LLM Arena 排行榜 (实时更新)

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: 2026-04-21 08:42:13 UTC / 2026-04-21 16:42:13 CST (北京时间)

排行榜

Rank Rank Spread 模型 分数 票数 Price $/M Context
1 16 Anthropicclaude-opus-4-7-thinkingAnthropic · Proprietary 1504±9 3,898 $5/$25 1M
2 16 Anthropicclaude-opus-4-6-thinkingAnthropic · Proprietary 1502±5 18,888 $5/$25 1M
3 17 Anthropicclaude-opus-4-7Anthropic · Proprietary 1497±9 4,646 $5/$25 1M
4 16 Anthropicclaude-opus-4-6Anthropic · Proprietary 1496±5 20,158 $5/$25 1M
5 110 Metamuse-sparkMeta · Proprietary 1493±8Preliminary 5,877 N/A N/A
6 17 gemini-3.1-pro-previewGoogle · Proprietary 1493±5 23,766 $2/$12 1M
7 410 gemini-3-proGoogle · Proprietary 1486±4 41,378 $2/$12 1M
8 614 grok-4.20-beta1xAI · Proprietary 1482±6 13,010 N/A N/A
9 614 gpt-5.4-highOpenAI · Proprietary 1482±6 12,322 $2.50/$15 1.1M
10 615 grok-4.20-beta-0309-reasoningxAI · Proprietary 1480±6 12,442 $2/$6 2M
11 819 gpt-5.2-chat-latest-20260210OpenAI · Proprietary 1477±5 18,619 $1.75/$14 128K
12 819 gemini-3-flashGoogle · Proprietary 1474±4 30,788 $0.50/$3 1M
13 820 grok-4.20-multi-agent-beta-0309xAI · Proprietary 1474±6 12,841 $2/$6 2M
14 820 Anthropicclaude-opus-4-5-20251101-thinking-32kAnthropic · Proprietary 1473±4 37,167 $5/$25 200K
15 1121 grok-4.1-thinkingxAI · Proprietary 1469±4 50,170 N/A N/A
16 1025 glm-5.1Z.ai · MIT 1469±7 7,927 $0.70/$4.40 202.8K
17 1122 Anthropicclaude-opus-4-5-20251101Anthropic · Proprietary 1469±4 50,046 $5/$25 200K
18 1125 gpt-5.4OpenAI · Proprietary 1467±6 12,870 $2.50/$15 1.1M
19 1125 qwen3.5-max-previewAlibaba · Proprietary 1466±6Preliminary 10,245 N/A N/A
20 1327 Anthropicclaude-sonnet-4-6Anthropic · Proprietary 1463±6 12,043 $3/$15 1M
21 1527 gemini-3-flash (thinking-minimal)Google · Proprietary 1462±4 36,244 $0.50/$3 1M
22 1727 grok-4.1xAI · Proprietary 1461±4 54,146 N/A N/A
23 1631 Bytedancedola-seed-2.0-proBytedance · Proprietary 1460±5 21,521 N/A N/A
24 1736 gpt-5.4-mini-highOpenAI · Proprietary 1458±6 9,900 $2.50/$15 1.1M
25 1736 glm-5Z.ai · MIT 1457±5 16,528 $1/$3.20 202.8K
26 2038 gpt-5.1-highOpenAI · Proprietary 1455±4 40,884 $1.25/$10 400K
27 2440 Anthropicclaude-sonnet-4-5-20250929-thinking-32kAnthropic · Proprietary 1452±3 62,470 $3/$15 200K
28 2441 Anthropicclaude-sonnet-4-5-20250929Anthropic · Proprietary 1452±3 60,425 $3/$15 200K
29 2044 gemma-4-31bGoogle · Apache 2.0 1451±8Preliminary 5,822 $0.14/$0.40 262.1K
30 2341 ernie-5.0-0110Baidu · Proprietary 1451±5 24,817 N/A N/A
31 2343 gpt-5.3-chat-latestOpenAI · Proprietary 1451±5 17,274 $1.75/$14 128K
32 2442 kimi-k2.5-thinkingMoonshot · Modified MIT 1451±5 23,091 $0.60/$3 N/A
33 2346 ernie-5.0-preview-1203Baidu · Proprietary 1449±7 9,766 N/A N/A
34 2444 Anthropicclaude-opus-4-1-20250805-thinking-16kAnthropic · Proprietary 1449±3 49,870 $15/$75 200K
35 2643 gemini-2.5-proGoogle · Proprietary 1448±3 109,917 $1.25/$10 1M
36 2349 qwen3.6-plusAlibaba · Proprietary 1448±9 4,305 $0.33/$1.95 1M
37 2647 qwen3.5-397b-a17bAlibaba · Apache 2.0 1447±5 17,989 $0.39/$2.34 262.1K
38 2744 Anthropicclaude-opus-4-1-20250805Anthropic · Proprietary 1447±3 77,459 $15/$75 200K
39 2447 mimo-v2-proXiaomi · Proprietary 1446±6 10,827 $1/$3 1M
40 2750 gpt-4.5-preview-2025-02-27OpenAI · Proprietary 1444±6 14,547 $75/$150 128K
41 3147 chatgpt-4o-latest-20250326OpenAI · Proprietary 1443±3 82,573 $5/$15 128K
42 2852 glm-4.7Z.ai · MIT 1443±6 12,138 $0.38/$1.74 202.8K
