| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Gemini 4 Argon (High)
Google · Proprietary · Preliminary
|
1519±18.0 |
|
›
🥈
|
Claude Opus 5.5 (High)
Anthropic · Proprietary
|
1502±13.0 |
|
›
🥉
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
1493±7.0 |
|
›
4
|
Claude Opus 4.6 (High)
Anthropic · Proprietary
|
1491±6.0 |
|
›
5
|
Muse Wonder (Max)
Meta · Proprietary
|
1485±17.0 |
|
›
6
|
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
1480±6.0 |
|
›
7
|
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
1478±10.0 |
|
›
8
|
Gemini 3.7 Flash (High)
Google · Proprietary · Preliminary
|
1478±8.0 |
|
›
9
|
Gemini 3.8 Flash (High)
Google · Proprietary · Preliminary
|
1477±7.0 |
|
›
10
|
Claude Opus 4.6
Anthropic · Proprietary
|
1477±6.0 |
|
›
11
|
Claude Opus 4.7
Anthropic · Proprietary
|
1473±6.0 |
|
›
12
|
GPT-5.6 Sol (xHigh)
OpenAI · Proprietary
|
1471±7.0 |
|
›
13
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
1470±5.0 |
|
›
14
|
Gemini 3 Pro
Google · Proprietary
|
1469±7.0 |
|
›
15
|
Claude Sonnet 5.5 (xHigh)
Anthropic · Proprietary
|
1464±14.0 |
|
›
16
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
1463±6.0 |
|
›
17
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
1463±8.0 |
|
›
18
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
1462±7.0 |
|
›
19
|
Muse Spark
Meta · Proprietary
|
1462±12.0 |
|
›
20
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
1461±7.0 |
|
›
21
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
1460±6.0 |
|
›
22
|
Muse Spark 1.3 (Max)
Meta · Proprietary
|
1459±9.0 |
|
›
23
|
Qwen3.8-Max
阿里巴巴 · Proprietary
|
1459±8.0 |
|
›
24
|
GPT-6 Astra (Max)
OpenAI · Proprietary
|
1458±11.0 |
|
›
25
|
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
1457±7.0 |
|
›
26
|
GPT-6.1 Sol (Max)
OpenAI · Proprietary
|
1457±15.0 |
|
›
27
|
Claude Opus 4.5 (High, 32K, 20251101)
Anthropic · Proprietary
|
1456±8.0 |
|
›
28
|
Claude Opus 4.5 (20251101)
Anthropic · Proprietary
|
1454±6.0 |
|
›
29
|
Gemini 3.5 Flash (High)
Google · Proprietary
|
1454±7.0 |
|
›
30
|
Claude Opus 4.8
Anthropic · Proprietary
|
1454±6.0 |
|
›
31
|
Gemini 3 Flash
Google · Proprietary
|
1454±8.0 |
|
›
32
|
GPT-5.5 Instant
OpenAI · Proprietary
|
1452±9.0 |
|
›
33
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1451±13.0 |
|
›
34
|
DeepSeek-V4.1-Flash-20260910 (Max)
DeepSeek · MIT
|
1450±11.0 |
|
›
35
|
Grok 4.20 Beta 1
SpaceXAI · Proprietary
|
1449±9.0 |
|
›
36
|
GPT-5.5 (High)
OpenAI · Proprietary
|
1449±6.0 |
|
›
37
|
Muse Spark 1.1
Meta · Proprietary
|
1449±7.0 |
|
›
38
|
GLM-5.3 (Max)
智谱 ZAI · MIT
|
1448±8.0 |
|
›
39
|
GPT-5.5
OpenAI · Proprietary
|
1447±6.0 |
|
›
40
|
MiMo-V2.6-Pro
小米 · MIT
|
1447±20.0 |
|
›
41
|
GLM-5.2 (Max)
智谱 ZAI · MIT
|
1447±6.0 |
|
›
42
|
Grok 4.5
SpaceXAI · Proprietary
|
1446±7.0 |
|
›
43
|
Claude Sonnet 4.5 (High, 32K, 20250929)
Anthropic · Proprietary
|
1446±5.0 |
|
›
44
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
1445±6.0 |
|
›
45
|
Grok 4.20 Beta (Reasoning, 0309)
SpaceXAI · Proprietary
|
1445±6.0 |
|
›
46
|
Qwen3.5-Max-Preview
阿里巴巴 · Proprietary
|
1444±10.0 |
|
›
47
|
Claude Sonnet 4.5 (20250929)
Anthropic · Proprietary
|
1443±5.0 |
|
›
48
|
Qwen3.7-Max-Preview
阿里巴巴 · Proprietary
|
1442±22.0 |
|
›
49
|
GPT-5.4 (High)
OpenAI · Proprietary
|
1441±6.0 |
|
›
50
|
GLM-5.1
智谱 ZAI · MIT
