Chat · Text · French Leaderboard

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

Selection guide

French model ranking guide

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

gpt-5.5claude-opus-4-7claude-opus-4-6-thinkingernie-5.1muse-spark
Current DirectoryChat · Text · French
Models245
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / FrenchPublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
gpt-5.5
Openai
100.0
581
1.05M
¥36 / ¥216Input/Output
2
claude-opus-4-7
Anthropic
99.6
690
1M
¥36 / ¥180Input/Output
3
claude-opus-4-6-thinking
Anthropic
99.2
936
1M
¥36 / ¥180Input/Output
4
ernie-5.1
Baidu
98.8
528
119K
¥5.4 / ¥21.6Input/Output
5
muse-spark
Meta
98.4
391
-
-
6
claude-opus-4-6
Anthropic
98.0
1K
1M
¥36 / ¥180Input/Output
7
gpt-5.4-high
Openai
97.5
905
1.05M
¥18 / ¥108Input/Output
8
gpt-5.5-high
Openai
97.1
587
1.05M
¥36 / ¥216Input/Output
9
claude-opus-4-7-thinking
Anthropic
96.7
625
1M
¥36 / ¥180Input/Output
10
gemini-3-pro
Google
96.3
891
1.05M
¥14.4 / ¥86.4Input/Output
11
gemini-3-flash
Google
95.9
754
1.05M
¥3.6 / ¥21.6Input/Output
12
gemini-3.1-pro-preview
Google
95.5
1.3K
1.05M
¥14.4 / ¥86.4Input/Output
13
mimo-v2.5-pro
Xiaomi
95.1
537
1.05M
¥7.2 / ¥21.6Input/Output
14
grok-4.20-beta-0309-reasoning
Xai
94.7
809
2M
¥14.4 / ¥43.2Input/Output
15
claude-opus-4-5-20251101
Anthropic
94.3
1.7K
200K
¥36 / ¥180Input/Output
16
qwen3.5-max-preview
Alibaba
93.9
631
-
-
17
mistral-large-3
Mistral
93.4
976
262K
¥3.6 / ¥10.8Input/Output
18
glm-5.1
Zai
93.0
454
200K
¥0 / ¥0Input/Output
19
qwen3.6-plus
Alibaba
92.6
628
1M
¥3.6 / ¥21.6Input/Output
20
gemini-2.5-pro
Google
92.2
2.1K
1.05M
¥9 / ¥72Input/Output
21
dola-seed-2.0-pro
Bytedance
91.8
1K
-
-
22
kimi-k2.6
Moonshot
91.4
543
262K
¥6.84 / ¥28.8Input/Output
23
grok-4.20-multi-agent-beta-0309
Xai
91.0
850
2M
¥14.4 / ¥43.2Input/Output
24
glm-5
Zai
90.6
641
205K
¥7.2 / ¥23Input/Output
25
grok-3-preview-02-24
Xai
90.2
359
1M
¥9 / ¥18Input/Output
26
mimo-v2-pro
Xiaomi
89.8
785
1.05M
¥7.2 / ¥21.6Input/Output
27
gemma-4-26b-a4b
Google
89.3
214
262K
¥0.94 / ¥2.88Input/Output
28
ernie-5.0-0110
Baidu
88.9
906
128K
¥7.92 / ¥14.4Input/Output
29
ernie-5.0-preview-1203
Baidu
88.5
228
128K
¥7.92 / ¥14.4Input/Output
30
glm-4.6
Zai
88.1
639
205K
¥4.32 / ¥15.8Input/Output
31
mistral-medium-2508
Mistral
87.7
1.8K
262K
¥2.88 / ¥14.4Input/Output
32
claude-sonnet-4-6
Anthropic
87.3
738
1M
¥21.6 / ¥108Input/Output