43 3352 gpt-5.2-highOpenAI · Proprietary 1441±4 33,089 $1.75/$14 400K
44 3653 gpt-5.2OpenAI · Proprietary 1439±4 30,208 $1.75/$14 400K
45 3055 gemma-4-26b-a4bGoogle · Apache 2.0 1439±8Preliminary 5,780 N/A N/A
46 3753 gpt-5.1OpenAI · Proprietary 1439±4 43,525 $1.25/$10 400K
47 3655 gemini-3.1-flash-lite-previewGoogle · Proprietary 1438±5 18,747 $0.25/$1.50 1M
48 4058 qwen3-max-previewAlibaba · Proprietary 1435±5 27,770 $0.78/$3.90 262.1K
49 4260 gpt-5-highOpenAI · Proprietary 1433±5 31,997 $1.25/$10 400K
50 4066 longcat-flash-chat-2602-expMeituan · Proprietary 1433±7Preliminary 8,528 N/A N/A
51 4168 kimi-k2.5-instantMoonshot · Modified MIT 1432±7 8,208 $0.44/$2 262.1K
52 4461 grok-4-1-fast-reasoningxAI · Proprietary 1432±4 45,216 $0.20/$0.50 2M
53 4664 o3-2025-04-16OpenAI · Proprietary 1431±4 59,810 $2/$8 200K
54 4666 kimi-k2-thinking-turboMoonshot · Modified MIT 1430±3 48,416 $1.15/$8 262.1K
55 4277 amazon-nova-experimental-chat-26-02-10Amazon · Proprietary 1428±10 3,429 N/A N/A
56 4875 gpt-5-chatOpenAI · Proprietary 1426±4 31,636 $1.25/$10 128K
57 4976 glm-4.6Z.ai · MIT 1426±4 35,724 $0.39/$1.90 204.8K
58 4877 deepseek-v3.2-exp-thinkingDeepSeek · MIT 1425±7 9,080 $0.27/$0.41 163.8K
59 5176 deepseek-v3.2DeepSeek · MIT 1424±4 43,509 $0.25/$0.38 131.1K
60 4877 qwen3-max-2025-09-23Alibaba · Proprietary 1424±6 9,185 $0.78/$3.90 262.1K
61 5176 Anthropicclaude-opus-4-20250514-thinking-16kAnthropic · Proprietary 1424±4 36,962 $15/$75 200K
62 5476 qwen3-235b-a22b-instruct-2507Alibaba · Apache 2.0 1423±3 84,048 $0.26/$1.06 N/A
63 4978 deepseek-v3.2-expDeepSeek · MIT 1423±6 11,950 $0.27/$0.41 163.8K
64 5279 deepseek-r1-0528DeepSeek · MIT 1422±6 18,479 $0.50/$2.15 163.8K
65 5577 deepseek-v3.2-thinkingDeepSeek · MIT 1422±4 37,837 $0.25/$0.38 131.1K
66 5083 grok-4-fast-chatxAI · Proprietary 1421±8 6,826 $3/$15 256K
67 5185 ernie-5.0-preview-1022Baidu · Proprietary 1419±9 4,730 N/A N/A
68 5582 qwen3.5-122b-a10bAlibaba · Apache 2.0 1419±5 14,744 $0.26/$2.08 262.1K
69 5584 kimi-k2-0905-previewMoonshot · Modified MIT 1418±7 11,805 $0.60/$2.50 262.1K
70 5584 deepseek-v3.1DeepSeek · MIT 1418±6 14,989 $1.23/$4.94 N/A
71 5684 kimi-k2-0711-previewMoonshot · Modified MIT 1417±5 27,662 $0.60/$2.50 131.1K
72 5585 deepseek-v3.1-thinkingDeepSeek · MIT 1417±7 11,761 $1.23/$4.94 N/A
73 5293 deepseek-v3.1-terminus-thinkingDeepSeek · MIT 1417±10 3,473 $0.21/$0.79 163.8K
74 5594 deepseek-v3.1-terminusDeepSeek · MIT 1416±10 3,713 $0.21/$0.79 163.8K
75 5496 amazon-nova-experimental-chat-26-01-10Amazon · Proprietary 1416±10 3,419 N/A N/A
76 5588 qwen3-vl-235b-a22b-instructAlibaba · Apache 2.0 1416±6 11,536 $0.20/$0.88 262.1K
77 6084 mistral-large-3Mistral · Apache 2.0 1415±4 40,823 $0.50/$1.50 N/A
78 6486 gpt-4.1-2025-04-14OpenAI · Proprietary 1413±4 51,076 $2/$8 1M
79 6591 Anthropicclaude-opus-4-20250514Anthropic · Proprietary 1412±4 44,270 $15/$75 200K
80 6693 grok-3-preview-02-24xAI · Proprietary 1412±4 32,922 $3/$15 131.1K
81 6694 glm-4.5Z.ai · MIT 1411±5 24,356 $0.60/$2.20 131.1K
82 6791 gemini-2.5-flashGoogle · Proprietary 1411±3 109,492 $0.30/$2.50 1M
83 6695 grok-4-0709xAI · Proprietary 1410±4 41,445 $3/$15 256K
84 6893 mistral-medium-2508Mistral · Proprietary 1410±3 79,664 $2.70/$8.10 32K
85 7298 Anthropicclaude-haiku-4-5-20251001Anthropic · Proprietary 1408±3 61,939 $1/$5 200K
86 76102 gemini-2.5-flash-preview-09-2025Google · Proprietary 1405±4 32,962 $0.30/$2.50 1M
87 75104 qwen3.5-27bAlibaba · Apache 2.0 1404±5 14,416 $0.20/$1.56 262.1K
