模型榜单
这是一个基于 Chatbot Arena (lmarena.ai) 数据的排行榜，通过自动化流程生成。
数据更新时间: 2026-02-16 08:17:47 UTC / 2026-02-16 16:17:47 CST (北京时间)
排行榜
1
12
Anthropicclaude-opus-4-6-thinkingAnthropic · Proprietary
1507±9
4,650
2
12
Anthropicclaude-opus-4-6Anthropic · Proprietary
1504±8
5,427
3
34
gemini-3-proGoogle · Proprietary
1486±4
36,238
4
48
grok-4.1-thinkingxAI · Proprietary
1475±4
35,770
5
48
gemini-3-flashGoogle · Proprietary
1473±5
26,986
6
311
Bytedancedola-seed-2.0-previewBytedance · Proprietary
1473±10Preliminary
3,154
7
410
Anthropicclaude-opus-4-5-20251101-thinking-32kAnthropic · Proprietary
1471±5
28,374
8
411
Anthropicclaude-opus-4-5-20251101Anthropic · Proprietary
1467±4
33,214
9
613
grok-4.1xAI · Proprietary
1463±4
39,883
10
613
gemini-3-flash (thinking-minimal)Google · Proprietary
1462±5
18,355
11
917
gpt-5.1-highOpenAI · Proprietary
1458±4
32,297
12
722
glm-5Z.ai · MIT
1455±9
4,643
13
922
ernie-5.0-0110Baidu · Proprietary
1453±6
11,982
14
1122
Anthropicclaude-sonnet-4-5-20250929-thinking-32kAnthropic · Proprietary
1450±4
46,773
15
1123
Anthropicclaude-sonnet-4-5-20250929Anthropic · Proprietary
1450±4
44,565
16
1223
gemini-2.5-proGoogle · Proprietary
1449±3
95,526
17
1126
ernie-5.0-preview-1203Baidu · Proprietary
1449±7
9,744
18
1223
Anthropicclaude-opus-4-1-20250805-thinking-16kAnthropic · Proprietary
1449±4
49,819
19
1126
MoonshotAIkimi-k2.5-thinkingMoonshot · Modified MIT
1448±7
9,050
20
1226
Anthropicclaude-opus-4-1-20250805Anthropic · Proprietary
1445±3
75,773
21
1229
gpt-4.5-preview-2025-02-27OpenAI · Proprietary
1444±6
14,549
22
1827
chatgpt-4o-latest-20250326OpenAI · Proprietary
1442±3
83,193
23
1231
glm-4.7Z.ai · MIT
1441±6
11,971
24
1832
gpt-5.2-highOpenAI · Proprietary
1438±6
17,088
25
1537
MoonshotAIkimi-k2.5-instantMoonshot · Modified MIT
1438±9
5,007
26
1832
gpt-5.2OpenAI · Proprietary
1438±6
13,795
27
2131
gpt-5.1OpenAI · Proprietary
1437±4
34,522
28
2235
gpt-5-highOpenAI · Proprietary
1434±5
32,559
29
2235
qwen3-max-previewAlibaba · Proprietary
1434±5
27,763
30
2338
o3-2025-04-16OpenAI · Proprietary
1432±4
61,272
31
2340
grok-4-1-fast-reasoningxAI · Proprietary
1431±4
29,040
32
2544
MoonshotAIkimi-k2-thinking-turboMoonshot · Modified MIT
1429±4
34,127
33
2749
gpt-5-chatOpenAI · Proprietary
1426±4
31,753
34
3051
glm-4.6Z.ai · MIT
1425±4
35,242
35
2752
qwen3-max-2025-09-23Alibaba · Proprietary
1425±6
9,203
36
3151
Anthropicclaude-opus-4-20250514-thinking-16kAnthropic · Proprietary
1424±4
37,930
37
2754
deepseek-v3.2-exp-thinkingDeepSeek · MIT
1423±7
8,981
38
2954
deepseek-v3.2-expDeepSeek · MIT
1423±6
11,721
39
3251
qwen3-235b-a22b-instruct-2507Alibaba · Apache 2.0