33
longcat-flash-chat
Meituan
86.9
164
128K
¥1.08 / ¥10.8Input/Output
34
qwen3-max-preview
Alibaba
86.5
396
262K
¥6.2 / ¥24.8Input/Output
35
qwen3-vl-235b-a22b-instruct
Alibaba
86.1
234
128K
¥2.16 / ¥8.64Input/Output
36
kimi-k2.5-thinking
Moonshot
85.7
1K
262K
¥4.32 / ¥21.6Input/Output
37
claude-opus-4-5-20251101-thinking-32k
Anthropic
85.2
766
200K
¥108 / ¥540Input/Output
38
gpt-5.4
Openai
84.8
900
1.05M
¥18 / ¥108Input/Output
39
qwen3.5-397b-a17b
Alibaba
84.4
900
262K
¥3.1 / ¥18.6Input/Output
40
deepseek-v3.1
Deepseek
84.0
248
128K
¥1.44 / ¥5.04Input/Output
41
gemini-3.5-flash
Google
83.6
308
1.05M
¥10.8 / ¥64.8Input/Output
42
gpt-5.1-high
Openai
83.2
862
400K
¥9 / ¥72Input/Output
43
grok-4.1-thinking
Xai
82.8
1.5K
200K
¥14.4 / ¥72Input/Output
44
claude-sonnet-4-5-20250929
Anthropic
82.4
1.6K
200K
¥21.6 / ¥108Input/Output
45
gemini-3-flash (thinking-minimal)
Google
82.0
1.4K
1.05M
¥3.6 / ¥21.6Input/Output
46
gpt-5.2-high
Openai
81.6
1.2K
400K
¥12.6 / ¥101Input/Output
47
qwen3-235b-a22b-instruct-2507
Alibaba
81.1
1.9K
128K
¥2.09 / ¥8.23Input/Output
48
amazon-nova-experimental-chat-11-10
Amazon
80.7
567
-
-
49
deepseek-v4-pro
Deepseek
80.3
600
1M
¥3.13 / ¥6.26Input/Output
50
o3-2025-04-16
Openai
79.9
764
200K
¥14.4 / ¥57.6Input/Output
51
chatgpt-4o-latest-20250326
Openai
79.5
1.3K
128K
¥18 / ¥72Input/Output
52
grok-4.1
Xai
79.1
1.5K
200K
¥14.4 / ¥72Input/Output
53
grok-4.20-beta1
Xai
78.7
695
2M
¥14.4 / ¥43.2Input/Output
54
gpt-5.2
Openai
78.3
1.2K
400K
¥12.6 / ¥101Input/Output
55
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
77.9
1.7K
200K
¥21.6 / ¥108Input/Output
56
deepseek-v4-flash-thinking
Deepseek
77.5
536
1M
¥1.01 / ¥2.02Input/Output
57
gpt-5.2-chat-latest-20260210
Openai
77.0
850
400K
¥12.6 / ¥101Input/Output
58
deepseek-v3.2-exp
Deepseek
76.6
198
128K
¥0 / ¥0Input/Output
59
gemini-2.5-flash-preview-09-2025
Google
76.2
522
1M
¥2.16 / ¥18Input/Output
60
gemma-4-31b
Google
75.8
240
262K
¥3.24 / ¥7.2Input/Output
61
qwen3.5-122b-a10b
Alibaba
75.4
770
262K
¥2.88 / ¥23Input/Output
62
gpt-5.1
Openai
75.0
834
400K
¥9 / ¥72Input/Output
63
claude-opus-4-1-20250805-thinking-16k
Anthropic
74.6
766
200K
¥108 / ¥540Input/Output
64
grok-4-fast-reasoning
Xai
74.2
267
2M
¥1.44 / ¥3.6Input/Output
65
mimo-v2.5
Xiaomi
73.8
566
1.05M
¥2.88 / ¥14.4Input/Output
66
gemini-2.5-flash
Google
73.4
2.3K
1.05M
¥2.16 / ¥18Input/Output
67
deepseek-v3.2