88 76104 grok-4-fast-reasoningxAI · Proprietary 1404±5 18,750 $0.20/$0.50 2M
89 74106 gpt-5.4-nano-highOpenAI · Proprietary 1404±6 9,234 $2.50/$15 1.1M
90 78104 qwen3-235b-a22b-no-thinkingAlibaba · Apache 2.0 1403±5 38,249 $0.46/$1.82 131.1K
91 75107 minimax-m2.7MiniMax · Modified MIT 1403±7 9,172 $0.30/$1.20 196.6K
92 83106 o1-2024-12-17OpenAI · Proprietary 1402±4 27,807 $15/$60 200K
93 81106 qwen3-next-80b-a3b-instructAlibaba · Apache 2.0 1402±5 22,912 $0.09/$1.10 262.1K
94 78108 longcat-flash-chatMeituan · MIT 1401±6 11,420 $0.20/$0.80 131.1K
95 85107 minimax-m2.5MiniMax · Modified MIT 1401±5 19,891 $0.15/$1.20 196.6K
96 84112 qwen3-235b-a22b-thinking-2507Alibaba · Apache 2.0 1399±7 9,008 $0.13/$0.60 262.1K
97 86111 qwen3.5-flashAlibaba · Proprietary 1399±5 15,199 N/A N/A
98 86109 Anthropicclaude-sonnet-4-20250514-thinking-32kAnthropic · Proprietary 1399±4 35,170 $3/$15 1M
99 86113 deepseek-r1DeepSeek · MIT 1398±5 18,524 $0.70/$2.50 64K
100 76121 Tencenthunyuan-vision-1.5-thinkingTencent · Proprietary 1396±12 2,218 N/A N/A
101 86117 qwen3-vl-235b-a22b-thinkingAlibaba · Apache 2.0 1396±7 7,960 $0.26/$2.60 131.1K
102 87117 qwen3.5-35b-a3bAlibaba · Apache 2.0 1396±5 15,041 $0.16/$1.30 262.1K
103 85121 amazon-nova-experimental-chat-12-10Amazon · Proprietary 1396±10 3,687 N/A N/A
104 87115 deepseek-v3-0324DeepSeek · MIT 1395±4 45,547 $3/$4.50 32.8K
105 90120 Stepfunstep-3.5-flashStepFun · Apache 2.0 1393±5 20,897 $0.10/$0.30 262.1K
106 93119 mimo-v2-flash (non-thinking)Xiaomi · MIT 1393±4 32,693 $0.09/$0.29 262.1K
107 90120 mai-1-previewMicrosoft AI · Proprietary 1393±5 17,903 N/A N/A
108 96121 gpt-5-mini-highOpenAI · Proprietary 1390±5 27,072 $0.25/$2 400K
109 97121 o4-mini-2025-04-16OpenAI · Proprietary 1390±4 45,485 $1.10/$4.40 200K
110 98121 Anthropicclaude-sonnet-4-20250514Anthropic · Proprietary 1389±4 40,365 $3/$15 1M
111 99122 o1-previewOpenAI · Proprietary 1388±5 31,122 $15/$60 N/A
112 95124 Tencenthunyuan-t1-20250711Tencent · Proprietary 1388±9 4,715 N/A N/A
113 100122 qwen3-coder-480b-a35b-instructAlibaba · Apache 2.0 1387±5 25,766 $0.40/$1.60 262.1K
114 97122 mimo-v2-flash (thinking)Xiaomi · MIT 1387±6 10,983 $0.09/$0.29 262.1K
115 101122 Anthropicclaude-3-7-sonnet-20250219-thinking-32kAnthropic · Proprietary 1387±4 38,843 $3/$15 200K
116 100122 mistral-medium-2505Mistral · Proprietary 1387±5 33,269 $0.40/$2 131.1K
117 101123 minimax-m2.1-previewMiniMax · MIT 1386±5 17,159 $0.29/$0.95 196.6K
118 104125 qwen3-30b-a3b-instruct-2507Alibaba · Apache 2.0 1383±5 23,776 $0.09/$0.30 262.1K
119 103127 Tencenthunyuan-turbos-20250416Tencent · Proprietary 1382±6 10,725 N/A N/A
120 106126 gpt-4.1-mini-2025-04-14OpenAI · Proprietary 1382±4 39,373 $0.40/$1.60 1M
121 111127 gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle · Proprietary 1380±3 47,299 $0.10/$0.40 1M
122 103137 glm-4.6vZ.ai · MIT 1378±11 2,805 $0.30/$0.90 131.1K
123 116132 trinity-large-previewArcee AI · Apache 2.0 1376±5 15,782 N/A N/A
124 117132 qwen3-235b-a22bAlibaba · Apache 2.0 1375±5 26,284 $0.46/$1.82 131.1K
125 117132 gemini-2.5-flash-lite-preview-06-17-thinkingGoogle · Proprietary 1374±5 32,972 $0.10/$0.40 1M
126 119132 qwen2.5-maxAlibaba · Proprietary 1374±4 32,631 N/A N/A
127 120133 glm-4.5-airZ.ai · MIT 1373±4 31,139 $0.13/$0.85 131.1K
128 122133 Anthropicclaude-3-5-sonnet-20241022Anthropic · Proprietary 1372±3 88,366 $3/$15 200K