1423±3
69,847
40
2956
grok-4-fast-chatxAI · Proprietary
1422±8
6,983
41
3255
deepseek-v3.2-thinkingDeepSeek · MIT
1420±5
23,731
42
3355
deepseek-v3.2DeepSeek · MIT
1420±5
28,747
43
3359
deepseek-r1-0528DeepSeek · MIT
1419±6
19,281
44
3159
ernie-5.0-preview-1022Baidu · Proprietary
1419±9
4,594
45
3359
deepseek-v3.1DeepSeek · MIT
1418±6
15,269
46
3359
MoonshotAIkimi-k2-0905-previewMoonshot · Modified MIT
1417±6
11,959
47
3359
deepseek-v3.1-thinkingDeepSeek · MIT
1417±7
11,963
48
3459
MoonshotAIkimi-k2-0711-previewMoonshot · Modified MIT
1417±5
28,632
49
3262
deepseek-v3.1-terminusDeepSeek · MIT
1416±10
3,757
50
3266
deepseek-v3.1-terminus-thinkingDeepSeek · MIT
1416±10
3,547
51
3461
qwen3-vl-235b-a22b-instructAlibaba · Apache 2.0
1415±6
11,653
52
3759
mistral-large-3Mistral · Apache 2.0
1414±5
24,945
53
3859
gpt-4.1-2025-04-14OpenAI · Proprietary
1413±4
52,121
54
3859
Anthropicclaude-opus-4-20250514Anthropic · Proprietary
1413±4
45,522
55
4362
mistral-medium-2508Mistral · Proprietary
1411±3
63,710
56
4062
grok-3-preview-02-24xAI · Proprietary
1411±4
33,966
57
4362
gemini-2.5-flashGoogle · Proprietary
1411±3
94,795
58
4267
glm-4.5Z.ai · MIT
1410±5
24,751
59
4366
grok-4-0709xAI · Proprietary
1410±4
41,993
60
5372
Anthropicclaude-haiku-4-5-20251001Anthropic · Proprietary
1405±4
45,273
61
5272
gemini-2.5-flash-preview-09-2025Google · Proprietary
1405±4
32,649
62
5272
grok-4-fast-reasoningxAI · Proprietary
1404±5
18,531
63
5773
o1-2024-12-17OpenAI · Proprietary
1402±4
27,822
64
5774
qwen3-235b-a22b-no-thinkingAlibaba · Apache 2.0
1402±4
39,513
65
5775
qwen3-next-80b-a3b-instructAlibaba · Apache 2.0
1401±5
22,799
66
6075
Anthropicclaude-sonnet-4-20250514-thinking-32kAnthropic · Proprietary
1400±4
36,169
67
5780
longcat-flash-chatMeituan · MIT
1400±6
11,526
68
6082
qwen3-235b-a22b-thinking-2507Alibaba · Apache 2.0
1399±6
9,242
69
6081
deepseek-r1DeepSeek · MIT
1398±5
18,537
70
6087
qwen3-vl-235b-a22b-thinkingAlibaba · Apache 2.0
1395±7
7,960
71
6089
amazon-nova-experimental-chat-12-10Amazon · Proprietary
1394±10
3,707
72
6384
deepseek-v3-0324DeepSeek · MIT
1394±4
46,652
73
5990
Tencenthunyuan-vision-1.5-thinkingTencent · Proprietary
1393±12
2,222
74
6488
mimo-v2-flash (non-thinking)Xiaomi · MIT
1392±5
17,587
75
6588
mai-1-previewMicrosoft AI · Proprietary
1392±5
18,099
76
6788
o4-mini-2025-04-16OpenAI · Proprietary
1391±4
46,627
77
6789
gpt-5-mini-highOpenAI · Proprietary
1390±5
27,072
78
6789
Anthropicclaude-sonnet-4-20250514Anthropic · Proprietary
1390±4
41,613
79
6989
Anthropicclaude-3-7-sonnet-20250219-thinking-32kAnthropic · Proprietary
1388±4
39,870
80
6889
o1-previewOpenAI · Proprietary