Deepseek
73.0
1.1K
128K
¥2.09 / ¥3.1Input/Output
68
claude-opus-4-1-20250805
Anthropic
72.5
1.3K
200K
¥108 / ¥540Input/Output
69
glm-4.5
Zai
72.1
308
131K
¥4.32 / ¥15.8Input/Output
70
gpt-5.4-mini-high
Openai
71.7
810
400K
¥5.4 / ¥32.4Input/Output
71
mimo-v2-flash (thinking)
Xiaomi
71.3
303
262K
¥0.72 / ¥2.16Input/Output
72
kimi-k2-thinking-turbo
Moonshot
70.9
1.4K
262K
¥17.3 / ¥72Input/Output
73
glm-4.7
Zai
70.5
271
205K
¥0 / ¥0Input/Output
74
step-3.5-flash
Stepfun
70.1
948
256K
¥0.69 / ¥2.07Input/Output
75
amazon-nova-experimental-chat-10-20
Amazon
69.7
224
-
-
76
grok-4-0709
Xai
69.3
544
256K
¥21.6 / ¥108Input/Output
77
minimax-m2.7
Minimax
68.9
803
205K
¥0 / ¥0Input/Output
78
deepseek-v4-flash
Deepseek
68.4
621
1M
¥1.01 / ¥2.02Input/Output
79
gpt-5.5-instant
Openai
68.0
982
400K
¥9 / ¥72Input/Output
80
qwen3-30b-a3b-instruct-2507
Alibaba
67.6
308
262K
¥2.16 / ¥3.6Input/Output
81
longcat-flash-chat-2602-exp
Meituan
67.2
753
128K
¥1.08 / ¥10.8Input/Output
82
deepseek-r1-0528
Deepseek
66.8
207
164K
¥3.6 / ¥15.5Input/Output
83
deepseek-v3.2-thinking
Deepseek
66.4
910
128K
¥2.09 / ¥3.1Input/Output
84
gpt-4.5-preview-2025-02-27
Openai
66.0
121
8.19K
¥216 / ¥432Input/Output
85
gemini-3.1-flash-lite-preview
Google
65.6
1K
1.05M
¥1.8 / ¥10.8Input/Output
86
grok-4-1-fast-reasoning
Xai
65.2
1.2K
2M
¥1.44 / ¥3.6Input/Output
87
qwen3.5-35b-a3b
Alibaba
64.8
731
262K
¥1.8 / ¥14.4Input/Output
88
qwen3-next-80b-a3b-instruct
Alibaba
64.3
347
131K
¥1.04 / ¥4.13Input/Output
89
mimo-v2-flash (non-thinking)
Xiaomi
63.9
1.2K
262K
¥0.72 / ¥2.16Input/Output
90
hunyuan-hy3-preview
Tencent
63.5
178
256K
¥0 / ¥0Input/Output
91
grok-4.3
Xai
63.1
575
1M
¥9 / ¥18Input/Output
92
gpt-5-chat
Openai
62.7
393
400K
¥9 / ¥72Input/Output
93
deepseek-v3.2-exp-thinking
Deepseek
62.3
139
128K
¥0 / ¥0Input/Output
94
glm-4.5-air
Zai
61.9
470
131K
¥0 / ¥0Input/Output
95
nvidia-nemotron-3-super-120b-a12b
Nvidia
61.5
244
262K
¥1.44 / ¥5.76Input/Output
96
gpt-5-high
Openai
61.1
444
400K
¥9 / ¥72Input/Output
97
deepseek-v4-pro-thinking
Deepseek
60.7
574
1M
¥3.13 / ¥6.26Input/Output
98
kimi-k2.5-instant
Moonshot
60.2
153
262K
¥4.32 / ¥21.6Input/Output
99
minimax-m2.1-preview
Minimax
59.8
398
205K
¥0 / ¥0Input/Output
100
qwen3.5-flash
Alibaba
59.4
908
1M
¥1.24 / ¥12.4Input/Output
101
claude-haiku-4-5-20251001
Anthropic
59.0
1.7K
200K
¥7.2 / ¥36Input/Output
102
qwen3.5-27b
Alibaba
58.6
691
262K
