排名 模型
🥇
gpt-6-astra-max OpenAI · Proprietary
1743±47.0
🥈
claude-fable-5.1-max Anthropic · Proprietary
1669±32.0
🥉
qwen3.8-max 阿里巴巴 · Proprietary · Preliminary
1645±32.0
4
claude-opus-5-max Anthropic · Proprietary
1625±15.0
5
qwen3.8-max-0902 阿里巴巴 · Proprietary · Preliminary
1622±35.0
6
kimi-k3-max 月之暗面 · Kimi K3 license
1616±22.0
7
muse-spark-1.3-max Meta · Proprietary
1608±30.0
8
claude-opus-5-high Anthropic · Proprietary
1604±15.0
9
muse-spark-1.3 (xHigh) Meta · Proprietary
1592±33.0
10
grok-4.6-high SpaceXAI · Proprietary
1591±25.0
11
hy4-preview 腾讯 · Apache 2.0 · Preliminary
1588±32.0
12
deepseek-v4.1-flash-max DeepSeek · MIT
1580±41.0
13
qwen3.8-flash-next 阿里巴巴 · qwen-community-1.0 · Preliminary
1580±32.0
14
glm-5.3-flash 智谱 ZAI · MIT
1572±28.0
15
gpt-5.6-sol-xhigh (codex-harness) OpenAI · Proprietary
1572±14.0
16
qwen3.8-27b 阿里巴巴 · Apache 2.0
1571±23.0
17
claude-fable-5-high Anthropic · Proprietary
1567±15.0
18
glm-5.3-max 智谱 ZAI · MIT
1566±27.0
19
deepseek-v4-flash-high DeepSeek · MIT
1563±22.0
20
deepseek-v4-pro-high-20260813 DeepSeek · MIT
1562±22.0
21
glm-5.2-max 智谱 ZAI · MIT
1559±13.0
22
claude-opus-4-8-high Anthropic · Proprietary
1542±12.0
23
claude-opus-4-7-high Anthropic · Proprietary
1538±10.0
24
claude-opus-4-7 Anthropic · Proprietary
1537±11.0
25
gemini-3.7-flash-high Google · Proprietary · Preliminary
1537±29.0
26
claude-opus-4-8 Anthropic · Proprietary
1534±12.0
27
claude-opus-4-6-high Anthropic · Proprietary
1532±10.0
28
muse-spark-1.2 (xHigh) Meta · Proprietary
1531±33.0
29
claude-opus-4-6 Anthropic · Proprietary
1529±10.0
30
muse-spark-1.1 Meta · Proprietary
1529±16.0
31
grok-4.5 SpaceXAI · Proprietary
1528±16.0
32
gemini-3.8-flash-high Google · Proprietary · Preliminary
1524±28.0
33
claude-sonnet-4-6 Anthropic · Proprietary
1523±9.0
34
claude-sonnet-5-high Anthropic · Proprietary
1520±15.0
35
gemini-3.6-flash-high Google · Proprietary
1515±15.0
36
seed-2.1-pro-preview 字节跳动 · Proprietary
1510±15.0
37
gpt-5.6-terra-xhigh (codex-harness) OpenAI · Proprietary
1509±17.0
38
glm-5.1 智谱 ZAI · MIT
1508±14.0
39
kimi-k2.6 月之暗面 · Modified MIT
1507±12.0
40
qwen3.7-max-20260517 阿里巴巴 · Proprietary
1507±13.0
41
gpt-5.6-luna-xhigh (codex-harness) OpenAI · Proprietary
1501±16.0
42
claude-opus-4-5-20251101-high-32k Anthropic · Proprietary
1499±15.0
43
minimax-m3 MiniMax · MiniMax Community License
1484±12.0
44
hy3 腾讯 · Apache 2.0
1482±25.0
45
kimi-k2.7-code 月之暗面 · Modified MIT
1474±18.0
46
gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary
1474±11.0
47
gemini-3.5-flash-high Google · Proprietary
1474±15.0
48
qwen3.6-max-preview 阿里巴巴 · Proprietary
1469±23.0
49
deepseek-v4-pro-high-preview DeepSeek · MIT
1467±12.0
50
gemini-3.5-flash-medium Google · Proprietary
1464±13.0
51
gpt-5.4-high (codex-harness) OpenAI · Proprietary
1463±35.0
52
claude-opus-4-5-20251101 Anthropic · Proprietary
1462±13.0
53
mimo-v2.5-pro 小米 · MIT
1461±10.0
54
gpt-5.5-high (codex-harness) OpenAI · Proprietary
1458±10.0
55
mimo-v2.5 小米 · MIT
1452±11.0
56
qwen3.6-plus 阿里巴巴 · Proprietary
1450±10.0
57
deepseek-v4-pro DeepSeek · MIT
1448±11.0
58
gemini-3-flash Google · Proprietary
1445±15.0
59
glm-5 智谱 ZAI · MIT
1445±16.0
60
mimo-v2-pro 小米 · Proprietary
1443±14.0
61
glm-5v-turbo 智谱 ZAI · Proprietary
1440±30.0
62
kimi-k2.5-thinking 月之暗面 · Modified MIT
1439±10.0
63
gpt-5.4-medium (codex-harness) OpenAI · Proprietary