|
1441±6.0 |
|
›
51
|
Grok 4.6 (High)
SpaceXAI · Proprietary
|
1440±8.0 |
|
›
52
|
Grok 4.20 Multi-Agent Beta (0309)
SpaceXAI · Proprietary
|
1440±6.0 |
|
›
53
|
Gemini 3 Flash (Minimal)
Google · Proprietary
|
1438±5.0 |
|
›
54
|
GLM-5
智谱 ZAI · MIT
|
1438±8.0 |
|
›
55
|
GLM-5.3-Flash
智谱 ZAI · MIT
|
1437±7.0 |
|
›
56
|
MiMo-V2.5-Pro
小米 · MIT
|
1437±6.0 |
|
›
57
|
GPT-5.2 Chat (20260210)
OpenAI · Proprietary
|
1437±8.0 |
|
›
58
|
GPT-4.5 Preview (2025-02-27)
OpenAI · Proprietary
|
1435±12.0 |
|
›
59
|
DeepSeek-V4-Pro
DeepSeek · MIT
|
1435±7.0 |
|
›
60
|
DeepSeek-V4-Pro (High, 20260813)
DeepSeek · MIT
|
1435±13.0 |
|
›
61
|
Claude Opus 4.1 (Thinking 16K, 20250805)
Anthropic · Proprietary
|
1435±7.0 |
|
›
62
|
Claude Opus 4.1 (20250805)
Anthropic · Proprietary
|
1434±6.0 |
|
›
63
|
GPT-5.6 Terra (xHigh)
OpenAI · Proprietary
|
1434±7.0 |
|
›
64
|
Gemini 3.5 Flash-Lite
Google · Proprietary
|
1434±7.0 |
|
›
65
|
Grok 4.1 (Thinking)
SpaceXAI · Proprietary
|
1434±6.0 |
|
›
66
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
1432±6.0 |
|
›
67
|
DeepSeek-V4-Pro Preview (High)
DeepSeek · MIT
|
1432±7.0 |
|
›
68
|
GPT-5.4
OpenAI · Proprietary
|
1432±6.0 |
|
›
69
|
GPT-6 Sol (Max)
OpenAI · Proprietary
|
1431±11.0 |
|
›
70
|
Gemini 2.5 Pro
Google · Proprietary
|
1430±5.0 |
|
›
71
|
Kimi K2.6
月之暗面 · Modified MIT
|
1430±8.0 |
|
›
72
|
Grok 4.1
SpaceXAI · Proprietary
|
1429±6.0 |
|
›
73
|
ERNIE 5.1
百度 · Proprietary
|
1428±8.0 |
|
›
74
|
Qwen3.6-Max-Preview
阿里巴巴 · Proprietary
|
1427±19.0 |
|
›
75
|
MiMo-V2-Pro
小米 · Proprietary
|
1426±9.0 |
|
›
76
|
ChatGPT-4o Latest (20250326)
OpenAI · Proprietary
|
1424±5.0 |
|
›
77
|
GPT-5.1 (High)
OpenAI · Proprietary
|
1422±7.0 |
|
›
78
|
Claude Opus 4 (Thinking 16K, 20250514)
Anthropic · Proprietary
|
1422±8.0 |
|
›
79
|
Kimi K2.5 (Thinking)
月之暗面 · Modified MIT
|
1421±6.0 |
|
›
80
|
Qwen3.7-Plus
阿里巴巴 · Proprietary
|
1418±7.0 |
|
›
81
|
Hy3
腾讯 · Apache 2.0
|
1418±11.0 |
|
›
82
|
GPT-5.6 Luna (xHigh)
OpenAI · Proprietary
|
1417±7.0 |
|
›
83
|
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
1417±11.0 |
|
›
84
|
Gemma 4 31B
Google · Apache 2.0
|
1416±18.0 |
|
›
85
|
Grok 4.3
SpaceXAI · Proprietary
|
1416±6.0 |
|
›
86
|
GPT-5.3 Chat
OpenAI · Proprietary
|
1415±8.0 |
|
›
87
|
GPT-6 Luna (Max)
OpenAI · Proprietary
|
1414±6.0 |
|
›
88
|
Dola Seed 2.0 Pro
字节跳动 · Proprietary
|
1414±6.0 |
|
›
89
|
Step 5 Preview
阶跃星辰 · Proprietary
|
1412±13.0 |
|
›
90
|
ERNIE 5.0 (0110)
百度 · Proprietary
|
1412±7.0 |
|
›
91
|
ERNIE-5.0-Preview (1203)
百度 · Proprietary
|
1410±13.0 |
|
›
92
|
DeepSeek-V3.2-Exp
DeepSeek · MIT
|
1409±12.0 |
|
›
93
|
GPT-5.4 mini (High)
OpenAI · Proprietary
|
1409±6.0 |
|
›
94
|
DeepSeek-V4-Flash Preview (High)
DeepSeek · MIT
|
1408±7.0 |
|
›
95
|
Kimi K2.5 (Instant)
月之暗面 · Modified MIT
|
1408±15.0 |
|
›
96
|
GPT-5.1
OpenAI · Proprietary
|
1408±7.0 |
|
›
97
|
MiniMax-M3
MiniMax · MiniMax Community License
|
1407±6.0 |
|
›
98
|
Gemma 4 26B A4B
Google · Apache 2.0
|
1407±18.0 |
|
›
99
|
Qwen3.6-Plus
阿里巴巴 · Proprietary
|
1406±7.0 |
|
›
100
|
MiMo-V2.6-Flash
小米 · MIT
|
1406±12.0 |
|
›
101
|
GLM-4.7
智谱 ZAI · MIT
|
1405±12.0 |
|
›
102
|
DeepSeek-V4-Flash
DeepSeek · MIT
|
1405±7.0 |
|
›
103
|
Gemini 3.1 Flash-Lite Preview
Google · Proprietary
|
1404±6.0 |
|
›
104
|
Qwen3.5-397B-A17B
阿里巴巴 · Apache 2.0
|
1403±5.0 |
|