¥2.16 / ¥17.3Input/Output
103
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
58.2
341
131K
¥0 / ¥0Input/Output
104
qwen3-coder-480b-a35b-instruct
Alibaba
57.8
408
262K
¥6.2 / ¥24.8Input/Output
105
qwen2.5-max
Alibaba
57.4
328
32K
¥11.5 / ¥46Input/Output
106
gpt-5.3-chat-latest
Openai
57.0
875
128K
¥12.6 / ¥101Input/Output
107
gemini-2.0-flash-001
Google
56.6
506
1.05M
¥1.08 / ¥4.32Input/Output
108
deepseek-v3-0324
Deepseek
56.1
540
75K
¥1.44 / ¥5.76Input/Output
109
gpt-5.4-nano-high
Openai
55.7
775
400K
¥1.44 / ¥9Input/Output
110
gemini-2.5-flash-lite-preview-06-17-thinking
Google
55.3
403
65.5K
¥0.72 / ¥2.88Input/Output
111
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
54.9
769
1.05M
¥0.72 / ¥2.88Input/Output
112
minimax-m1
Minimax
54.5
425
1M
¥0.95 / ¥9.03Input/Output
113
deepseek-v3.1-thinking
Deepseek
54.1
172
128K
¥1.44 / ¥5.04Input/Output
114
claude-opus-4-20250514-thinking-16k
Anthropic
53.7
470
200K
¥108 / ¥540Input/Output
115
gpt-4.1-2025-04-14
Openai
53.3
691
1.05M
¥14.4 / ¥57.6Input/Output
116
hunyuan-turbos-20250416
Tencent
52.9
144
131K
¥0 / ¥0Input/Output
117
gpt-5-mini-high
Openai
52.5
368
400K
¥1.8 / ¥14.4Input/Output
118
trinity-large-thinking
-
52.0
768
262K
¥1.8 / ¥6.48Input/Output
119
kimi-k2-0905-preview
Moonshot
51.6
184
262K
¥4.32 / ¥18Input/Output
120
trinity-large-preview
-
51.2
746
262K
¥1.8 / ¥6.48Input/Output
121
nova-2-lite
Amazon
50.8
225
128K
¥2.38 / ¥19.8Input/Output
122
qwen3-235b-a22b-no-thinking
Alibaba
50.4
472
131K
¥2.07 / ¥8.26Input/Output
123
gpt-oss-120b
Openai
50.0
405
131K
¥1.08 / ¥4.32Input/Output
124
mistral-medium-2505
Mistral
49.6
454
262K
¥2.88 / ¥14.4Input/Output
125
gemma-3-27b-it
Google
49.2
600
128K
¥2.15 / ¥2.15Input/Output
126
kimi-k2-0711-preview
Moonshot
48.8
364
131K
¥4.32 / ¥18Input/Output
127
qwen3-235b-a22b
Alibaba
48.4
326
131K
¥2.07 / ¥8.26Input/Output
128
deepseek-r1
Deepseek
48.0
188
164K
¥5.04 / ¥18Input/Output
129
minimax-m2.5
Minimax
47.5
1K
205K
¥0 / ¥0Input/Output
130
claude-opus-4-20250514
Anthropic
47.1
580
200K
¥108 / ¥540Input/Output
131
claude-sonnet-4-20250514
Anthropic
46.7
529
200K
¥21.6 / ¥108Input/Output
132
o4-mini-2025-04-16
Openai
46.3
564
200K
¥7.92 / ¥31.7Input/Output
133
claude-sonnet-4-20250514-thinking-32k
Anthropic
45.9
425
200K
¥21.6 / ¥108Input/Output
134
grok-3-mini-beta
Xai
45.5
273
1M
¥9 / ¥18Input/Output
135
qwen3-next-80b-a3b-thinking
Alibaba
45.1