1388±5
31,120
81
6792
Tencenthunyuan-t1-20250711Tencent · Proprietary
1387±9
4,795
82
6791
Stepfunstep-3.5-flashStepFun · Apache 2.0
1387±8
6,638
83
7090
qwen3-coder-480b-a35b-instructAlibaba · Apache 2.0
1386±5
26,598
84
7090
Minimaxminimax-m2.1-previewMiniMax · MIT
1386±5
17,052
85
7190
mistral-medium-2505Mistral · Proprietary
1385±5
34,528
86
7292
qwen3-30b-a3b-instruct-2507Alibaba · Apache 2.0
1383±5
24,062
87
7193
Tencenthunyuan-turbos-20250416Tencent · Proprietary
1383±6
11,051
88
7593
gpt-4.1-mini-2025-04-14OpenAI · Proprietary
1382±4
40,498
89
8093
gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle · Proprietary
1380±4
47,022
90
71103
glm-4.6vZ.ai · MIT
1378±11
2,790
91
84100
qwen3-235b-a22bAlibaba · Apache 2.0
1375±5
27,153
92
85100
gemini-2.5-flash-lite-preview-06-17-thinkingGoogle · Proprietary
1375±4
33,884
93
87100
qwen2.5-maxAlibaba · Proprietary
1374±4
33,287
94
90100
Anthropicclaude-3-5-sonnet-20241022Anthropic · Proprietary
1373±3
89,453
95
90103
Anthropicclaude-3-7-sonnet-20250219Anthropic · Proprietary
1372±4
44,417
96
90103
glm-4.5-airZ.ai · MIT
1371±4
31,309
97
90106
qwen3-next-80b-a3b-thinkingAlibaba · Apache 2.0
1369±6
13,835
98
90106
Minimaxminimax-m1MiniMax · Apache 2.0
1367±4
36,803
99
90110
glm-4.7-flashZ.ai · MIT
1366±7
8,440
100
90110
amazon-nova-experimental-chat-11-10Amazon · Proprietary
1366±5
17,326
101
94108
gemma-3-27b-itGoogle · Gemma
1365±4
48,656
102
94111
o3-mini-highOpenAI · Proprietary
1364±5
18,584
103
94114
grok-3-mini-highxAI · Proprietary
1363±5
17,513
104
97114
gemini-2.0-flash-001Google · Proprietary
1361±4
44,818
105
97122
deepseek-v3DeepSeek · DeepSeek
1359±5
21,788
106
99123
grok-3-mini-betaxAI · Proprietary
1357±5
23,753
107
97128
intellect-3Prime Intellect · MIT
1356±8
5,308
108
100127
mistral-small-2506Mistral · Apache 2.0
1356±5
18,332
109
103127
gpt-oss-120bOpenAI · Apache 2.0
1354±4
30,898
110
103128
gemini-2.0-flash-lite-preview-02-05Google · Proprietary
1353±4
24,951
111
99129
glm-4.5vZ.ai · MIT
1353±8
4,968
112
105127
Coherecommand-a-03-2025Cohere · CC-BY-NC-4.0
1353±3
57,368
113
105128
gemini-1.5-pro-002Google · Proprietary
1351±3
55,607
114
105130
amazon-nova-experimental-chat-10-20Amazon · Proprietary
1350±6
11,371
115
100141
Tencenthunyuan-turbos-20250226Tencent · Proprietary
1349±12
2,226
116
107130
o3-miniOpenAI · Proprietary
1348±3
58,616
117
103141
amazon-nova-experimental-chat-10-09Amazon · Proprietary
1348±11
2,886
118
102142
Nvidiallama-3.1-nemotron-ultra-253b-v1Nvidia · Nvidia Open Model
1347±12
2,546
119
105135
ling-flash-2.0Ant Group · MIT
1347±7
7,032
120
105136