›
105
|
MiMo-V2.5
小米 · MIT
|
1403±7.0 |
|
›
106
|
Grok 4.1 Fast (Reasoning)
SpaceXAI · Proprietary
|
1403±6.0 |
|
›
107
|
Beam 1.0 501B A23B
Reflection · Apache 2.0
|
1403±18.0 |
|
›
108
|
MiMo-V2-Omni
小米 · Proprietary
|
1402±10.0 |
|
›
109
|
Claude Opus 4 (20250514)
Anthropic · Proprietary
|
1401±7.0 |
|
›
110
|
GPT-4.1 (2025-04-14)
OpenAI · Proprietary
|
1401±7.0 |
|
›
111
|
GPT-5.2
OpenAI · Proprietary
|
1399±6.0 |
|
›
112
|
GLM-5V-Turbo
智谱 ZAI · Proprietary
|
1399±12.0 |
|
›
113
|
GPT-5 (High)
OpenAI · Proprietary
|
1398±8.0 |
|
›
114
|
Qwen3-Max-Preview
阿里巴巴 · Proprietary
|
1397±9.0 |
|
›
115
|
LongCat-Flash-Chat Exp (2602)
美团 · Proprietary
|
1397±8.0 |
|
›
116
|
Grok 3 Preview (02-24)
SpaceXAI · Proprietary
|
1397±8.0 |
|
›
117
|
Mistral Medium 3.5
Mistral · Modified MIT
|
1396±12.0 |
|
›
118
|
DeepSeek-V3.2
DeepSeek · MIT
|
1396±7.0 |
|
›
119
|
GLM-4.6
智谱 ZAI · MIT
|
1395±7.0 |
|
›
120
|
o3 (2025-04-16)
OpenAI · Proprietary
|
1395±6.0 |
|
›
121
|
Kimi K2 Thinking Turbo
月之暗面 · Modified MIT
|
1394±6.0 |
|
›
122
|
DeepSeek-V3.1 (Thinking)
DeepSeek · MIT
|
1393±13.0 |
|
›
123
|
Inkling
Thinky · Apache 2.0
|
1392±7.0 |
|
›
124
|
ERNIE-5.0-Preview (1022)
百度 · Proprietary
|
1391±19.0 |
|
›
125
|
o1 (2024-12-17)
OpenAI · Proprietary
|
1390±8.0 |
|
›
126
|
Qwen3-Max (2025-09-23)
阿里巴巴 · Proprietary
|
1390±14.0 |
|
›
127
|
GPT-5 Chat
OpenAI · Proprietary
|
1389±8.0 |
|
›
128
|
DeepSeek-V3.2-Exp (Thinking)
DeepSeek · MIT
|
1389±14.0 |
|
›
129
|
Claude Sonnet 4 (Thinking 32K, 20250514)
Anthropic · Proprietary
|
1389±8.0 |
|
›
130
|
DeepSeek-V3.2 (Thinking)
DeepSeek · MIT
|
1389±7.0 |
|
›
131
|
DeepSeek-R1 (0528)
DeepSeek · MIT
|
1388±11.0 |
|
›
132
|
Claude Haiku 4.5 (20251001)
Anthropic · Proprietary
|
1388±4.0 |
|
›
133
|
GPT-5.2 (High)
OpenAI · Proprietary
|
1388±7.0 |
|
›
134
|
DeepSeek-V3.1-Terminus (Thinking)
DeepSeek · MIT
|
1387±24.0 |
|
›
135
|
Gemini 2.5 Flash
Google · Proprietary
|
1386±4.0 |
|
›
136
|
Grok 4 (0709)
SpaceXAI · Proprietary
|
1386±7.0 |
|
›
137
|
Claude 3.7 Sonnet (Thinking 32K, 20250219)
Anthropic · Proprietary
|
1386±8.0 |
|
›
138
|
Grok 4 Fast (Non-Reasoning)
SpaceXAI · Proprietary
|
1384±17.0 |
|
›
139
|
DeepSeek-V3 (0324)
DeepSeek · MIT
|
1383±7.0 |
|
›
140
|
GLM-4.5
智谱 ZAI · MIT
|
1383±9.0 |
|
›
141
|
Qwen3.8-27B
阿里巴巴 · Apache 2.0
|
1382±8.0 |
|
›
142
|
Kimi K2 Preview (0711)
月之暗面 · Modified MIT
|
1382±9.0 |
|
›
143
|
Gemini 2.5 Flash Preview (09-2025)
Google · Proprietary
|
1380±8.0 |
|
›
144
|
Kimi K2 Preview (0905)
月之暗面 · Modified MIT
|
1380±13.0 |
|
›
145
|
NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)
NVIDIA · OpenMDW-1.1
|
1379±12.0 |
|
›
146
|
Mistral Large 4
Mistral · Proprietary
|
1378±13.0 |
|
›
147
|
DeepSeek-V3.1-Terminus
DeepSeek · MIT
|
1378±23.0 |
|
›
148
|
DeepSeek-V3.1
DeepSeek · MIT
|
1377±11.0 |
|
›
149
|
Muse Glimmer
Meta · Apache-2.0
|
1376±20.0 |
|
›
150
|
Qwen3-235B-A22B-Instruct (2507)
阿里巴巴 · Apache 2.0
|
1376±5.0 |
|
›
151
|
Claude Sonnet 4 (20250514)
Anthropic · Proprietary
|
1376±8.0 |
|
›
152
|
Mistral Medium 3.1 (2508)
Mistral · Proprietary
|
1374±5.0 |
|
›
153
|
Mistral Large 3
Mistral · Apache 2.0
|
1373±5.0 |
|
›
154
|
MiniMax-M2.7
MiniMax · Modified MIT
|
1373±6.0 |
|
›
155
|
Hunyuan Vision 1.5 Thinking
腾讯 · Proprietary
|
1373±29.0 |
|
›
156
|
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