129 122137 Anthropicclaude-3-7-sonnet-20250219Anthropic · Proprietary 1371±4 43,219 $3/$15 200K
130 122139 qwen3-next-80b-a3b-thinkingAlibaba · Apache 2.0 1369±6 13,715 $0.10/$0.78 131.1K
131 122141 glm-4.7-flashZ.ai · MIT 1368±6 11,771 $0.06/$0.40 202.8K
132 122140 amazon-nova-experimental-chat-11-10Amazon · Proprietary 1367±4 25,443 N/A N/A
133 126142 gemma-3-27b-itGoogle · Gemma 1366±4 47,584 $0.08/$0.16 131.1K
134 128144 minimax-m1MiniMax · Apache 2.0 1363±4 35,265 $0.40/$2.20 1M
135 128145 o3-mini-highOpenAI · Proprietary 1363±5 18,589 $1.10/$4.40 200K
136 128150 grok-3-mini-highxAI · Proprietary 1362±5 16,982 $0.30/$0.50 131.1K
137 128156 nvidia-nemotron-3-super-120b-a12bNvidia · NVIDIA Open Model 1361±7 7,410 N/A N/A
138 130151 gemini-2.0-flash-001Google · Proprietary 1360±4 43,775 $0.10/$0.40 1M
139 131156 deepseek-v3DeepSeek · DeepSeek 1358±5 21,770 $1.14/$4.56 N/A
140 132158 mistral-small-2506Mistral · Apache 2.0 1357±5 17,725 $0.10/$0.30 32K
141 133158 grok-3-mini-betaxAI · Proprietary 1357±5 22,730 $0.30/$0.50 131.1K
142 130164 intellect-3Prime Intellect · MIT 1357±8 5,337 $0.20/$1.10 131.1K
143 136162 Coherecommand-a-03-2025Cohere · CC-BY-NC-4.0 1354±3 56,352 $2.50/$10 256K
144 136162 gpt-oss-120bOpenAI · Apache 2.0 1353±4 30,681 $0.04/$0.19 131.1K
145 134165 glm-4.5vZ.ai · MIT 1353±8 4,966 $0.60/$1.80 65.5K
146 136163 gemini-2.0-flash-lite-preview-02-05Google · Proprietary 1353±4 24,955 $0.07/$0.30 1M
147 138164 gemini-1.5-pro-002Google · Proprietary 1351±3 55,606 $3.50/$10.50 2.1M
148 138166 amazon-nova-experimental-chat-10-20Amazon · Proprietary 1350±6 11,486 N/A N/A
149 134175 Tencenthunyuan-turbos-20250226Tencent · Proprietary 1349±12 2,220 N/A N/A
150 138170 Stepfunstep-3StepFun · Apache 2.0 1348±7 6,560 $0.57/$1.42 65.5K
151 142165 o3-miniOpenAI · Proprietary 1348±4 57,373 $1.10/$4.40 200K
152 136177 amazon-nova-experimental-chat-10-09Amazon · Proprietary 1347±11 2,840 N/A N/A
153 137175 qwen3-32bAlibaba · Apache 2.0 1347±9 3,926 $0.08/$0.24 41K
154 135178 llama-3.1-nemotron-ultra-253b-v1Nvidia · Nvidia Open Model 1347±12 2,549 $0.60/$1.80 131.1K
155 136177 mercury-2Inception AI · Proprietary 1347±11 3,120 $0.25/$0.75 128K
156 138174 minimax-m2MiniMax · Apache 2.0 1346±8 6,877 $0.26/$1 196.6K
157 140173 ling-flash-2.0Ant Group · MIT 1346±7 7,019 N/A N/A
158 138175 qwen-plus-0125Alibaba · Proprietary 1346±8 5,819 $0.40/$1.20 131.1K
159 145168 gpt-4o-2024-05-13OpenAI · Proprietary 1345±3 112,881 $5/$15 128K
160 140179 nvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia · Nvidia Open 1343±10 3,346 $0.10/$0.40 131.1K
161 142178 glm-4-plus-0111Zhipu · Proprietary 1343±8 5,760 N/A N/A
162 147174 Anthropicclaude-3-5-sonnet-20240620Anthropic · Proprietary 1342±3 82,419 $3/$15 200K
163 142179 gemma-3-12b-itGoogle · Gemma 1342±10 3,829 $0.04/$0.13 131.1K
164 142183 Tencenthunyuan-turbo-0110Tencent · Proprietary 1340±12 2,290 N/A N/A
165 150181 nova-2-liteAmazon · Proprietary 1337±6 12,260 $0.30/$2.50 1M
166 149182 gpt-5-nano-highOpenAI · Proprietary 1337±7 8,281 $0.05/$0.40 400K
167 151179 o1-miniOpenAI · Proprietary 1337±4 51,981 $1.10/$4.40 N/A
168 151180 qwq-32bAlibaba · Apache 2.0 1336±4 25,411 $0.15/$0.58 131.1K
169 153181 grok-2-2024-08-13xAI · Proprietary 1335±4 63,498 $2/$10 131.1K
170 152182 gpt-4o-2024-08-06OpenAI · Proprietary 1335±4 45,499 $2.50/$10 128K
171 152182 gemini-advanced-0514Google · Proprietary 1335±5 50,148 N/A N/A
