排名 模型
🥇
kimi-k3 月之暗面 · Proprietary · Preliminary
1694±21.0
🥈
gpt-5.6-sol-xhigh (codex-harness) OpenAI · Proprietary
1643±13.0
🥉
claude-fable-5 Anthropic · Proprietary
1637±14.0
4
glm-5.2 (max) 智谱 ZAI · MIT
1603±11.0
5
claude-opus-4-8-thinking Anthropic · Proprietary
1563±9.0
6
claude-opus-4-7-thinking Anthropic · Proprietary
1559±7.0
7
grok-4.5 SpaceXAI · Proprietary
1554±14.0
8
claude-opus-4-7 Anthropic · Proprietary
1553±7.0
9
claude-sonnet-5-high Anthropic · Proprietary
1547±12.0
10
hy3 腾讯 · Apache 2.0
1544±22.0
11
claude-opus-4-8 Anthropic · Proprietary
1537±9.0
12
claude-opus-4-6-thinking Anthropic · Proprietary
1537±7.0
13
muse-spark-1.1 Meta · Proprietary · Preliminary
1533±15.0
14
seed-2.1-pro-preview 字节跳动 · Proprietary · Preliminary
1532±11.0
15
gemini-3.6-flash Google · Proprietary · Preliminary
1532±15.0
16
claude-opus-4-6 Anthropic · Proprietary
1529±6.0
17
glm-5.1 智谱 ZAI · MIT
1521±9.0
18
claude-sonnet-4-6 Anthropic · Proprietary
1516±6.0
19
qwen3.7-max-20260517 阿里巴巴 · Proprietary · Preliminary
1512±9.0
20
kimi-k2.6 月之暗面 · Modified MIT
1511±8.0
21
gemini-3.5-flash Google · Proprietary
1502±14.0
22
gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary
1500±8.0
23
minimax-m3 MiniMax · MiniMax Community License
1489±9.0
24
gemini-3.5-flash-medium Google · Proprietary
1487±10.0
25
gpt-5.5-high (codex-harness) OpenAI · Proprietary
1477±8.0
26
claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary
1476±10.0
27
qwen3.6-max-preview 阿里巴巴 · Proprietary
1475±13.0
28
kimi-k2.7-code 月之暗面 · Modified MIT
1468±10.0
29
mimo-v2.5-pro 小米 · MIT
1466±7.0
30
claude-opus-4-5-20251101 Anthropic · Proprietary
1458±8.0
31
qwen3.6-plus 阿里巴巴 · Proprietary
1454±7.0
32
deepseek-v4-pro-thinking DeepSeek · MIT
1451±8.0
33
gpt-5.4-high (codex-harness) OpenAI · Proprietary
1448±18.0
34
deepseek-v4-pro DeepSeek · MIT
1441±8.0
35
gpt-5.5 (codex-harness) OpenAI · Proprietary
1438±8.0
36
glm-4.7 智谱 ZAI · MIT
1436±60.0
37
gemini-3.1-pro-preview Google · Proprietary
1434±6.0
38
gemini-3-flash Google · Proprietary
1430±11.0
39
kimi-k2.5-thinking 月之暗面 · Modified MIT
1426±6.0
40
gpt-5.4-medium (codex-harness) OpenAI · Proprietary
1426±17.0
41
mimo-v2-pro 小米 · Proprietary
1423±8.0
42
mimo-v2.5 小米 · MIT
1422±8.0
43
glm-5 智谱 ZAI · MIT
1420±8.0
44
inkling Thinky · Apache 2.0
1413±13.0
45
gemini-3-pro Google · Proprietary
1402±11.0
46
gpt-5.3-codex (codex-harness) OpenAI · Proprietary
1396±13.0
47
kimi-k2.5-instant 月之暗面 · Modified MIT
1395±12.0
48
glm-5v-turbo 智谱 ZAI · Proprietary
1390±18.0
49
minimax-m2.7 MiniMax · Modified MIT
1390±7.0
50
gpt-5.4-mini-high OpenAI · Proprietary
1388±7.0
51
qwen3.5-397b-a17b 阿里巴巴 · Apache 2.0
1386±6.0
52
claude-sonnet-4-5-20250929 Anthropic · Proprietary
1386±9.0
53
claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary
1381±10.0
54
gpt-5.4 OpenAI · Proprietary
1380±21.0
55
gemini-3-flash (thinking-minimal) Google · Proprietary
1378±6.0
56
grok-4.20-beta-0309-reasoning SpaceXAI · Proprietary
1375±7.0
57
minimax-m2.1-preview MiniMax · MIT
1372±13.0
58
minimax-m2.5 MiniMax · Modified MIT
1371±8.0
59
deepseek-v3.2-thinking DeepSeek · MIT
1361±10.0
60
gemma-4-31b Google · Apache 2.0
1361±8.0
61
gpt-5.3-codex (codex-harness) OpenAI · Proprietary
1358±11.0
62
qwen3.5-122b-a10b 阿里巴巴 · Apache 2.0
1358±8.0
63
hunyuan-hy3-preview 腾讯 · tencent-hunyuan-community
1357±18.0
64
grok-4.3 SpaceXAI · Proprietary
1355±8.0
65
gemma-4-26b-a4b Google · Apache 2.0
1354±17.0
66
qwen3.5-27b 阿里巴巴 · Apache 2.0
1346±8.0
67
deepseek-v3.2 DeepSeek · MIT
1346±9.0
68
laguna-m.1 Poolside · Apache 2.0
1344±11.0
69
gpt-5.2-codex OpenAI · Proprietary
1327±9.0
70
claude-haiku-4-5-20251001 Anthropic · Proprietary
1326±6.0
71
kimi-k2-thinking-turbo 月之暗面 · Modified MIT
1318±9.0
72
mimo-v2-flash (non-thinking) 小米 · MIT
1311±12.0
73
gpt-5.1 OpenAI · Proprietary
1305±12.0
74
laguna-xs.2 Poolside · Apache 2.0
1296±12.0
75
qwen3-coder-480b-a35b-instruct 阿里巴巴 · Apache 2.0
1265±10.0
76
mistral-medium-3.5 Mistral · Modified MIT
1259±16.0
77
gemini-3.1-flash-lite-preview Google · Proprietary
1242±7.0
78
mimo-v2-flash (thinking) 小米 · MIT
1236±21.0
79
trinity-large-thinking · Apache 2.0
1232±21.0
80
qwen3.5-35b-a3b 阿里巴巴 · Apache 2.0
1232±17.0
81
grok-4-1-fast-reasoning SpaceXAI · Proprietary
1225±18.0
82
qwen3.5-flash 阿里巴巴 · Proprietary
1218±18.0
83
granite-4.1-8b IBM · Apache 2.0
1191±19.0
84
devstral-2 Mistral · Modified MIT
1164±43.0
85
mercury-2 Inception AI · Proprietary
1153±24.0

没有找到相关模型