NVIDIA · OpenMDW-1.1 · Preliminary
|
1373±19.0 |
|
›
157
|
DeepSeek-R1
DeepSeek · MIT
|
1372±10.0 |
|
›
158
|
o1-preview
OpenAI · Proprietary
|
1372±10.0 |
|
›
159
|
Claude 3.7 Sonnet (20250219)
Anthropic · Proprietary
|
1372±7.0 |
|
›
160
|
amazon-nova-experimental-chat (26-01-10)
Amazon · Proprietary
|
1369±23.0 |
|
›
161
|
amazon-nova-experimental-chat (26-02-10)
Amazon · Proprietary
|
1368±24.0 |
|
›
162
|
Grok 4 Fast (Reasoning)
SpaceXAI · Proprietary
|
1368±10.0 |
|
›
163
|
Claude 3.5 Sonnet (20241022)
Anthropic · Proprietary
|
1365±6.0 |
|
›
164
|
Hy3 preview
腾讯 · tencent-hunyuan-community
|
1364±17.0 |
|
›
165
|
Qwen3.5-122B-A10B
阿里巴巴 · Apache 2.0
|
1364±8.0 |
|
›
166
|
Qwen3.5-27B
阿里巴巴 · Apache 2.0
|
1362±8.0 |
|
›
167
|
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Google · Proprietary
|
1361±8.0 |
|
›
168
|
MiniMax-M2.5
MiniMax · Modified MIT
|
1361±7.0 |
|
›
169
|
Qwen3-VL-235B-A22B-Thinking
阿里巴巴 · Apache 2.0
|
1360±15.0 |
|
›
170
|
Qwen3-235B-A22B (Non-Thinking)
阿里巴巴 · Apache 2.0
|
1358±8.0 |
|
›
171
|
Qwen3-VL-235B-A22B-Instruct
阿里巴巴 · Apache 2.0
|
1357±14.0 |
|
›
172
|
MiMo-V2-Flash (Non-Thinking)
小米 · MIT
|
1355±7.0 |
|
›
173
|
Mistral Medium 3 (2505)
Mistral · Proprietary
|
1355±8.0 |
|
›
174
|
Qwen3-Coder-480B-A35B-Instruct
阿里巴巴 · Apache 2.0
|
1353±9.0 |
|
›
175
|
GPT-5.4 nano (High)
OpenAI · Proprietary
|
1352±7.0 |
|
›
176
|
Trinity Large Preview
· Apache 2.0
|
1352±8.0 |
|
›
177
|
GLM-4.6V
智谱 ZAI · MIT
|
1351±26.0 |
|
›
178
|
MiniMax-M2.1 Preview
MiniMax · MIT
|
1351±10.0 |
|
›
179
|
Qwen3-235B-A22B-Thinking (2507)
阿里巴巴 · Apache 2.0
|
1350±15.0 |
|
›
180
|
o4-mini (2025-04-16)
OpenAI · Proprietary
|
1349±7.0 |
|
›
181
|
DeepSeek-V3
DeepSeek · DeepSeek
|
1348±9.0 |
|
›
182
|
Step-3.5-Flash
阶跃星辰 · Apache 2.0
|
1348±6.0 |
|
›
183
|
GPT-5 mini (High)
OpenAI · Proprietary
|
1348±9.0 |
|
›
184
|
GPT-4.1 mini (2025-04-14)
OpenAI · Proprietary
|
1348±8.0 |
|
›
185
|
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Google · Proprietary
|
1347±7.0 |
|
›
186
|
Qwen3.5-35B-A3B
阿里巴巴 · Apache 2.0
|
1345±8.0 |
|
›
187
|
MiMo-V2-Flash (Thinking)
小米 · MIT
|
1344±13.0 |
|
›
188
|
Qwen3.5-Flash
阿里巴巴 · Proprietary
|
1344±6.0 |
|
›
189
|
Gemini 2.0 Flash (001)
Google · Proprietary
|
1342±7.0 |
|
›
190
|
Qwen2.5-Max
阿里巴巴 · Proprietary
|
1339±8.0 |
|
›
191
|
Hunyuan T1 (20250711)
腾讯 · Proprietary
|
1339±20.0 |
|
›
192
|
Inkling-Small
Thinky · Apache 2.0
|
1339±7.0 |
|
›
193
|
LongCat-Flash-Chat
美团 · MIT
|
1338±13.0 |
|
›
194
|
GPT-4o (2024-05-13)
OpenAI · Proprietary
|
1338±7.0 |
|
›
195
|
Gemini Advanced (0514)
Google · Proprietary
|
1337±10.0 |
|
›
196
|
Gemini 1.5 Pro (002)
Google · Proprietary
|
1337±7.0 |
|
›
197
|
Hunyuan TurboS (20250416)
腾讯 · Proprietary
|
1335±14.0 |
|
›
198
|
Qwen3-30B-A3B-Instruct (2507)
阿里巴巴 · Apache 2.0
|
1331±9.0 |
|
›
199
|
Command A (03-2025)
Cohere · CC-BY-NC-4.0
|
1330±6.0 |
|
›
200
|
Solar Pro 4
Upstage · Proprietary
|
1330±9.0 |
|
›
201
|
Grok 3 Mini (High)
SpaceXAI · Proprietary
|
1329±11.0 |
|
›
202
|
Gemma 3 27B IT
Google · Gemma
|
1327±7.0 |
|
›
203
|
Gemini 2.0 Flash-Lite Preview (02-05)
Google · Proprietary
|
1327±9.0 |
|
›
204
|
MiniMax-M1
MiniMax · Apache 2.0
|
1325±8.0 |
|
›
205
|
GLM-4.5-Air
智谱 ZAI · MIT
|
1325±8.0 |
|
›
206
|
GPT-4o (2024-08-06)
OpenAI · Proprietary
