131K
¥0 / ¥0Input/Output
117
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
53.0
328
131K
¥0 / ¥0Input/Output
118
gpt-4.1-2025-04-14
Openai
52.6
986
1.05M
¥14.4 / ¥57.6Input/Output
119
gpt-5.3-chat-latest
Openai
52.2
1.1K
128K
¥12.6 / ¥101Input/Output
120
amazon-nova-experimental-chat-10-20
Amazon
51.8
272
-
-
121
gpt-5-nano-high
Openai
51.4
206
400K
¥0.36 / ¥2.88Input/Output
122
mistral-medium-2505
Mistral
51.0
500
262K
¥2.88 / ¥14.4Input/Output
123
qwen3-235b-a22b
Alibaba
50.6
421
131K
¥2.07 / ¥8.26Input/Output
124
gemini-2.5-flash-lite-preview-06-17-thinking
Google
50.2
713
65.5K
¥0.72 / ¥2.88Input/Output
125
gpt-5.4-nano-high
Openai
49.8
754
400K
¥1.44 / ¥9Input/Output
126
gemini-2.0-flash-001
Google
49.4
517
1.05M
¥1.08 / ¥4.32Input/Output
127
nova-2-lite
Amazon
49.0
201
128K
¥2.38 / ¥19.8Input/Output
128
gpt-5-mini-high
Openai
48.6
741
400K
¥1.8 / ¥14.4Input/Output
129
glm-4.7-flash
Zai
48.2
337
200K
¥0 / ¥0Input/Output
130
grok-3-mini-high
Xai
47.8
292
128K
¥0 / ¥0Input/Output
131
minimax-m2.5
Minimax
47.4
1.1K
205K
¥0 / ¥0Input/Output
132
qwen3-coder-480b-a35b-instruct
Alibaba
47.0
602
262K
¥6.2 / ¥24.8Input/Output
133
claude-sonnet-4-20250514-thinking-32k
Anthropic
46.6
737
200K
¥21.6 / ¥108Input/Output
134
claude-sonnet-4-20250514
Anthropic
46.2
782
200K
¥21.6 / ¥108Input/Output
135
claude-opus-4-20250514
Anthropic
45.7
872
200K
¥108 / ¥540Input/Output
136
deepseek-v3
Deepseek
45.3
127
128K
¥0 / ¥0Input/Output
137
trinity-large-preview
-
44.9
839
262K
¥1.8 / ¥6.48Input/Output
138
qwen3-next-80b-a3b-thinking
Alibaba
44.5
398
131K
¥1.04 / ¥10.3Input/Output
139
mistral-small-2506
Mistral
44.1
365
262K
¥2.88 / ¥14.4Input/Output
140
deepseek-v3-0324
Deepseek
43.7
893
75K
¥1.44 / ¥5.76Input/Output
141
o4-mini-2025-04-16
Openai
43.3
876
200K
¥7.92 / ¥31.7Input/Output
142
qwq-32b
Alibaba
42.9
348
131K
¥2.07 / ¥6.2Input/Output
143
gemma-3-27b-it
Google
42.5
775
128K
¥2.15 / ¥2.15Input/Output
144
o1-2024-12-17
Openai
42.1
142
128K
¥108 / ¥432Input/Output
145
minimax-m1
Minimax
41.7
716
1M
¥0.95 / ¥9.03Input/Output
146
olmo-3.1-32b-instruct
Allenai
41.3
338
200K
¥14.4 / ¥57.6Input/Output
147
trinity-large-thinking
-
40.9
724
262K
¥1.8 / ¥6.48Input/Output
148
command-a-03-2025
Cohere
40.5
1K
256K
¥18 / ¥72Input/Output
149
glm-4.5v
Zai
40.1
177
64K
¥4.32 / ¥13Input/Output
150
kimi-k2-0711-preview
Moonshot
39.7
532
131K
¥4.32 / ¥18Input/Output
151
minimax-m2
Minimax
39.3
173
197K
¥0 / ¥0Input/Output
152
qwen3-30b-a3b
Alibaba
38.9
410
128K
¥0.79 / ¥7.78Input/Output
153
o3-mini-high
Openai
38.5
126
200K
¥7.92 / ¥31.7Input/Output
154
yi-lightning
-
38.1
341
12K
¥1.44 / ¥1.44Input/Output
155
gemini-2.0-flash-lite-preview-02-05
Google
37.7
157
1.05M
¥0.54 / ¥2.16Input/Output
156
glm-4-plus
Zai
37.2
332
128K
¥54 / ¥54Input/Output
157
gemini-1.5-pro-002
Google
36.8
405
-
-
158
gpt-4.1-mini-2025-04-14
Openai
36.4
721
1.05M
¥2.88 / ¥11.5Input/Output
159