Minimaxminimax-m2MiniMax · Apache 2.0
1347±8
6,710
121
105139
qwen3-32bAlibaba · Apache 2.0
1347±9
3,932
122
105137
Stepfunstep-3StepFun · Apache 2.0
1347±7
6,587
123
105139
qwen-plus-0125Alibaba · Proprietary
1346±8
5,823
124
110132
gpt-4o-2024-05-13OpenAI · Proprietary
1346±3
112,863
125
107142
glm-4-plus-0111Zhipu · Proprietary
1343±8
5,760
126
113137
Anthropicclaude-3-5-sonnet-20240620Anthropic · Proprietary
1343±3
82,417
127
107144
gemma-3-12b-itGoogle · Gemma
1342±10
3,829
128
107146
Nvidianvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia · Nvidia Open
1341±10
3,431
129
106147
Tencenthunyuan-turbo-0110Tencent · Proprietary
1340±12
2,295
130
114146
gpt-5-nano-highOpenAI · Proprietary
1338±7
8,394
131
116146
nova-2-liteAmazon · Proprietary
1337±6
12,132
132
117143
o1-miniOpenAI · Proprietary
1337±4
51,986
133
117146
qwq-32bAlibaba · Apache 2.0
1336±4
26,102
134
121145
Metallama-3.1-405b-instruct-bf16Meta · Llama 3.1 Community
1335±4
41,392
135
121146
grok-2-2024-08-13xAI · Proprietary
1335±4
63,495
136
118146
gpt-4o-2024-08-06OpenAI · Proprietary
1335±4
45,498
137
117146
gemini-advanced-0514Google · Proprietary
1335±5
50,142
138
116153
Stepfunstep-2-16k-exp-202412StepFun · Proprietary
1334±9
4,829
139
123146
Metallama-3.1-405b-instruct-fp8Meta · Llama 3.1 Community
1334±4
59,655
140
123154
olmo-3.1-32b-instructAllen AI · Apache 2.0
1331±6
12,275
141
127158
01.AIyi-lightning01 AI · Proprietary
1329±5
27,340
142
128159
qwen3-30b-a3bAlibaba · Apache 2.0
1328±5
27,416
143
129159
Metallama-4-maverick-17b-128e-instructMeta · Llama 4
1328±4
41,108
144
119168
Nvidiallama-3.3-nemotron-49b-super-v1Nvidia · Nvidia
1327±12
2,230
145
125168
Tencenthunyuan-large-2025-02-10Tencent · Proprietary
1326±10
3,738
146
139164
gpt-4-turbo-2024-04-09OpenAI · Proprietary
1324±4
98,130
147
139164
Anthropicclaude-3-5-haiku-20241022Anthropic · Proprietary
1324±3
71,157
148
130168
deepseek-v2.5-1210DeepSeek · DeepSeek
1323±8
6,793
149
139164
gemini-1.5-pro-001Google · Proprietary
1323±4
79,132
150
139165
Metallama-4-scout-17b-16e-instructMeta · Llama
1323±5
31,207
151
140164
Anthropicclaude-3-opus-20240229Anthropic · Proprietary
1322±3
194,904
152
138169
gpt-4.1-nano-2025-04-14OpenAI · Proprietary
1322±8
6,107
153
139168
Stepfunstep-1o-turbo-202506StepFun · Proprietary
1322±7
9,683
154
139170
ring-flash-2.0Ant Group · MIT
1320±7
7,189
155
144168
Metallama-3.3-70b-instructMeta · Llama-3.3
1320±3
55,560
156
141168
glm-4-plusZhipu AI · Proprietary
1319±5
26,134
157
141170
gemma-3n-e4b-itGoogle · Gemma
1319±5
23,326
158
141171
qwen-max-0919Alibaba · Qwen
1318±6
16,479
159
144168
gpt-4o-mini-2024-07-18OpenAI · Proprietary