|
1325±8.0 |
|
›
207
|
Qwen3-Next-80B-A3B-Instruct
阿里巴巴 · Apache 2.0
|
1325±9.0 |
|
›
208
|
Grok 3 Mini Beta
SpaceXAI · Proprietary
|
1325±10.0 |
|
›
209
|
Step-3
阶跃星辰 · Apache 2.0
|
1325±17.0 |
|
›
210
|
Trinity Large Thinking
· Apache 2.0
|
1325±8.0 |
|
›
211
|
Mistral Small 3.2 (2506)
Mistral · Apache 2.0
|
1324±10.0 |
|
›
212
|
Qwen3-235B-A22B
阿里巴巴 · Apache 2.0
|
1323±9.0 |
|
›
213
|
GLM-4.5V
智谱 ZAI · MIT
|
1321±19.0 |
|
›
214
|
amazon-nova-experimental-chat (12-10)
Amazon · Proprietary
|
1321±21.0 |
|
›
215
|
GLM-4.7-Flash
智谱 ZAI · MIT
|
1316±13.0 |
|
›
216
|
NVIDIA-Nemotron-3-Super-120B-A12B
NVIDIA · NVIDIA Open Model
|
1316±16.0 |
|
›
217
|
Qwen3-Next-80B-A3B-Thinking
阿里巴巴 · Apache 2.0
|
1316±12.0 |
|
›
218
|
Grok 2 (2024-08-13)
SpaceXAI · Proprietary
|
1315±7.0 |
|
›
219
|
GPT-4 Turbo (2024-04-09)
OpenAI · Proprietary
|
1314±7.0 |
|
›
220
|
amazon-nova-experimental-chat (11-10)
Amazon · Proprietary
|
1314±9.0 |
|
›
221
|
Claude 3.5 Sonnet (20240620)
Anthropic · Proprietary
|
1312±7.0 |
|
›
222
|
o3-mini (High)
OpenAI · Proprietary
|
1310±10.0 |
|
›
223
|
Gemini 1.5 Pro (001)
Google · Proprietary
|
1309±8.0 |
|
›
224
|
Mercury 2
Inception AI · Proprietary
|
1308±23.0 |
|
›
225
|
INTELLECT-3
· MIT
|
1306±18.0 |
|
›
226
|
Gemma 3 12B IT
Google · Gemma
|
1306±21.0 |
|
›
227
|
Llama 3.3 Nemotron Super 49B v1
NVIDIA · Nvidia
|
1305±27.0 |
|
›
228
|
Claude 3.5 Haiku (20241022)
Anthropic · Proprietary
|
1305±6.0 |
|
›
229
|
Llama 3.1 405B Instruct (FP8)
Meta · Llama 3.1 Community
|
1304±7.0 |
|
›
230
|
Llama 3.1 Nemotron Ultra 253B v1
NVIDIA · Nvidia Open Model
|
1302±24.0 |
|
›
231
|
DeepSeek-V2.5 (1210)
DeepSeek · DeepSeek
|
1302±16.0 |
|
›
232
|
Hunyuan Large (2025-02-10)
腾讯 · Proprietary
|
1302±22.0 |
|
›
233
|
o3-mini
OpenAI · Proprietary
|
1301±6.0 |
|
›
234
|
Step-2 16K Exp (202412)
阶跃星辰 · Proprietary
|
1301±18.0 |
|
›
235
|
Hunyuan Turbo (0110)
腾讯 · Proprietary
|
1301±25.0 |
|
›
236
|
GLM-4-Plus (0111)
智谱 ZAI · Proprietary
|
1300±17.0 |
|
›
237
|
amazon-nova-experimental-chat (10-20)
Amazon · Proprietary
|
1298±13.0 |
|
›
238
|
MiniMax-M2
MiniMax · Apache 2.0
|
1297±17.0 |
|
›
239
|
Llama 3.1 405B Instruct (BF16)
Meta · Llama 3.1 Community
|
1296±7.0 |
|
›
240
|
NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
NVIDIA · OpenMDW-1.1
|
1296±10.0 |
|
›
241
|
Llama 4 Maverick 17B 128E Instruct
Meta · Llama 4
|
1295±8.0 |
|
›
242
|
Olmo 3.1 32B Instruct
Allen AI · Apache 2.0
|
1294±13.0 |
|
›
243
|
Yi Lightning
· Proprietary
|
1294±10.0 |
|
›
244
|
Qwen-Plus (0125)
阿里巴巴 · Proprietary
|
1294±17.0 |
|
›
245
|
Mistral Large 2 (2407)
Mistral · Mistral Research
|
1290±8.0 |
|
›
246
|
GPT-4 Turbo Preview (1106)
OpenAI · Proprietary
|
1290±8.0 |
|
›
247
|
Llama 3.3 Nemotron Super 49B v1.5
NVIDIA · Nvidia Open
|
1289±23.0 |
|
›
248
|
Llama 4 Scout 17B 16E Instruct
Meta · Llama
|
1289±9.0 |
|
›
249
|
amazon-nova-experimental-chat (10-09)
Amazon · Proprietary
|
1288±24.0 |
|
›
250
|
Magistral Medium (2506)
Mistral · Proprietary
|
1288±14.0 |
|
›
251
|
GPT-4 Turbo Preview (0125)
OpenAI · Proprietary
|
1288±8.0 |
|
›
252
|
GPT-4.1 nano (2025-04-14)
OpenAI · Proprietary
|
1287±17.0 |
|
›
253
|
gpt-oss-120b
OpenAI · Apache 2.0
|
1287±8.0 |
|
›
254
|
Hunyuan TurboS (20250226)
腾讯 · Proprietary
|
1286±25.0 |
|
›
255
|
QwQ-32B
阿里巴巴 · Apache 2.0
|
1286±9.0 |