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
36.0
550
-
-
160
o1-mini
Openai
35.6
425
128K
¥7.92 / ¥31.7Input/Output
161
o1-preview
Openai
35.2
347
128K
¥108 / ¥432Input/Output
162
o3-mini
Openai
34.8
837
200K
¥7.92 / ¥31.7Input/Output
163
gemma-3n-e4b-it
Google
34.4
408
128K
¥0 / ¥0Input/Output
164
gpt-4o-2024-05-13
Openai
34.0
1.7K
128K
¥36 / ¥108Input/Output
165
olmo-3.1-32b-think
Allenai
33.6
177
200K
¥14.4 / ¥57.6Input/Output
166
qwen-max-0919
Alibaba
33.2
222
131K
¥2.48 / ¥9.91Input/Output
167
claude-3-7-sonnet-20250219
Anthropic
32.8
560
200K
¥21.6 / ¥108Input/Output
168
claude-3-5-sonnet-20240620
Anthropic
32.4
1.1K
200K
¥21.6 / ¥108Input/Output
169
llama-4-maverick-17b-128e-instruct
Meta
32.0
746
1M
¥1.8 / ¥6.26Input/Output
170
claude-3-5-sonnet-20241022
Anthropic
31.6
918
200K
¥21.6 / ¥108Input/Output
171
mistral-small-3.1-24b-instruct-2503
Mistral
31.2
703
262K
¥2.88 / ¥14.4Input/Output
172
grok-2-2024-08-13
Xai
30.8
671
1M
¥9 / ¥18Input/Output
173
gpt-4o-mini-2024-07-18
Openai
30.4
740
128K
¥1.08 / ¥4.32Input/Output
174
grok-2-mini-2024-08-13
Xai
30.0
575
1M
¥9 / ¥18Input/Output
175
magistral-medium-2506
Mistral
29.6
232
128K
¥14.4 / ¥36Input/Output
176
athene-v2-chat
-
29.1
180
-
-
177
gpt-4o-2024-08-06
Openai
28.7
546
128K
¥18 / ¥72Input/Output
178
gpt-oss-20b
Openai
28.3
253
131K
¥0.32 / ¥1.3Input/Output
179
llama-4-scout-17b-16e-instruct
Meta
27.9
638
128K
¥1.44 / ¥5.62Input/Output
180
llama-3.3-70b-instruct
Meta
27.5
590
128K
¥0 / ¥0Input/Output
181
mistral-large-2411
Mistral
27.1
153
128K
¥14.4 / ¥43.2Input/Output
182
gpt-4-1106-preview
Openai
26.7
1.5K
8.19K
¥216 / ¥432Input/Output
183
gpt-4-turbo-2024-04-09
Openai
26.3
1.4K
128K
¥72 / ¥216Input/Output
184
ibm-granite-h-small
Ibm
25.9
168
-
-
185
athene-70b-0725
-
25.5
271
-
-
186
llama-3.1-405b-instruct-bf16
Meta
25.1
348
128K
¥0 / ¥0Input/Output
187
qwen2.5-72b-instruct
Alibaba
24.7
347
131K
¥4.13 / ¥12.4Input/Output
188
llama-3.1-405b-instruct-fp8
Meta
24.3
652
128K
¥0 / ¥0Input/Output
189
llama-3.1-70b-instruct
Meta
23.9
606
131K
¥2.88 / ¥2.88Input/Output
190
claude-3-5-haiku-20241022
Anthropic
23.5
883
200K
¥5.76 / ¥28.8Input/Output
191
deepseek-v2.5
Deepseek
23.1
293
1M
¥1.01 / ¥2.02Input/Output
192
gpt-4-0125-preview
Openai
22.7
1.2K
8.19K
¥216 / ¥432Input/Output
193
claude-3-opus-20240229
Anthropic
22.3
2.6K
200K
¥108 / ¥540Input/Output
194
gemini-1.5-pro-001
Google
21.9
1.3K
-
-
195
gemini-advanced-0514
Google
21.5
898
-
-
196
gemini-1.5-flash-002
Google
21.1
283
2M
¥0.54 / ¥2.2Input/Output
197
llama-3-70b-instruct
Meta
20.6
2.7K
8.19K
¥3.67 / ¥5.33Input/Output
198
mistral-large-2407
Mistral
20.2
584
131K
¥14.4 / ¥43.2Input/Output
199
phi-4
Microsoft
19.8
127
128K
¥0.9 / ¥3.6Input/Output
200
gemma-2-27b-it
Google
19.4
845
8.19K
¥0.58 / ¥0.58Input/Output
201
gemini-1.5-flash-001
Google
19.0
1.1K
2M
¥0.54 / ¥2.2Input/Output
202
amazon-nova-lite-v1.0
Amazon
18.6
107
300K
¥0.43 / ¥1.73Input/Output