195
131K
¥1.04 / ¥10.3Input/Output
136
gpt-4.1-mini-2025-04-14
Openai
44.7
532
1.05M
¥2.88 / ¥11.5Input/Output
137
qwen3-30b-a3b
Alibaba
44.3
322
128K
¥0.79 / ¥7.78Input/Output
138
command-a-03-2025
Cohere
43.9
692
256K
¥18 / ¥72Input/Output
139
grok-3-mini-high
Xai
43.4
162
128K
¥0 / ¥0Input/Output
140
gemini-2.0-flash-lite-preview-02-05
Google
43.0
253
1.05M
¥0.54 / ¥2.16Input/Output
141
glm-4.7-flash
Zai
42.6
238
200K
¥0 / ¥0Input/Output
142
o1-2024-12-17
Openai
42.2
252
128K
¥108 / ¥432Input/Output
143
o1-preview
Openai
41.8
290
128K
¥108 / ¥432Input/Output
144
deepseek-v3
Deepseek
41.4
242
128K
¥0 / ¥0Input/Output
145
mistral-small-2506
Mistral
41.0
222
262K
¥2.88 / ¥14.4Input/Output
146
qwq-32b
Alibaba
40.6
286
131K
¥2.07 / ¥6.2Input/Output
147
o3-mini-high
Openai
40.2
203
200K
¥7.92 / ¥31.7Input/Output
148
athene-v2-chat
-
39.8
228
-
-
149
olmo-3.1-32b-instruct
Allenai
39.3
327
200K
¥14.4 / ¥57.6Input/Output
150
qwen-max-0919
Alibaba
38.9
183
131K
¥2.48 / ¥9.91Input/Output
151
gemma-3n-e4b-it
Google
38.5
295
128K
¥0 / ¥0Input/Output
152
mistral-large-2411
Mistral
38.1
204
128K
¥14.4 / ¥43.2Input/Output
153
o3-mini
Openai
37.7
656
200K
¥7.92 / ¥31.7Input/Output
154
grok-2-2024-08-13
Xai
37.3
604
1M
¥9 / ¥18Input/Output
155
glm-4-plus
Zai
36.9
286
128K
¥54 / ¥54Input/Output
156
gemini-advanced-0514
Google
36.5
754
-
-
157
yi-lightning
-
36.1
270
12K
¥1.44 / ¥1.44Input/Output
158
gpt-4o-2024-05-13
Openai
35.7
1.4K
128K
¥36 / ¥108Input/Output
159
claude-3-7-sonnet-20250219
Anthropic
35.2
505
200K
¥21.6 / ¥108Input/Output
160
claude-3-5-sonnet-20241022
Anthropic
34.8
814
200K
¥21.6 / ¥108Input/Output
161
gemini-1.5-pro-002
Google
34.4
459
-
-
162
gpt-4o-mini-2024-07-18
Openai
34.0
649
128K
¥1.08 / ¥4.32Input/Output
163
claude-3-5-sonnet-20240620
Anthropic
33.6
936
200K
¥21.6 / ¥108Input/Output
164
o1-mini
Openai
33.2
424
128K
¥7.92 / ¥31.7Input/Output
165
llama-4-scout-17b-16e-instruct
Meta
32.8
398
128K
¥1.44 / ¥5.62Input/Output
166
deepseek-v2.5
Deepseek
32.4
222
1M
¥1.01 / ¥2.02Input/Output
167
athene-70b-0725
-
32.0
199
-
-
168
grok-2-mini-2024-08-13
Xai
31.6
471
1M
¥9 / ¥18Input/Output
169
gpt-4-1106-preview
Openai
31.1
1.7K
8.19K
¥216 / ¥432Input/Output
170
llama-3.3-70b-instruct
Meta
30.7
537
128K
¥0 / ¥0Input/Output
171
gpt-4-0125-preview
Openai
30.3
1.5K
8.19K
¥216 / ¥432Input/Output
172
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