|
›
256
|
Qwen3-32B
阿里巴巴 · Apache 2.0
|
1285±21.0 |
|
›
257
|
Llama 3.3 70B Instruct
Meta · Llama-3.3
|
1285±6.0 |
|
›
258
|
Claude 3 Opus (20240229)
Anthropic · Proprietary
|
1284±6.0 |
|
›
259
|
GPT-4o mini (2024-07-18)
OpenAI · Proprietary
|
1284±7.0 |
|
›
260
|
Amazon Nova 2 Lite
Amazon · Proprietary
|
1283±13.0 |
|
›
261
|
o1-mini
OpenAI · Proprietary
|
1282±7.0 |
|
›
262
|
GLM-4-Plus
智谱 ZAI · Proprietary
|
1280±10.0 |
|
›
263
|
Qwen-Max (0919)
阿里巴巴 · Qwen
|
1280±12.0 |
|
›
264
|
Gemma 3n E4B IT
Google · Gemma
|
1279±10.0 |
|
›
265
|
Step-1o Turbo (202506)
阶跃星辰 · Proprietary
|
1279±15.0 |
|
›
266
|
GPT-5 nano (High)
OpenAI · Proprietary
|
1277±16.0 |
|
›
267
|
Mistral Small 3.1 24B Instruct (2503)
Mistral · Apache 2.0
|
1276±8.0 |
|
›
268
|
Granite 4.2 30B
IBM · Apache 2.0
|
1276±23.0 |
|
›
269
|
Ling-flash-2.0
蚂蚁集团 · MIT
|
1275±17.0 |
|
›
270
|
Gemini 1.5 Flash (002)
Google · Proprietary
|
1273±8.0 |
|
›
271
|
Gemma 2 27B IT
Google · Gemma license
|
1273±6.0 |
|
›
272
|
Mistral Large (2411)
Mistral · MRL
|
1271±8.0 |
|
›
273
|
Ring-flash-2.0
蚂蚁集团 · MIT
|
1271±16.0 |
|
›
274
|
Athene 70B (0725)
· CC-BY-NC-4.0
|
1271±11.0 |
|
›
275
|
Olmo 3 32B Think
Allen AI · Apache 2.0
|
1271±18.0 |
|
›
276
|
Jamba 1.5 Large
· Jamba Open
|
1270±15.0 |
|
›
277
|
Qwen3-30B-A3B
阿里巴巴 · Apache 2.0
|
1270±9.0 |
|
›
278
|
GPT-4 (0613)
OpenAI · Proprietary
|
1269±8.0 |
|
›
279
|
Gemma 2 9B IT SimPO
· MIT
|
1269±14.0 |
|
›
280
|
Llama 3.1 Nemotron 70B Instruct
NVIDIA · Llama 3.1
|
1268±19.0 |
|
›
281
|
GPT-4 (0314)
OpenAI · Proprietary
|
1264±10.0 |
|
›
282
|
Llama 3.1 70B Instruct
Meta · Llama 3.1 Community
|
1264±7.0 |
|
›
283
|
DeepSeek-V2.5
DeepSeek · DeepSeek
|
1264±10.0 |
|
›
284
|
Grok 2 mini (2024-08-13)
SpaceXAI · Proprietary
|
1264±7.0 |
|
›
285
|
Llama 3.1 Tulu 3 70B
Allen AI · Llama 3.1
|
1260±22.0 |
|
›
286
|
Granite-4.0-H-Small
IBM · Apache 2.0
|
1259±20.0 |
|
›
287
|
Hunyuan Standard (2025-02-10)
腾讯 · Proprietary
|
1259±22.0 |
|
›
288
|
Command R+ (08-2024)
Cohere · CC-BY-NC-4.0
|
1258±15.0 |
|
›
289
|
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
NVIDIA · NVIDIA Open Model
|
1258±11.0 |
|
›
290
|
Olmo 3.1 32B Think
Allen AI · Apache 2.0
|
1257±15.0 |
|
›
291
|
gpt-oss-20b
OpenAI · Apache 2.0
|
1256±15.0 |
|
›
292
|
Gemini 1.5 Flash (001)
Google · Proprietary
|
1256±8.0 |
|
›
293
|
Granite 4.1 8B
IBM · Apache 2.0
|
1255±22.0 |
|
›
294
|
Qwen2.5-Plus (1127)
阿里巴巴 · Proprietary
|
1254±13.0 |
|
›
295
|
Hunyuan Large Vision
腾讯 · Proprietary
|
1254±20.0 |
|
›
296
|
Nemotron-4 340B Instruct
NVIDIA · NVIDIA Open Model
|
1254±11.0 |
|
›
297
|
OLMo 2 32B Instruct (0325)
Allen AI · Apache-2.0
|
1253±23.0 |
|
›
298
|
Llama 3.1 Nemotron 51B Instruct
NVIDIA · Llama 3.1
|
1251±24.0 |
|
›
299
|
Llama 3 70B Instruct
Meta · Llama 3 Community
|
1250±7.0 |
|
›
300
|
Athene V2 Chat
NexusFlow · —
|
1249±9.0 |
|
›
301
|
Gemma 2 9B IT
Google · Gemma license
|
1248±7.0 |
|
›
302
|
Gemma 3 4B IT
Google · Gemma
|
1248±21.0 |
|
›
303
|
Reka Core (20240904)
· Proprietary
|
1247±17.0 |
|
›
304
|
Qwen2.5-72B-Instruct
阿里巴巴 · Qwen
|
1245±8.0 |
|
›
305
|
Mercury
Inception AI · Proprietary
|
1245±32.0 |
|
›
306
|
Amazon Nova Pro 1.0
Amazon · Proprietary
|
1240±9.0 |
|
›
307
|
Claude 3 Sonnet (20240229)
Anthropic · Proprietary
|
1239±8.0 |
|
›
308
|
Command R+
