| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
claude-opus-4-6
Anthropic · Proprietary
|
1549±11.2 |
|
›
🥇
|
claude-opus-4-6
Anthropic · Proprietary
|
1549±11.2 |
|
›
🥈
|
claude-opus-4-6-thinking
Anthropic · Proprietary
|
1545±11.9 |
|
›
🥈
|
claude-opus-4-6-thinking
Anthropic · Proprietary
|
1545±11.9 |
|
›
🥉
|
claude-sonnet-4-6
Anthropic · Proprietary
|
1523±8.9 |
|
›
🥉
|
claude-sonnet-4-6
Anthropic · Proprietary
|
1523±8.9 |
|
›
4
|
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
|
1491±7.0 |
|
›
4
|
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
|
1491±7.0 |
|
›
5
|
claude-opus-4-5-20251101
Anthropic · Proprietary
|
1465±6.8 |
|
›
5
|
claude-opus-4-5-20251101
Anthropic · Proprietary
|
1465±6.8 |
|
›
6
|
gpt-5.4-high (codex-harness)
OpenAI · Proprietary
|
1457±16.8 |
|
›
6
|
gpt-5.4-high (codex-harness)
OpenAI · Proprietary
|
1457±16.8 |
|
›
7
|
gemini-3.1-pro-preview
Google · Proprietary
|
1455±9.7 |
|
›
7
|
gemini-3.1-pro-preview
Google · Proprietary
|
1455±9.7 |
|
›
8
|
glm-5
智谱 ZAI · MIT
|
1445±10.2 |
|
›
8
|
glm-5
智谱 ZAI · MIT
|
1445±10.2 |
|
›
9
|
glm-4.7
智谱 ZAI · MIT
|
1439±10.1 |
|
›
9
|
glm-4.7
智谱 ZAI · MIT
|
1439±10.1 |
|
›
10
|
gemini-3-pro
Google · Proprietary
|
1438±7.1 |
|
›
10
|
gemini-3-pro
Google · Proprietary
|
1438±7.1 |
|
›
11
|
mimo-v2-pro
小米 · Proprietary
|
1437±13.3 |
|
›
11
|
mimo-v2-pro
小米 · Proprietary
|
1437±13.3 |
|
›
12
|
gemini-3-flash
Google · Proprietary
|
1437±7.3 |
|
›
12
|
gemini-3-flash
Google · Proprietary
|
1437±7.3 |
|
›
13
|
minimax-m2.7
MiniMax · Proprietary
|
1435±13.6 |
|
›
13
|
minimax-m2.7
MiniMax · Proprietary
|
1435±13.6 |
|
›
14
|
kimi-k2.5-thinking
月之暗面 · Modified MIT
|
1430±8.4 |
|
›
14
|
kimi-k2.5-thinking
月之暗面 · Modified MIT
|
1430±8.4 |
|
›
15
|
gpt-5.4-medium (codex-harness)
OpenAI · Proprietary
|
1428±15.8 |
|
›
15
|
gpt-5.4-medium (codex-harness)
OpenAI · Proprietary
|
1428±15.8 |
|
›
16
|
kimi-k2.5-instant
月之暗面 · Modified MIT
|
1408±10.6 |
|
›
16
|
kimi-k2.5-instant
月之暗面 · Modified MIT
|
1408±10.6 |
|
›
17
|
gpt-5.3-codex (codex-harness)
OpenAI · Proprietary
|
1407±12.0 |
|
›
17
|
gpt-5.3-codex (codex-harness)
OpenAI · Proprietary
|
1407±12.0 |
|
›
18
|
minimax-m2.5
MiniMax · MIT
|
1403±8.7 |
|
›
18
|
minimax-m2.5
MiniMax · MIT
|
1403±8.7 |
|
›
19
|
gpt-5.2
OpenAI · Proprietary
|
1403±16.5 |
|
›
19
|
gpt-5.2
OpenAI · Proprietary
|
1403±16.5 |
|
›
20
|
gpt-5-medium
OpenAI · Proprietary
|
1392±12.6 |
|
›
20
|
gpt-5-medium
OpenAI · Proprietary
|
1392±12.6 |
|
›
21
|
minimax-m2.1-preview
MiniMax · MIT
|
1392±8.0 |
|
›
21
|
minimax-m2.1-preview
MiniMax · MIT
|
1392±8.0 |
|
›
22
|
gemini-3-flash (thinking-minimal)
Google · Proprietary
|
1392±6.9 |
|
›
22
|
gemini-3-flash (thinking-minimal)
Google · Proprietary
|
1392±6.9 |
|
›
23
|
gpt-5.1-medium
OpenAI · Proprietary
|
1390±9.3 |
|
›
23
|
gpt-5.1-medium
OpenAI · Proprietary
|
1390±9.3 |
|
›
24
|
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
|
1389±6.3 |
|
›
24
|
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
|
1389±6.3 |
|
›
25
|
qwen3.5-397b-a17b
阿里巴巴 · Apache 2.0
|
1387±9.2 |
|
›
25
|