1318±3
68,801
160
142175
gpt-oss-20bOpenAI · Apache 2.0
1317±6
10,795
161
144174
Nvidianvidia-nemotron-3-nano-30b-a3b-bf16Nvidia · NVIDIA Open Model
1317±6
15,440
162
144177
qwen2.5-plus-1127Alibaba · Proprietary
1315±6
10,179
163
148175
athene-v2-chatNexusFlow · NexusFlow
1314±5
24,746
164
149175
mistral-large-2407Mistral · Mistral Research
1314±4
45,460
165
149176
gpt-4-0125-previewOpenAI · Proprietary
1313±4
93,439
166
149176
gpt-4-1106-previewOpenAI · Proprietary
1313±4
100,107
167
144180
Tencenthunyuan-standard-2025-02-10Tencent · Proprietary
1312±10
3,905
168
141185
mercuryInception AI · Proprietary
1310±14
1,896
169
156179
gemini-1.5-flash-002Google · Proprietary
1310±4
34,909
170
160180
grok-2-mini-2024-08-13xAI · Proprietary
1308±4
52,574
171
160180
deepseek-v2.5DeepSeek · DeepSeek
1307±5
24,574
172
160180
athene-70b-0725NexusFlow · CC-BY-NC-4.0
1306±6
19,622
173
157180
olmo-3-32b-thinkAllen AI · Apache 2.0
1306±8
5,878
174
164180
mistral-large-2411Mistral · MRL
1305±4
28,081
175
161180
magistral-medium-2506Mistral · Proprietary
1305±6
12,059
176
166180
mistral-small-3.1-24b-instruct-2503Mistral · Apache 2.0
1305±4
34,094
177
159187
gemma-3-4b-itGoogle · Gemma
1303±9
4,177
178
167180
qwen2.5-72b-instructAlibaba · Qwen
1303±4
39,409
179
167190
Nvidiallama-3.1-nemotron-70b-instructNvidia · Llama 3.1
1299±8
7,136
180
168191
Tencenthunyuan-large-visionTencent · Proprietary
1296±9
5,599
181
177191
Metallama-3.1-70b-instructMeta · Llama 3.1 Community
1294±4
55,234
182
178192
amazon-nova-pro-v1.0Amazon · Proprietary
1290±5
24,753
183
177195
jamba-1.5-largeAI21 Labs · Jamba Open
1289±7
8,659
184
179193
gemma-2-27b-itGoogle · Gemma license
1288±3
75,764
185
177197
ibm-granite-h-smallIBM · Apache 2.0
1288±8
5,659
186
178195
reka-core-20240904Reka AI · Proprietary
1288±7
7,309
187
179195
gpt-4-0314OpenAI · Proprietary
1287±5
54,167
188
177201
llama-3.1-tulu-3-70bAi2 · Llama 3.1
1287±10
2,846
189
177201
Nvidiallama-3.1-nemotron-51b-instructNvidia · Llama 3.1
1286±10
3,749
190
179201
olmo-3.1-32b-thinkAllen AI · Apache 2.0
1286±7
8,458
191
180195
gemini-1.5-flash-001Google · Proprietary
1286±4
62,823
192
183201
Anthropicclaude-3-sonnet-20240229Anthropic · Proprietary
1281±4
109,289
193
182201
gemma-2-9b-it-simpoPrinceton · MIT
1280±7
10,069
194
184201
Nvidianemotron-4-340b-instructNvidia · NVIDIA Open Model
1278±5
19,661
195
184203
Coherecommand-r-plus-08-2024Cohere · CC-BY-NC-4.0
1277±7
9,869
196
189201
Metallama-3-70b-instructMeta · Llama 3 Community
1276±4
156,880
197
189202
gpt-4-0613OpenAI · Proprietary
1275±4
88,721
198
188204
mistral-small-24b-instruct-2501Mistral · Apache 2.0