Cohere · CC-BY-NC-4.0
|
1238±8.0 |
|
›
309
|
Granite 4.2 8B
IBM · Apache 2.0
|
1236±23.0 |
|
›
310
|
GLM-4 (0520)
智谱 ZAI · Proprietary
|
1234±15.0 |
|
›
311
|
Reka Flash (20240904)
· Proprietary
|
1228±17.0 |
|
›
312
|
Mistral Small 24B Instruct (2501)
Mistral · Apache 2.0
|
1225±12.0 |
|
›
313
|
Qwen2-72B-Instruct
阿里巴巴 · Qianwen LICENSE
|
1222±9.0 |
|
›
314
|
Aya Expanse 32B
Cohere · CC-BY-NC-4.0
|
1221±9.0 |
|
›
315
|
Claude 3 Haiku (20240307)
Anthropic · Proprietary
|
1221±7.0 |
|
›
316
|
Gemini 1.5 Flash-8B (001)
Google · Proprietary
|
1217±8.0 |
|
›
317
|
Command R (08-2024)
Cohere · CC-BY-NC-4.0
|
1215±14.0 |
|
›
318
|
Granite 4.2 3B
IBM · Apache 2.0
|
1214±25.0 |
|
›
319
|
Mistral Large (2402)
Mistral · Proprietary
|
1213±9.0 |
|
›
320
|
DeepSeek-Coder-V2
DeepSeek · DeepSeek License
|
1213±12.0 |
|
›
321
|
Jamba 1.5 Mini
· Jamba Open
|
1210±15.0 |
|
›
322
|
Amazon Nova Lite 1.0
Amazon · Proprietary
|
1207±10.0 |
|
›
323
|
Phi-4
Microsoft · MIT
|
1202±9.0 |
|
›
324
|
Mixtral 8x22B Instruct v0.1
Mistral · Apache 2.0
|
1202±9.0 |
|
›
325
|
Reka Flash 21B (Online, 20240226)
· Proprietary
|
1198±14.0 |
|
›
326
|
GPT-3.5 Turbo (0125)
OpenAI · Proprietary
|
1197±9.0 |
|
›
327
|
Command R
Cohere · CC-BY-NC-4.0
|
1194±9.0 |
|
›
328
|
Amazon Nova Micro 1.0
Amazon · Proprietary
|
1193±10.0 |
|
›
329
|
Qwen1.5-110B-Chat
阿里巴巴 · Qianwen LICENSE
|
1192±11.0 |
|
›
330
|
Zephyr ORPO 141B A35B v0.1
· Apache 2.0
|
1190±23.0 |
|
›
331
|
Ministral 8B (2410)
Mistral · MRL
|
1190±20.0 |
|
›
332
|
Mistral Medium
Mistral · Proprietary
|
1190±11.0 |
|
›
333
|
Gemini Pro (Dev API)
Google · Proprietary
|
1188±14.0 |
|
›
334
|
Llama 3 8B Instruct
Meta · Llama 3 Community
|
1188±8.0 |
|
›
335
|
Qwen1.5-72B-Chat
阿里巴巴 · Qianwen LICENSE
|
1187±10.0 |
|
›
336
|
Qwen2.5-Coder-32B-Instruct
阿里巴巴 · Apache 2.0
|
1187±19.0 |
|
›
337
|
Hunyuan Standard 256K
腾讯 · Proprietary
|
1186±29.0 |
|
›
338
|
Aya Expanse 8B
Cohere · CC-BY-NC-4.0
|
1181±14.0 |
|
›
339
|
Llama 3.1 Tulu 3 8B
Allen AI · Llama 3.1
|
1179±23.0 |
|
›
340
|
Gemini Pro
Google · Proprietary
|
1177±21.0 |
|
›
341
|
WizardLM 70B
Microsoft · Llama 2 Community
|
1176±17.0 |
|
›
342
|
Llama 3.1 8B Instruct
Meta · Llama 3.1 Community
|
1174±8.0 |
|
›
343
|
OpenChat 3.5
· Apache-2.0
|
1172±17.0 |
|
›
344
|
Gemma 2 2B IT
Google · Gemma license
|
1172±8.0 |
|
›
345
|
Tulu 2 DPO 70B
· AI2 ImpACT Low-risk
|
1172±20.0 |
|
›
346
|
DBRX Instruct Preview
· DBRX LICENSE
|
1171±11.0 |
|
›
347
|
Mixtral 8x7B Instruct v0.1
Mistral · Apache 2.0
|
1167±8.0 |
|
›
348
|
Granite 3.1 8B Instruct
IBM · Apache 2.0
|
1166±25.0 |
|
›
349
|
Vicuna 33B
· Non-commercial
|
1166±12.0 |
|
›
350
|
GPT-3.5 Turbo (1106)
OpenAI · Proprietary
|
1164±15.0 |
|
›
351
|
Reka Flash 21B (20240226)
· Proprietary
|
1163±12.0 |
|
›
352
|
Yi 34B Chat
· Yi License
|
1160±13.0 |
|
›
353
|
Yi 1.5 34B Chat
· Apache-2.0
|
1152±11.0 |
|
›
354
|
Gemma 1.1 7B IT
Google · Gemma license
|
1151±11.0 |
|
›
355
|
OpenHermes 2.5 Mistral 7B
· Apache-2.0
|
1151±21.0 |
|
›
356
|
Granite 3.1 2B Instruct
IBM · Apache 2.0
|
1148±24.0 |
|
›
357
|
Snowflake Arctic Instruct
· Apache 2.0
|
1146±12.0 |
|
›
358
|
Llama 3.2 3B Instruct
Meta · Llama 3.2
|
1142±18.0 |
|
›
359
|
Granite 3.0 8B Instruct
IBM · Apache 2.0
|
1142±21.0 |
|
›
360
|
Guanaco 33B
· Non-commercial
|
1141±29.0 |
|
›
361
|