203
amazon-nova-micro-v1.0
Amazon
18.2
144
128K
¥0.25 / ¥1.01Input/Output
204
gemini-1.5-flash-8b-001
Google
17.8
323
2M
¥0.54 / ¥2.2Input/Output
205
claude-3-sonnet-20240229
Anthropic
17.4
1.4K
200K
¥21.6 / ¥108Input/Output
206
gemma-2-9b-it
Google
17.0
614
8.19K
¥1.44 / ¥1.44Input/Output
207
gpt-4-0314
Openai
16.6
647
8.19K
¥216 / ¥432Input/Output
208
nemotron-4-340b-instruct
Nvidia
16.2
367
-
-
209
mistral-large-2402
Mistral
15.8
886
262K
¥2.88 / ¥14.4Input/Output
210
c4ai-aya-expanse-32b
Cohere
15.4
256
-
-
211
command-r-plus
Cohere
15.0
1.2K
128K
¥18 / ¥72Input/Output
212
amazon-nova-pro-v1.0
Amazon
14.6
150
300K
¥5.76 / ¥23Input/Output
213
llama-3-8b-instruct
Meta
14.2
1.7K
8.19K
¥0.29 / ¥0.29Input/Output
214
llama-3.1-8b-instruct
Meta
13.8
565
131K
¥0.79 / ¥0.79Input/Output
215
qwen2-72b-instruct
Alibaba
13.4
596
131K
¥4.13 / ¥12.4Input/Output
216
gpt-4-0613
Openai
13.0
1.4K
8.19K
¥216 / ¥432Input/Output
217
claude-3-haiku-20240307
Anthropic
12.6
1.7K
200K
¥1.8 / ¥9Input/Output
218
deepseek-coder-v2
Deepseek
12.1
245
1M
¥1.01 / ¥2.02Input/Output
219
command-r
Cohere
11.7
698
128K
¥18 / ¥72Input/Output
220
mixtral-8x22b-instruct-v0.1
Mistral
11.3
826
64K
¥14.4 / ¥43.2Input/Output
221
reka-flash-21b-20240226-online
-
10.9
217
-
-
222
mistral-medium
Mistral
10.5
439
262K
¥2.88 / ¥14.4Input/Output
223
llama-2-70b-chat
Meta
10.1
506
-
-
224
qwen1.5-110b-chat
Alibaba
9.7
487
-
-
225
gemma-2-2b-it
Google
9.3
544
128K
¥0 / ¥0Input/Output
226
reka-flash-21b-20240226
-
8.9
409
-
-
227
yi-1.5-34b-chat
-
8.5
458
-
-
228
gpt-3.5-turbo-0125
Openai
8.1
895
16.4K
¥3.6 / ¥10.8Input/Output
229
gemini-pro-dev-api
Google
7.7
213
1.05M
¥14.4 / ¥86.4Input/Output
230
phi-3-small-8k-instruct
Microsoft
7.3
272
8.19K
¥1.08 / ¥4.32Input/Output
231
mixtral-8x7b-instruct-v0.1
Mistral
6.9
1.1K
32K
¥5.04 / ¥5.04Input/Output
232
qwen1.5-72b-chat
Alibaba
6.5
501
-
-
233
phi-3-medium-4k-instruct
Microsoft
6.1
419
4.1K
¥1.22 / ¥4.9Input/Output
234
gpt-3.5-turbo-1106
Openai
5.7
260
16.4K
¥7.2 / ¥14.4Input/Output
235
qwen1.5-32b-chat
Alibaba
5.3
369
-
-
236
snowflake-arctic-instruct
-
4.9
500
-
-
237
llama-2-13b-chat
Meta
4.5
262
-
-
238
qwen1.5-14b-chat
Alibaba
4.0
293
-
-
239
phi-3-mini-4k-instruct
Microsoft
3.6
410
4.1K
¥0.94 / ¥3.74Input/Output
240
vicuna-33b
-
3.2
275
-
-
241
vicuna-13b
-
2.8
161
-
-
242
zephyr-7b-beta
-
2.4
127
-
-
243
yi-34b-chat
-
2.0
218
-
-
244
dbrx-instruct-preview
-
1.6
404
-
-
245
phi-3-mini-128k-instruct
Microsoft
1.2
366
128K
¥0.94 / ¥3.74Input/Output
246
gemma-1.1-7b-it
Google
0.8
411
-
-
247
mistral-7b-instruct-v0.2
Mistral
0.4
202
262K
¥2.88 / ¥14.4Input/Output
248
llama-2-7b-chat
Meta
0.0
143
128K
¥4.03 / ¥48Input/Output
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 1.1K 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

西班牙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。

西班牙语模型应该怎么选?

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。