172 155182 Metallama-3.1-405b-instruct-bf16Meta · Llama 3.1 Community 1335±4 41,375 $4/$4 32.8K
173 150189 Stepfunstep-2-16k-exp-202412StepFun · Proprietary 1334±9 4,833 N/A N/A
174 158183 Metallama-3.1-405b-instruct-fp8Meta · Llama 3.1 Community 1333±4 59,656 $4/$4 32.8K
175 158189 olmo-3.1-32b-instructAi2 · Apache 2.0 1331±6 12,241 $0.20/$0.60 65.5K
176 162193 01.AIyi-lightning01 AI · Proprietary 1328±5 27,332 N/A N/A
177 152204 llama-3.3-nemotron-49b-super-v1Nvidia · Nvidia 1328±12 2,218 N/A N/A
178 144215 molmo-2-8bAi2 · Apache 2.0 1327±21 804 $0.20/$0.20 36.9K
179 165195 qwen3-30b-a3bAlibaba · Apache 2.0 1327±5 26,510 $0.08/$0.28 41K
180 168195 Metallama-4-maverick-17b-128e-instructMeta · Llama 4 1327±4 40,009 $0.63/$1.80 131.1K
181 160204 Tencenthunyuan-large-2025-02-10Tencent · Proprietary 1326±10 3,738 N/A N/A
182 174200 gpt-4-turbo-2024-04-09OpenAI · Proprietary 1324±4 98,114 $10/$30 128K
183 166204 deepseek-v2.5-1210DeepSeek · DeepSeek 1323±8 6,795 N/A N/A
184 174200 gemini-1.5-pro-001Google · Proprietary 1323±4 79,138 $3.50/$10.50 2.1M
185 174200 Anthropicclaude-3-5-haiku-20241022Anthropic · Proprietary 1323±3 70,030 $0.80/$4 200K
186 174201 Metallama-4-scout-17b-16e-instructMeta · Llama 1322±5 30,321 $0.40/$0.70 8.2K
187 172204 gpt-4.1-nano-2025-04-14OpenAI · Proprietary 1322±8 6,103 $0.10/$0.40 1M
188 176201 Anthropicclaude-3-opus-20240229Anthropic · Proprietary 1321±3 194,909 $15/$75 200K
189 174206 ring-flash-2.0Ant Group · MIT 1321±7 7,157 N/A N/A
190 174204 Stepfunstep-1o-turbo-202506StepFun · Proprietary 1320±7 9,044 N/A N/A
191 176204 glm-4-plusZhipu AI · Proprietary 1319±5 26,126 $0.44/$1.76 204.8K
192 177206 gemma-3n-e4b-itGoogle · Gemma 1318±5 22,621 $0.06/$0.12 32.8K
193 179204 Metallama-3.3-70b-instructMeta · Llama-3.3 1318±3 54,758 $0.12/$0.38 131.1K
194 176207 qwen-max-0919Alibaba · Qwen 1318±6 16,478 $1.60/$6.40 32.8K
195 176210 gpt-oss-20bOpenAI · Apache 2.0 1317±6 10,638 $0.03/$0.14 131.1K
196 179204 gpt-4o-mini-2024-07-18OpenAI · Proprietary 1317±4 68,710 $0.15/$0.60 128K
197 177207 nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia · NVIDIA Open Model 1317±6 15,538 $0.06/$0.24 262.1K
198 179212 qwen2.5-plus-1127Alibaba · Proprietary 1315±6 10,187 N/A N/A
199 182211 athene-v2-chatNexusFlow · NexusFlow 1314±5 24,739 N/A N/A
200 184211 mistral-large-2407Mistral · Mistral Research 1314±4 45,459 $2/$6 131.1K
201 184212 gpt-4-0125-previewOpenAI · Proprietary 1313±4 93,439 $10/$30 128K
202 184212 gpt-4-1106-previewOpenAI · Proprietary 1312±4 100,105 $10/$30 128K
203 179216 Tencenthunyuan-standard-2025-02-10Tencent · Proprietary 1311±10 3,904 N/A N/A
204 192215 gemini-1.5-flash-002Google · Proprietary 1309±4 34,902 $0.07/$0.30 1M
205 196215 grok-2-mini-2024-08-13xAI · Proprietary 1308±4 52,567 $2/$10 131.1K
206 196216 deepseek-v2.5DeepSeek · DeepSeek 1307±5 24,572 N/A N/A
207 179224 mercuryInception AI · Proprietary 1307±14 1,959 $0.25/$0.75 128K
208 196216 athene-70b-0725NexusFlow · CC-BY-NC-4.0 1306±6 19,621 N/A N/A
209 192216 olmo-3-32b-thinkAi2 · Apache 2.0 1305±8 5,969 $0.15/$0.50 65.5K
210 199216 mistral-large-2411Mistral · MRL 1305±4 28,073 $2/$6 131.1K
211 197216 magistral-medium-2506Mistral · Proprietary 1304±6 11,651 $2/$5 40K
212 202216 mistral-small-3.1-24b-instruct-2503Mistral · Apache 2.0 1303±5 33,245 $0.10/$0.30 32K
213 194223 gemma-3-4b-itGoogle · Gemma 1303±9 4,171 $0.04/$0.08 131.1K
214 202216 qwen2.5-72b-instructAlibaba · Qwen 1303±4 39,406 $1.20/$1.20 N/A