1438±34.0
64
deepseek-v4-flash-high-preview DeepSeek · MIT
1437±13.0
65
glm-4.7 智谱 ZAI · MIT
1437±25.0
66
gpt-5.5 (codex-harness) OpenAI · Proprietary
1437±11.0
67
gemini-3-pro Google · Proprietary
1436±14.0
68
inkling Thinky · Apache 2.0
1431±16.0
69
Inkling Small Thinky · Apache 2.0
1427±22.0
70
gemini-3.1-pro-preview Google · Proprietary
1423±9.0
71
gpt-5-medium OpenAI · Proprietary
1419±34.0
72
gpt-5.2 OpenAI · Proprietary
1412±51.0
73
minimax-m2.7 MiniMax · Modified MIT
1407±11.0
74
gpt-5.3-codex (codex-harness) OpenAI · Proprietary
1405±26.0
75
qwen3.5-397b-a17b 阿里巴巴 · Apache 2.0
1400±9.0
76
gpt-5.1-medium OpenAI · Proprietary
1399±24.0
77
solar-pro4 Upstage · Proprietary
1393±41.0
78
claude-sonnet-4-5-20250929-high-32k Anthropic · Proprietary
1391±14.0
79
gpt-5.4-mini-high OpenAI · Proprietary
1390±12.0
80
kimi-k2.5-instant 月之暗面 · Modified MIT
1389±24.0
81
claude-sonnet-4-5-20250929 Anthropic · Proprietary
1385±13.0
82
minimax-m2.1-preview MiniMax · MIT
1384±17.0
83
claude-opus-4-1-20250805 Anthropic · Proprietary
1379±20.0
84
laguna-m.1 Poolside · Apache 2.0
1374±18.0
85
gemini-3-flash (thinking-minimal) Google · Proprietary
1373±9.0
86
gpt-5.4 OpenAI · Proprietary
1372±26.0
87
deepseek-v3.2-thinking DeepSeek · MIT
1367±17.0
88
minimax-m2.5 MiniMax · Modified MIT
1367±15.0
89
grok-4.20-beta-0309-reasoning SpaceXAI · Proprietary
1365±10.0
90
qwen3.5-27b 阿里巴巴 · Apache 2.0
1362±14.0
91
gemma-4-31b Google · Apache 2.0
1362±15.0
92
gpt-5.1-codex OpenAI · Proprietary
1360±24.0
93
muse-glimmer Meta · Apache-2.0
1358±42.0
94
gpt-5.3-codex (codex-harness) OpenAI · Proprietary
1357±21.0
95
glm-4.6 智谱 ZAI · MIT
1356±21.0
96
qwen3.5-122b-a10b 阿里巴巴 · Apache 2.0
1356±14.0
97
grok-4.3 SpaceXAI · Proprietary
1346±11.0
98
gpt-5.2-codex OpenAI · Proprietary
1345±17.0
99
gemma-4-26b-a4b Google · Apache 2.0
1340±32.0
100
deepseek-v3.2 DeepSeek · MIT
1339±15.0
101
gpt-5.1 OpenAI · Proprietary
1334±15.0
102
claude-haiku-4-5-20251001 Anthropic · Proprietary
1331±9.0
103
mimo-v2-flash (non-thinking) 小米 · MIT
1324±19.0
104
hunyuan-hy3-preview 腾讯 · tencent-hunyuan-community
1323±33.0
105
kimi-k2-thinking-turbo 月之暗面 · Modified MIT
1318±13.0
106
laguna-xs.2 Poolside · Apache 2.0
1313±21.0
107
minimax-m2 MiniMax · Apache 2.0
1306±21.0
108
mimo-v2-flash (thinking) 小米 · MIT
1294±35.0
109
deepseek-v3.2-exp DeepSeek · MIT
1281±30.0
110
mistral-medium-3.5 Mistral · Modified MIT
1279±28.0
111
qwen3-coder-480b-a35b-instruct 阿里巴巴 · Apache 2.0
1274±14.0
112
KAT-Coder-Pro-V1 · Proprietary
1264±51.0
113
qwen3.5-35b-a3b 阿里巴巴 · Apache 2.0
1253±33.0
114
gemini-3.1-flash-lite-preview Google · Proprietary
1253±12.0
115
grok-4-1-fast-reasoning SpaceXAI · Proprietary
1251±22.0
116
gpt-5.1-codex-mini OpenAI · Proprietary
1241±53.0
117
trinity-large-thinking · Apache 2.0
1239±39.0
118
gemini-2.5-pro Google · Proprietary
1222±34.0
119
qwen3.5-flash 阿里巴巴 · Proprietary
1221±38.0
120
grok-code-fast-1 SpaceXAI · Proprietary
1209±61.0
121
devstral-2 Mistral · Modified MIT
1201±44.0
122
granite-4.1-8b IBM · Apache 2.0
1191±35.0
123
mistral-large-3 Mistral · Apache 2.0
1176±65.0
124
grok-4.1-thinking SpaceXAI · Proprietary
1159±60.0
125
mercury-2 Inception AI · Proprietary
1158±44.0
126
grok-4-fast-reasoning SpaceXAI · Proprietary
1157±60.0
127
devstral-medium-2507 Mistral · Proprietary
927±110.0

没有找到相关模型