1274±6
14,677
199
188205
glm-4-0520Zhipu AI · Proprietary
1274±7
9,788
200
189207
reka-flash-20240904Reka AI · Proprietary
1272±7
7,537
201
189210
qwen2.5-coder-32b-instructAlibaba · Apache 2.0
1271±8
5,430
202
196210
Coherec4ai-aya-expanse-32bCohere · CC-BY-NC-4.0
1267±5
27,123
203
198210
gemma-2-9b-itGoogle · Gemma license
1266±4
54,615
204
197211
deepseek-coder-v2DeepSeek · DeepSeek License
1264±6
15,147
205
200211
Coherecommand-r-plusCohere · CC-BY-NC-4.0
1262±4
77,556
206
199211
qwen2-72b-instructAlibaba · Qianwen LICENSE
1262±5
37,325
207
201211
Anthropicclaude-3-haiku-20240307Anthropic · Proprietary
1261±4
117,705
208
200212
amazon-nova-lite-v1.0Amazon · Proprietary
1261±5
19,376
209
201212
gemini-1.5-flash-8b-001Google · Proprietary
1259±4
35,556
210
204212
Azurephi-4Microsoft · MIT
1256±5
24,126
211
201218
olmo-2-0325-32b-instructAllen AI · Apache-2.0
1252±11
3,335
212
208217
Coherecommand-r-08-2024Cohere · CC-BY-NC-4.0
1250±7
10,141
213
211221
mistral-large-2402Mistral · Proprietary
1243±5
62,437
214
211221
amazon-nova-micro-v1.0Amazon · Proprietary
1241±5
19,355
215
211225
jamba-1.5-miniAI21 Labs · Jamba Open
1239±7
8,854
216
211229
ministral-8b-2410Mistral · MRL
1237±9
4,780
217
212229
gemini-pro-dev-apiGoogle · Proprietary
1235±7
18,352
218
213229
qwen1.5-110b-chatAlibaba · Qianwen LICENSE
1234±6
26,191
219
213230
reka-flash-21b-20240226-onlineReka AI · Proprietary
1233±7
15,451
220
211231
Tencenthunyuan-standard-256kTencent · Proprietary
1233±12
2,729
221
213229
qwen1.5-72b-chatAlibaba · Qianwen LICENSE
1233±5
39,296
222
215230
mixtral-8x22b-instruct-v0.1Mistral · Apache 2.0
1230±5
51,417
223
215231
Coherecommand-rCohere · CC-BY-NC-4.0
1227±5
54,038
224
215231
reka-flash-21b-20240226Reka AI · Proprietary
1227±6
24,806
225
216232
gpt-3.5-turbo-0125OpenAI · Proprietary
1224±5
66,191
226
220232
Metallama-3-8b-instructMeta · Llama 3 Community
1223±4
104,636
227
216233
mistral-mediumMistral · Proprietary
1223±5
34,552
228
216233
Coherec4ai-aya-expanse-8bCohere · CC-BY-NC-4.0
1223±7
9,827
229
215236
gemini-proGoogle · Proprietary
1222±12
6,390
230
216236
llama-3.1-tulu-3-8bAi2 · Llama 3.1
1221±11
2,895
231
227236
01.AIyi-1.5-34b-chat01 AI · Apache-2.0
1214±5
24,142
232
222238
HuggingFacezephyr-orpo-141b-A35b-v0.1HuggingFace · Apache 2.0
1213±11
4,653
233
229236
Metallama-3.1-8b-instructMeta · Llama 3.1 Community
1212±4
49,605
234
225242
granite-3.1-8b-instructIBM · Apache 2.0
1209±11
3,092
235
229242
qwen1.5-32b-chatAlibaba · Qianwen LICENSE
1204±6
21,744
236
229244
gpt-3.5-turbo-1106OpenAI · Proprietary
1203±9
16,616
237
233243