215 202226 llama-3.1-nemotron-70b-instructNvidia · Llama 3.1 1299±8 7,140 $1.20/$1.20 131.1K
216 205228 Tencenthunyuan-large-visionTencent · Proprietary 1294±9 5,377 N/A N/A
217 213227 Metallama-3.1-70b-instructMeta · Llama 3.1 Community 1293±4 55,240 $0.40/$0.40 131.1K
218 213228 amazon-nova-pro-v1.0Amazon · Proprietary 1290±5 24,745 $0.80/$3.20 300K
219 213231 jamba-1.5-largeAI21 Labs · Jamba Open 1288±7 8,662 $2/$8 256K
220 215228 gemma-2-27b-itGoogle · Gemma license 1288±3 75,754 $0.65/$0.65 8.2K
221 213231 reka-core-20240904Reka AI · Proprietary 1287±7 7,312 N/A N/A
222 213237 ibm-granite-h-smallIBM · Apache 2.0 1287±8 5,695 N/A N/A
223 215231 gpt-4-0314OpenAI · Proprietary 1286±5 54,173 $30/$60 8.2K
224 213237 llama-3.1-tulu-3-70bAi2 · Llama 3.1 1286±10 2,846 N/A N/A
225 213237 llama-3.1-nemotron-51b-instructNvidia · Llama 3.1 1286±10 3,749 N/A N/A
226 214236 olmo-3.1-32b-thinkAi2 · Apache 2.0 1286±7 8,508 $0.15/$0.50 65.5K
227 216231 gemini-1.5-flash-001Google · Proprietary 1285±4 62,833 $0.07/$0.30 1M
228 220237 Anthropicclaude-3-sonnet-20240229Anthropic · Proprietary 1280±4 109,284 $3/$15 200K
229 217237 gemma-2-9b-it-simpoPrinceton · MIT 1279±7 10,072 $0.03/$0.09 8.2K
230 220238 nemotron-4-340b-instructNvidia · NVIDIA Open Model 1277±5 19,659 N/A N/A
231 220240 Coherecommand-r-plus-08-2024Cohere · CC-BY-NC-4.0 1276±7 9,866 $2.50/$10 128K
232 224237 Metallama-3-70b-instructMeta · Llama 3 Community 1275±4 156,876 $0.51/$0.74 8.2K
233 224238 gpt-4-0613OpenAI · Proprietary 1274±4 88,723 $30/$60 8.2K
234 224240 mistral-small-24b-instruct-2501Mistral · Apache 2.0 1274±6 14,681 $0.05/$0.08 32.8K
235 224241 glm-4-0520Zhipu AI · Proprietary 1273±7 9,788 N/A N/A
236 224243 reka-flash-20240904Reka AI · Proprietary 1271±7 7,536 N/A N/A
237 225246 qwen2.5-coder-32b-instructAlibaba · Apache 2.0 1270±8 5,432 $0.87/$0.87 32K
238 231246 Coherec4ai-aya-expanse-32bCohere · CC-BY-NC-4.0 1267±5 27,124 N/A N/A
239 233246 gemma-2-9b-itGoogle · Gemma license 1265±4 54,611 $0.03/$0.09 8.2K
240 233247 deepseek-coder-v2DeepSeek · DeepSeek License 1264±6 15,147 $0.14/$0.28 128K
241 236247 Coherecommand-r-plusCohere · CC-BY-NC-4.0 1261±4 77,554 $2.50/$10 128K
242 235247 qwen2-72b-instructAlibaba · Qianwen LICENSE 1261±5 37,325 $0.90/$0.90 32.8K
243 237247 Anthropicclaude-3-haiku-20240307Anthropic · Proprietary 1260±4 117,701 $0.25/$1.25 200K
244 236248 amazon-nova-lite-v1.0Amazon · Proprietary 1260±5 19,372 $0.06/$0.24 300K
245 237248 gemini-1.5-flash-8b-001Google · Proprietary 1258±4 35,558 $0.07/$0.30 1M
246 240248 phi-4Microsoft · MIT 1256±5 24,126 $0.07/$0.14 16.4K
247 237254 olmo-2-0325-32b-instructAi2 · Apache-2.0 1251±11 3,334 $0.05/$0.20 128K
248 244253 Coherecommand-r-08-2024Cohere · CC-BY-NC-4.0 1249±7 10,140 $0.15/$0.60 128K
249 247257 mistral-large-2402Mistral · Proprietary 1242±5 62,436 $4/$12 32K
250 247257 amazon-nova-micro-v1.0Amazon · Proprietary 1240±5 19,364 $0.04/$0.14 128K
251 247260 jamba-1.5-miniAI21 Labs · Jamba Open 1239±7 8,858 $0.20/$0.40 256K
252 247264 ministral-8b-2410Mistral · MRL 1237±9 4,781 $0.10/$0.10 131.1K
253 248265 gemini-pro-dev-apiGoogle · Proprietary 1235±7 18,354 $0.35/$1.05 32.8K
254 249264 qwen1.5-110b-chatAlibaba · Qianwen LICENSE 1233±6 26,195 N/A N/A
255 247267 Tencenthunyuan-standard-256kTencent · Proprietary 1233±12 2,728 N/A N/A
256 249266 reka-flash-21b-20240226-onlineReka AI · Proprietary 1232±7 15,450 N/A N/A