29.9
474
-
-
173
qwen2.5-72b-instruct
Alibaba
29.5
340
131K
¥4.13 / ¥12.4Input/Output
174
llama-3.1-405b-instruct-bf16
Meta
29.1
364
128K
¥0 / ¥0Input/Output
175
gpt-4-turbo-2024-04-09
Openai
28.7
1.4K
128K
¥72 / ¥216Input/Output
176
claude-3-opus-20240229
Anthropic
28.3
2.8K
200K
¥108 / ¥540Input/Output
177
mistral-small-3.1-24b-instruct-2503
Mistral
27.9
411
262K
¥2.88 / ¥14.4Input/Output
178
mistral-large-2407
Mistral
27.5
441
131K
¥14.4 / ¥43.2Input/Output
179
gemini-1.5-pro-001
Google
27.0
1.1K
-
-
180
amazon-nova-pro-v1.0
Amazon
26.6
222
300K
¥5.76 / ¥23Input/Output
181
llama-3.1-405b-instruct-fp8
Meta
26.2
545
128K
¥0 / ¥0Input/Output
182
magistral-medium-2506
Mistral
25.8
163
128K
¥14.4 / ¥36Input/Output
183
claude-3-5-haiku-20241022
Anthropic
25.4
778
200K
¥5.76 / ¥28.8Input/Output
184
gpt-4o-2024-08-06
Openai
25.0
457
128K
¥18 / ¥72Input/Output
185
llama-3.1-70b-instruct
Meta
24.6
501
131K
¥2.88 / ¥2.88Input/Output
186
olmo-3.1-32b-think
Allenai
24.2
210
200K
¥14.4 / ¥57.6Input/Output
187
gemini-1.5-flash-002
Google
23.8
295
2M
¥0.54 / ¥2.2Input/Output
188
llama-4-maverick-17b-128e-instruct
Meta
23.4
563
1M
¥1.8 / ¥6.26Input/Output
189
c4ai-aya-expanse-32b
Cohere
23.0
274
-
-
190
gemma-2-27b-it
Google
22.5
793
8.19K
¥0.58 / ¥0.58Input/Output
191
gemini-1.5-flash-001
Google
22.1
919
2M
¥0.54 / ¥2.2Input/Output
192
amazon-nova-micro-v1.0
Amazon
21.7
163
128K
¥0.25 / ¥1.01Input/Output
193
amazon-nova-lite-v1.0
Amazon
21.3
170
300K
¥0.43 / ¥1.73Input/Output
194
gemini-1.5-flash-8b-001
Google
20.9
331
2M
¥0.54 / ¥2.2Input/Output
195
llama-3-70b-instruct
Meta
20.5
2.5K
8.19K
¥3.67 / ¥5.33Input/Output
196
claude-3-sonnet-20240229
Anthropic
20.1
1.8K
200K
¥21.6 / ¥108Input/Output
197
phi-4
Microsoft
19.7
205
128K
¥0.9 / ¥3.6Input/Output
198
gpt-4-0314
Openai
19.3
839
8.19K
¥216 / ¥432Input/Output
199
mistral-large-2402
Mistral
18.9
1K
262K
¥2.88 / ¥14.4Input/Output
200
command-r-plus
Cohere
18.4
1.2K
128K
¥18 / ¥72Input/Output
201
mistral-small-24b-instruct-2501
Mistral
18.0
142
262K
¥2.88 / ¥14.4Input/Output
202
nemotron-4-340b-instruct
Nvidia
17.6
357
-
-
203
claude-3-haiku-20240307
Anthropic
17.2
1.8K
200K
¥1.8 / ¥9Input/Output
204
gemma-2-9b-it
Google
16.8
591
8.19K
¥1.44 / ¥1.44Input/Output
205
deepseek-coder-v2
Deepseek
16.4
207
1M
¥1.01 / ¥2.02Input/Output
206
mistral-medium
Mistral
16.0
721
262K
¥2.88 / ¥14.4Input/Output
207
llama-3.1-8b-instruct