gemma-2-2b-itGoogle · Gemma license
1199±4
46,618
238
233244
Azurephi-3-medium-4k-instructMicrosoft · MIT
1198±5
25,055
239
234244
mixtral-8x7b-instruct-v0.1Mistral · Apache 2.0
1197±4
73,505
240
234249
dbrx-instruct-previewDatabricks · DBRX LICENSE
1195±6
32,196
241
234253
InternLMinternlm2_5-20b-chatInternLM · Other
1191±7
9,902
242
234253
qwen1.5-14b-chatAlibaba · Qianwen LICENSE
1191±7
17,841
243
237259
Azurewizardlm-70bMicrosoft · Llama 2 Community
1185±9
8,214
244
236260
deepseek-llm-67b-chatDeepSeek · DeepSeek License
1185±12
4,933
245
240256
01.AIyi-34b-chat01 AI · Yi License
1184±7
15,483
246
240259
OpenChatopenchat-3.5-0106OpenChat · Apache-2.0
1183±8
12,636
247
240260
OpenChatopenchat-3.5OpenChat · Apache-2.0
1182±10
7,967
248
240260
granite-3.0-8b-instructIBM · Apache 2.0
1182±9
6,643
249
241260
gemma-1.1-7b-itGoogle · Gemma license
1180±6
23,893
250
241260
Snowflakesnowflake-arctic-instructSnowflake · Apache 2.0
1180±6
32,836
251
240261
granite-3.1-2b-instructIBM · Apache 2.0
1180±11
3,191
252
241261
tulu-2-dpo-70bAllenAI/UW · AI2 ImpACT Low-risk
1178±10
6,534
253
241264
openhermes-2.5-mistral-7bNousResearch · Apache-2.0
1175±10
5,006
254
243263
vicuna-33bLMSYS · Non-commercial
1173±6
22,479
255
243266
starling-lm-7b-betaNexusflow · Apache-2.0
1172±7
16,057
256
243264
Azurephi-3-small-8k-instructMicrosoft · MIT
1171±6
17,763
257
244264
Metallama-2-70b-chatMeta · Llama 2 Community
1171±6
38,491
258
244267
starling-lm-7b-alphaUC Berkeley · CC-BY-NC-4.0
1168±8
10,224
259
246267
Metallama-3.2-3b-instructMeta · Llama 3.2
1167±8
7,936
260
244270
nous-hermes-2-mixtral-8x7b-dpoNousResearch · Apache-2.0
1165±12
3,776
261
251276
qwq-32b-previewAlibaba · Apache 2.0
1157±12
3,233
262
257274
granite-3.0-2b-instructIBM · Apache 2.0
1156±8
6,837
263
253277
Nvidiallama2-70b-steerlm-chatNvidia · Llama 2 Community
1156±13
3,584
264
254280
solar-10.7b-instruct-v1.0Upstage AI · CC-BY-NC-4.0
1153±13
4,155
265
253282
dolphin-2.2.1-mistral-7bCognitive Computations · Apache-2.0
1152±15
1,679
266
258280
mpt-30b-chatMosaicML · CC-BY-NC-SA-4.0
1150±12
2,571
267
260277
mistral-7b-instruct-v0.2Mistral · Apache-2.0
1150±7
19,402
268
260279
Azurewizardlm-13bMicrosoft · Llama 2 Community
1149±9
7,046
269
257284
falcon-180b-chatTII · Falcon-180B TII License
1147±17
1,295
270
260283
qwen1.5-7b-chatAlibaba · Qianwen LICENSE
1144±10
4,735
271
261282
Azurephi-3-mini-4k-instruct-june-2024Microsoft · MIT
1143±6
12,296
272
261283
Metallama-2-13b-chatMeta · Llama 2 Community
1142±7
19,171
273
261283
vicuna-13bLMSYS · Llama 2 Community
1141±7
19,366
274
261285
qwen-14b-chatAlibaba · Qianwen LICENSE
1139±11
4,964