257 249265 qwen1.5-72b-chatAlibaba · Qianwen LICENSE 1232±5 39,302 N/A N/A
258 251266 mixtral-8x22b-instruct-v0.1Mistral · Apache 2.0 1229±5 51,416 $0.90/$0.90 65.5K
259 252267 Coherecommand-rCohere · CC-BY-NC-4.0 1226±5 54,036 $0.15/$0.60 128K
260 251267 reka-flash-21b-20240226Reka AI · Proprietary 1226±6 24,806 N/A N/A
261 252268 gpt-3.5-turbo-0125OpenAI · Proprietary 1223±5 66,207 $0.50/$1.50 16.4K
262 256267 Metallama-3-8b-instructMeta · Llama 3 Community 1223±4 104,642 $0.03/$0.04 8.2K
263 252269 Coherec4ai-aya-expanse-8bCohere · CC-BY-NC-4.0 1223±7 9,818 N/A N/A
264 254269 mistral-mediumMistral · Proprietary 1222±6 34,550 $2.70/$8.10 32K
265 251271 gemini-proGoogle · Proprietary 1221±12 6,390 $0.35/$1.05 32.8K
266 252271 llama-3.1-tulu-3-8bAi2 · Llama 3.1 1221±11 2,896 N/A N/A
267 263272 01.AIyi-1.5-34b-chat01 AI · Apache-2.0 1213±5 24,146 N/A N/A
268 258274 zephyr-orpo-141b-A35b-v0.1HuggingFace · Apache 2.0 1212±11 4,652 N/A N/A
269 265272 Metallama-3.1-8b-instructMeta · Llama 3.1 Community 1211±4 49,605 $0.02/$0.05 16.4K
270 262278 granite-3.1-8b-instructIBM · Apache 2.0 1208±11 3,090 N/A N/A
271 267278 qwen1.5-32b-chatAlibaba · Qianwen LICENSE 1203±6 21,741 N/A N/A
272 265280 gpt-3.5-turbo-1106OpenAI · Proprietary 1202±9 16,619 $1/$2 16.4K
273 269279 gemma-2-2b-itGoogle · Gemma license 1199±4 46,616 N/A N/A
274 269280 phi-3-medium-4k-instructMicrosoft · MIT 1197±5 25,055 $0.17/$0.68 N/A
275 270280 mixtral-8x7b-instruct-v0.1Mistral · Apache 2.0 1196±4 73,503 $0.63/$0.63 32K
276 270285 dbrx-instruct-previewDatabricks · DBRX LICENSE 1194±6 32,191 $0.60/$0.60 32.8K
277 270289 internlm2_5-20b-chatInternLM · Other 1191±7 9,901 $0/$0 32.8K
278 270289 qwen1.5-14b-chatAlibaba · Qianwen LICENSE 1190±7 17,839 $0.30/$0.30 N/A
279 273295 wizardlm-70bMicrosoft · Llama 2 Community 1184±9 8,214 N/A N/A
280 272296 deepseek-llm-67b-chatDeepSeek · DeepSeek License 1184±12 4,932 N/A N/A
281 276291 01.AIyi-34b-chat01 AI · Yi License 1183±7 15,483 $0.90/$0.90 4.1K
282 276296 openchat-3.5-0106OpenChat · Apache-2.0 1181±8 12,637 N/A N/A
283 276296 openchat-3.5OpenChat · Apache-2.0 1181±10 7,968 $0.20/$0.20 N/A
284 276296 granite-3.0-8b-instructIBM · Apache 2.0 1181±9 6,638 N/A N/A
285 277295 gemma-1.1-7b-itGoogle · Gemma license 1180±6 23,893 $0.03/$0.09 8.2K
286 277296 snowflake-arctic-instructSnowflake · Apache 2.0 1179±6 32,832 N/A N/A
287 276297 granite-3.1-2b-instructIBM · Apache 2.0 1178±11 3,188 N/A N/A
288 277297 tulu-2-dpo-70bAllenAI/UW · AI2 ImpACT Low-risk 1177±10 6,535 N/A N/A
289 277300 openhermes-2.5-mistral-7bNousResearch · Apache-2.0 1174±10 5,006 $0.17/$0.17 N/A
290 279299 vicuna-33bLMSYS · Non-commercial 1172±6 22,479 $0/$0 2K
291 279301 starling-lm-7b-betaNexusflow · Apache-2.0 1171±7 16,056 N/A N/A
292 280300 phi-3-small-8k-instructMicrosoft · MIT 1170±6 17,766 $0.15/$0.60 N/A
293 280300 Metallama-2-70b-chatMeta · Llama 2 Community 1170±6 38,492 $0.70/$2.80 4.1K
294 280303 starling-lm-7b-alphaUC Berkeley · CC-BY-NC-4.0 1167±8 10,224 N/A N/A
295 282303 Metallama-3.2-3b-instructMeta · Llama 3.2 1166±8 7,936 $0.05/$0.34 80K
296 280306 nous-hermes-2-mixtral-8x7b-dpoNousResearch · Apache-2.0 1164±12 3,777 $0.90/$0.90 N/A
297 287313 qwq-32b-previewAlibaba · Apache 2.0 1156±12 3,231 $0.15/$0.58 131.1K
298 293309 granite-3.0-2b-instructIBM · Apache 2.0 1155±8 6,837 N/A N/A
299 289313 llama2-70b-steerlm-chatNvidia · Llama 2 Community 1154±13 3,585 N/A N/A