Meta
15.6
478
131K
¥0.79 / ¥0.79Input/Output
208
reka-flash-21b-20240226
-
15.2
430
-
-
209
qwen2-72b-instruct
Alibaba
14.8
596
131K
¥4.13 / ¥12.4Input/Output
210
gpt-4-0613
Openai
14.3
1.5K
8.19K
¥216 / ¥432Input/Output
211
mixtral-8x7b-instruct-v0.1
Mistral
13.9
1.3K
32K
¥5.04 / ¥5.04Input/Output
212
mixtral-8x22b-instruct-v0.1
Mistral
13.5
767
64K
¥14.4 / ¥43.2Input/Output
213
reka-flash-21b-20240226-online
-
13.1
230
-
-
214
command-r
Cohere
12.7
843
128K
¥18 / ¥72Input/Output
215
qwen1.5-72b-chat
Alibaba
12.3
858
-
-
216
llama-3-8b-instruct
Meta
11.9
1.6K
8.19K
¥0.29 / ¥0.29Input/Output
217
gemma-2-2b-it
Google
11.5
469
128K
¥0 / ¥0Input/Output
218
yi-1.5-34b-chat
-
11.1
399
-
-
219
qwen1.5-110b-chat
Alibaba
10.7
375
-
-
220
gemini-pro-dev-api
Google
10.2
462
1.05M
¥14.4 / ¥86.4Input/Output
221
phi-3-small-8k-instruct
Microsoft
9.8
271
8.19K
¥1.08 / ¥4.32Input/Output
222
snowflake-arctic-instruct
-
9.4
527
-
-
223
gpt-3.5-turbo-0125
Openai
9.0
1.3K
16.4K
¥3.6 / ¥10.8Input/Output
224
starling-lm-7b-beta
-
8.6
248
200K
¥5.4 / ¥18.7Input/Output
225
qwen1.5-14b-chat
Alibaba
8.2
279
-
-
226
phi-3-medium-4k-instruct
Microsoft
7.8
350
4.1K
¥1.22 / ¥4.9Input/Output
227
qwen1.5-32b-chat
Alibaba
7.4
313
-
-
228
dbrx-instruct-preview
-
7.0
538
-
-
229
openchat-3.5-0106
-
6.6
211
-
-
230
llama-2-70b-chat
Meta
6.1
679
-
-
231
vicuna-33b
-
5.7
295
-
-
232
starling-lm-7b-alpha
-
5.3
210
200K
¥5.4 / ¥18.7Input/Output
233
yi-34b-chat
-
4.9
234
-
-
234
phi-3-mini-4k-instruct
Microsoft
4.5
307
4.1K
¥0.94 / ¥3.74Input/Output
235
gpt-3.5-turbo-1106
Openai
4.1
310
16.4K
¥7.2 / ¥14.4Input/Output
236
gemma-1.1-7b-it
Google
3.7
401
-
-
237
llama-2-13b-chat
Meta
3.3
262
-
-
238
phi-3-mini-128k-instruct
Microsoft
2.9
372
128K
¥0.94 / ¥3.74Input/Output
239
mistral-7b-instruct-v0.2
Mistral
2.5
473
262K
¥2.88 / ¥14.4Input/Output
240
stripedhyena-nous-7b
-
2.0
169
-
-
241
zephyr-7b-beta
-
1.6
153
-
-
242
gemma-7b-it
Google
1.2
199
-
-
243
vicuna-13b
-
0.8
198
-
-
244
llama-2-7b-chat
Meta
0.4
257
128K
¥4.03 / ¥48Input/Output
245
mistral-7b-instruct
Mistral
0.0
175
262K
¥2.88 / ¥14.4Input/Output
Top model analysis

gpt-5.5 why it ranks first

gpt-5.5 ranks first with a percent score of 100.0 and 581 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

法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。

法语模型应该怎么选?

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。