275
262285
palm-2Google · Proprietary
1137±9
8,554
276
262285
Metacodellama-34b-instructMeta · Llama 2 Community
1137±9
7,363
277
263285
gemma-7b-itGoogle · Gemma license
1136±10
8,925
278
265286
HuggingFacezephyr-7b-betaHuggingFace · MIT
1131±9
11,116
279
268286
Azurephi-3-mini-128k-instructMicrosoft · MIT
1129±7
20,691
280
270286
Azurephi-3-mini-4k-instructMicrosoft · MIT
1129±6
20,115
281
266290
guanaco-33bUW · Non-commercial
1128±12
2,921
282
265290
HuggingFacezephyr-7b-alphaHuggingFace · MIT
1127±16
1,785
283
273290
stripedhyena-nous-7bTogether AI · Apache 2.0
1121±11
5,184
284
268291
Metacodellama-70b-instructMeta · Llama 2 Community
1119±18
1,143
285
278290
vicuna-7bLMSYS · Llama 2 Community
1115±9
6,923
286
274291
HuggingFacesmollm2-1.7b-instructHuggingFace · Apache 2.0
1115±14
2,201
287
281290
gemma-1.1-2b-itGoogle · Gemma license
1114±8
10,853
288
281290
Metallama-3.2-1b-instructMeta · Llama 3.2
1111±8
8,045
289
281291
mistral-7b-instructMistral · Apache 2.0
1110±9
8,977
290
281291
Metallama-2-7b-chatMeta · Llama 2 Community
1108±7
14,148
291
287295
gemma-2b-itGoogle · Gemma license
1092±12
4,779
292
291294
qwen1.5-4b-chatAlibaba · Qianwen LICENSE
1090±9
7,598
293
291298
olmo-7b-instructAllen AI · Apache-2.0
1075±11
6,329
294
292298
koala-13bUC Berkeley · Non-commercial
1071±10
6,964
295
293298
alpaca-13bStanford · Non-commercial
1068±12
5,745
296
291299
gpt4all-13b-snoozyNomic AI · Non-commercial
1066±15
1,743
297
293299
mpt-7b-chatMosaicML · CC-BY-NC-SA-4.0
1062±12
3,925
298
293299
chatglm3-6bTsinghua · Apache-2.0
1056±12
4,658
299
296301
RWKVRWKV-4-Raven-14BRWKV · Apache 2.0
1041±11
4,845
300
299301
chatglm2-6bTsinghua · Apache-2.0
1024±14
2,657
301
299301
oasst-pythia-12bOpenAssistant · Apache 2.0
1022±11
6,311
302
302305
chatglm-6bTsinghua · Non-commercial
996±13
4,914
303
302305
fastchat-t5-3bLMSYS · Apache 2.0
991±12
4,203
304
302305
dolly-v2-12bDatabricks · MIT
980±14
3,412
305
302306
Metallama-13bMeta · Non-commercial
972±16
2,391
306
305306
Stabilitystablelm-tuned-alpha-7bStability AI · CC-BY-NC-SA-4.0
953±13
3,287
说明
排名 (UB)：基于 Bradley-Terry 模型计算的排名。此排名反映了模型在竞技场中的综合表现，并提供了其 Elo 分数的 上界 估计，帮助理解模型的潜在竞争力。
模型：大型语言模型 (LLM) 的名称。部分模型名称可能已嵌入相关链接。
分数：模型在竞技场中通过用户投票获得的 Elo 评分。Elo 评分是一种相对排名系统，分数越高表示模型表现越好。
95% 置信区间 (±)：模型 Elo 评分的95%置信区间（例如：
±6）。这个区间越小，表示模型的评分越稳定和可靠。票数：该模型在竞技场中收到的总投票数量。投票数越多，通常意味着其评分的统计可靠性越高。
组织/公司：提供该模型的组织或公司。
许可证：模型的许可协议类型，例如专有 (Proprietary)、Apache 2.0、MIT 等。
数据来源与更新频率
本排行榜数据由自动化脚本直接从 1 2 官方网站获取。此排行榜由 GitHub Actions 每天自动更新。
免责声明
本报告仅供参考。排行榜数据是动态变化的，并基于特定时间段内用户在 Chatbot Arena 上的偏好投票。数据的完整性和准确性取决于上游数据源。不同模型可能采用不同的许可协议，使用时请务必参考模型提供商的官方说明。
最后更新于
这有帮助吗？