300 290316 solar-10.7b-instruct-v1.0Upstage AI · CC-BY-NC-4.0 1151±13 4,155 $0.30/$0.30 N/A
301 289318 dolphin-2.2.1-mistral-7bCognitive Computations · Apache-2.0 1151±15 1,679 $0.50/$0.50 16.4K
302 294316 mpt-30b-chatMosaicML · CC-BY-NC-SA-4.0 1149±12 2,572 N/A N/A
303 296313 mistral-7b-instruct-v0.2Mistral · Apache-2.0 1149±7 19,402 $0.20/$0.20 32.8K
304 296314 wizardlm-13bMicrosoft · Llama 2 Community 1148±9 7,044 $0.30/$0.30 N/A
305 293320 falcon-180b-chatTII · Falcon-180B TII License 1146±17 1,295 N/A N/A
306 296319 qwen1.5-7b-chatAlibaba · Qianwen LICENSE 1143±10 4,737 $0.20/$0.20 N/A
307 297318 phi-3-mini-4k-instruct-june-2024Microsoft · MIT 1142±6 12,297 $0.13/$0.52 4.1K
308 297319 Metallama-2-13b-chatMeta · Llama 2 Community 1141±7 19,174 $0.25/$0.25 4.1K
309 298319 vicuna-13bLMSYS · Llama 2 Community 1140±7 19,367 $0.30/$0.30 N/A
310 297321 qwen-14b-chatAlibaba · Qianwen LICENSE 1138±11 4,964 N/A N/A
311 298321 palm-2Google · Proprietary 1137±9 8,554 $0.50/$0.50 25.8K
312 298321 gemma-7b-itGoogle · Gemma license 1136±10 8,925 $0.05/$0.08 8.2K
313 298321 Metacodellama-34b-instructMeta · Llama 2 Community 1136±9 7,366 $0.35/$1.40 16.4K
314 302323 zephyr-7b-betaHuggingFace · MIT 1130±9 11,118 $0.15/$0.15 16.4K
315 304323 phi-3-mini-128k-instructMicrosoft · MIT 1128±7 20,685 $0.13/$0.52 N/A
316 306323 phi-3-mini-4k-instructMicrosoft · MIT 1127±6 20,118 $0.13/$0.52 N/A
317 302326 guanaco-33bUW · Non-commercial 1126±12 2,921 N/A N/A
318 301326 zephyr-7b-alphaHuggingFace · MIT 1126±16 1,785 N/A N/A
319 309326 stripedhyena-nous-7bTogether AI · Apache 2.0 1120±11 5,182 $0.20/$0.20 N/A
320 304327 Metacodellama-70b-instructMeta · Llama 2 Community 1118±18 1,143 $0.70/$2.80 16.4K
321 314326 gemma-1.1-2b-itGoogle · Gemma license 1114±8 10,854 N/A N/A
322 314326 vicuna-7bLMSYS · Llama 2 Community 1114±9 6,923 $0.20/$0.20 N/A
323 310327 smollm2-1.7b-instructHuggingFace · Apache 2.0 1113±14 2,199 N/A N/A
324 317327 Metallama-3.2-1b-instructMeta · Llama 3.2 1110±8 8,045 $0.03/$0.20 60K
325 317327 mistral-7b-instructMistral · Apache 2.0 1109±9 8,977 $0.07/$0.28 4.1K
326 317327 Metallama-2-7b-chatMeta · Llama 2 Community 1107±7 14,148 $0.15/$0.15 4.1K
327 322330 gemma-2b-itGoogle · Gemma license 1091±12 4,780 $0.10/$0.10 N/A
328 327330 qwen1.5-4b-chatAlibaba · Qianwen LICENSE 1089±9 7,597 $0.10/$0.10 N/A
329 327334 olmo-7b-instructAi2 · Apache-2.0 1074±11 6,328 $0.20/$0.20 N/A
330 329334 koala-13bUC Berkeley · Non-commercial 1070±10 6,965 N/A N/A
331 329334 alpaca-13bStanford · Non-commercial 1067±12 5,745 N/A N/A
332 327335 gpt4all-13b-snoozyNomic AI · Non-commercial 1065±15 1,743 N/A N/A
333 329335 mpt-7b-chatMosaicML · CC-BY-NC-SA-4.0 1061±12 3,924 N/A N/A
334 329335 chatglm3-6bTsinghua · Apache-2.0 1055±12 4,658 N/A N/A
335 332337 RWKV-4-Raven-14BRWKV · Apache 2.0 1040±11 4,845 N/A N/A
336 335337 chatglm2-6bTsinghua · Apache-2.0 1023±14 2,658 N/A N/A
337 335337 oasst-pythia-12bOpenAssistant · Apache 2.0 1021±11 6,310 N/A N/A
338 338341 chatglm-6bTsinghua · Non-commercial 995±13 4,914 N/A N/A
339 338341 fastchat-t5-3bLMSYS · Apache 2.0 990±12 4,203 N/A N/A
340 338341 dolly-v2-12bDatabricks · MIT 979±14 3,412 N/A N/A
341 338342 Metallama-13bMeta · Non-commercial 972±16 2,391 $0.23/$0.23 N/A
342 341342 Stabilitystablelm-tuned-alpha-7bStability AI · CC-BY-NC-SA-4.0 952±13 3,287 N/A N/A

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。

results matching ""

    No results matching ""