DeepSeek LLM 67B Chat
DeepSeek · DeepSeek License
|
1141±21.0 |
|
›
362
|
OpenChat 3.5 (0106)
· Apache-2.0
|
1141±15.0 |
|
›
363
|
Falcon 180B Chat
· Falcon-180B TII License
|
1141±37.0 |
|
›
364
|
WizardLM 13B
Microsoft · Llama 2 Community
|
1141±18.0 |
|
›
365
|
Qwen1.5-32B-Chat
阿里巴巴 · Qianwen LICENSE
|
1140±12.0 |
|
›
366
|
Phi-3 Medium 4K Instruct
Microsoft · MIT
|
1136±11.0 |
|
›
367
|
Starling LM 7B Alpha
· CC-BY-NC-4.0
|
1134±15.0 |
|
›
368
|
MPT 30B Chat
· CC-BY-NC-SA-4.0
|
1131±29.0 |
|
›
369
|
Qwen1.5-14B-Chat
阿里巴巴 · Qianwen LICENSE
|
1125±14.0 |
|
›
370
|
SOLAR 10.7B Instruct v1.0
Upstage · CC-BY-NC-4.0
|
1124±24.0 |
|
›
371
|
InternLM2.5 20B Chat
· Other
|
1122±16.0 |
|
›
372
|
Dolphin 2.2.1 Mistral 7B
· Apache-2.0
|
1119±33.0 |
|
›
373
|
Zephyr 7B Beta
· MIT
|
1116±16.0 |
|
›
374
|
Phi-3 Small 8K Instruct
Microsoft · MIT
|
1114±13.0 |
|
›
375
|
Starling LM 7B Beta
· Apache-2.0
|
1114±15.0 |
|
›
376
|
Nous Hermes 2 Mixtral 8x7B DPO
· Apache-2.0
|
1113±24.0 |
|
›
377
|
Llama 2 70B Chat
Meta · Llama 2 Community
|
1112±10.0 |
|
›
378
|
Vicuna 13B
· Llama 2 Community
|
1111±12.0 |
|
›
379
|
Llama 2 70B SteerLM Chat
NVIDIA · Llama 2 Community
|
1110±25.0 |
|
›
380
|
Mistral 7B Instruct v0.2
Mistral · Apache-2.0
|
1109±12.0 |
|
›
381
|
Granite 3.0 2B Instruct
IBM · Apache 2.0
|
1107±21.0 |
|
›
382
|
Llama 2 13B Chat
Meta · Llama 2 Community
|
1103±12.0 |
|
›
383
|
QwQ-32B-Preview
阿里巴巴 · Apache 2.0
|
1102±27.0 |
|
›
384
|
Zephyr 7B Alpha
· MIT
|
1100±31.0 |
|
›
385
|
Vicuna 7B
· Llama 2 Community
|
1098±18.0 |
|
›
386
|
PaLM 2
Google · Proprietary
|
1098±18.0 |
|
›
387
|
Phi-3 Mini 4K Instruct (June 2024)
Microsoft · MIT
|
1092±14.0 |
|
›
388
|
Gemma 7B IT
Google · Gemma license
|
1090±18.0 |
|
›
389
|
StripedHyena Nous 7B
· Apache 2.0
|
1089±21.0 |
|
›
390
|
Gemma 1.1 2B IT
Google · Gemma license
|
1087±17.0 |
|
›
391
|
Phi-3 Mini 128K Instruct
Microsoft · MIT
|
1087±14.0 |
|
›
392
|
Qwen-14B-Chat
阿里巴巴 · Qianwen LICENSE
|
1086±21.0 |
|
›
393
|
Qwen1.5-7B-Chat
阿里巴巴 · Qianwen LICENSE
|
1086±23.0 |
|
›
394
|
Llama 3.2 1B Instruct
Meta · Llama 3.2
|
1081±19.0 |
|
›
395
|
Code Llama 34B Instruct
Meta · Llama 2 Community
|
1081±17.0 |
|
›
396
|
Mistral 7B Instruct
Mistral · Apache 2.0
|
1080±17.0 |
|
›
397
|
Alpaca 13B
· Non-commercial
|
1075±21.0 |
|
›
398
|
SmolLM2 1.7B Instruct
· Apache 2.0
|
1075±33.0 |
|
›
399
|
Phi-3 Mini 4K Instruct
Microsoft · MIT
|
1069±12.0 |
|
›
400
|
Gemma 2B IT
Google · Gemma license
|
1069±23.0 |
|
›
401
|
Llama 2 7B Chat
Meta · Llama 2 Community
|
1068±14.0 |
|
›
402
|
GPT4All 13B Snoozy
· Non-commercial
|
1050±37.0 |
|
›
403
|
Qwen1.5-4B-Chat
阿里巴巴 · Qianwen LICENSE
|
1048±18.0 |
|
›
404
|
MPT 7B Chat
· CC-BY-NC-SA-4.0
|
1037±24.0 |
|
›
405
|
Koala 13B
· Non-commercial
|
1030±20.0 |
|
›
406
|
OLMo 7B Instruct
Allen AI · Apache-2.0
|
1025±21.0 |
|
›
407
|
ChatGLM3 6B
· Apache-2.0
|
1018±24.0 |
|
›
408
|
ChatGLM2 6B
· Apache-2.0
|
995±28.0 |
|
›
409
|
RWKV-4 Raven 14B
· Apache 2.0
|
990±22.0 |
|
›
410
|
OpenAssistant Pythia 12B
· Apache 2.0
|
988±21.0 |
|
›
411
|
FastChat-T5 3B
· Apache 2.0
|
959±25.0 |
|
›
412
|
LLaMA 13B
Meta · Non-commercial
|
939±32.0 |
|
›
413
|
Dolly 2.0 12B
· MIT
|
938±28.0 |
|
›
414
|
ChatGLM 6B
· Non-commercial
|
913±25.0 |
|
›
415
|
StableLM Tuned Alpha 7B
· CC-BY-NC-SA-4.0
|
906±29.0 |
没有找到相关模型