qwen3.5-397b-a17b
阿里巴巴 · Apache 2.0
|
1387±9.2 |
|
›
26
|
claude-sonnet-4-5-20250929
Anthropic · Proprietary
|
1386±6.2 |
|
›
26
|
claude-sonnet-4-5-20250929
Anthropic · Proprietary
|
1386±6.2 |
|
›
27
|
claude-opus-4-1-20250805
Anthropic · Proprietary
|
1384±8.7 |
|
›
27
|
claude-opus-4-1-20250805
Anthropic · Proprietary
|
1384±8.7 |
|
›
28
|
grok-4.20-beta-0309-reasoning
xAI · Proprietary
|
1378±13.1 |
|
›
28
|
grok-4.20-beta-0309-reasoning
xAI · Proprietary
|
1378±13.1 |
|
›
29
|
deepseek-v3.2-thinking
DeepSeek · MIT
|
1369±8.0 |
|
›
29
|
deepseek-v3.2-thinking
DeepSeek · MIT
|
1369±8.0 |
|
›
30
|
qwen3.5-122b-a10b
阿里巴巴 · Apache 2.0
|
1364±10.5 |
|
›
30
|
qwen3.5-122b-a10b
阿里巴巴 · Apache 2.0
|
1364±10.5 |
|
›
31
|
glm-4.6
智谱 ZAI · MIT
|
1353±8.6 |
|
›
31
|
glm-4.6
智谱 ZAI · MIT
|
1353±8.6 |
|
›
32
|
qwen3.5-27b
阿里巴巴 · Apache 2.0
|
1346±11.1 |
|
›
32
|
qwen3.5-27b
阿里巴巴 · Apache 2.0
|
1346±11.1 |
|
›
33
|
gpt-5.1
OpenAI · Proprietary
|
1339±7.0 |
|
›
33
|
gpt-5.1
OpenAI · Proprietary
|
1339±7.0 |
|
›
34
|
mimo-v2-flash (non-thinking)
小米 · MIT
|
1337±8.2 |
|
›
34
|
mimo-v2-flash (non-thinking)
小米 · MIT
|
1337±8.2 |
|
›
35
|
gpt-5.2-codex
OpenAI · Proprietary
|
1336±7.6 |
|
›
35
|
gpt-5.2-codex
OpenAI · Proprietary
|
1336±7.6 |
|
›
36
|
kimi-k2-thinking-turbo
月之暗面 · Modified MIT
|
1328±6.3 |
|
›
36
|
kimi-k2-thinking-turbo
月之暗面 · Modified MIT
|
1328±6.3 |
|
›
37
|
gpt-5.1-codex
OpenAI · Proprietary
|
1328±9.4 |
|
›
37
|
gpt-5.1-codex
OpenAI · Proprietary
|
1328±9.4 |
|
›
38
|
deepseek-v3.2
DeepSeek · MIT
|
1325±7.5 |
|
›
38
|
deepseek-v3.2
DeepSeek · MIT
|
1325±7.5 |
|
›
39
|
claude-haiku-4-5-20251001
Anthropic · Proprietary
|
1309±6.2 |
|
›
39
|
claude-haiku-4-5-20251001
Anthropic · Proprietary
|
1309±6.2 |
|
›
40
|
minimax-m2
MiniMax · Apache 2.0
|
1303±8.7 |
|
›
40
|
minimax-m2
MiniMax · Apache 2.0
|
1303±8.7 |
|
›
41
|
mimo-v2-flash (thinking)
小米 · MIT
|
1300±13.6 |
|
›
41
|
mimo-v2-flash (thinking)
小米 · MIT
|
1300±13.6 |
|
›
42
|
deepseek-v3.2-exp
DeepSeek · MIT
|
1285±10.6 |
|
›
42
|
deepseek-v3.2-exp
DeepSeek · MIT
|
1285±10.6 |
|
›
43
|
qwen3-coder-480b-a35b-instruct
阿里巴巴 · Apache 2.0
|
1280±6.3 |
|
›
43
|
qwen3-coder-480b-a35b-instruct
阿里巴巴 · Apache 2.0
|
1280±6.3 |
|
›
44
|
KAT-Coder-Pro-V1
快手 · Proprietary
|
1257±15.3 |
|
›
44
|
KAT-Coder-Pro-V1
快手 · Proprietary
|
1257±15.3 |
|
›
45
|
qwen3.5-35b-a3b
阿里巴巴 · Apache 2.0
|
1248±15.6 |
|
›
45
|
qwen3.5-35b-a3b
阿里巴巴 · Apache 2.0
|
1248±15.6 |
|
›
46
|
gemini-3.1-flash-lite-preview
Google · Proprietary
|
1242±10.3 |
|
›
46
|
gemini-3.1-flash-lite-preview
Google · Proprietary
|
1242±10.3 |
|
›
47
|
gpt-5.1-codex-mini
OpenAI · Proprietary
|
1238±17.3 |
|
›
47
|
gpt-5.1-codex-mini
OpenAI · Proprietary
|
1238±17.3 |
|
›
48
|
qwen3.5-flash
阿里巴巴 · Proprietary
|
1237±16.9 |
|
›
48
|
qwen3.5-flash
阿里巴巴 · Proprietary
|
1237±16.9 |
|
›
49
|
grok-4-1-fast-reasoning
xAI · Proprietary
|
1233±9.2 |
|
›
49
|
grok-4-1-fast-reasoning
xAI · Proprietary
|
1233±9.2 |
|
›
50
|
mistral-large-3
Mistral · Apache 2.0
|
1220±19.9 |
|
›
50
|
mistral-large-3
Mistral · Apache 2.0
|
1220±19.9 |
|
›
51
|
grok-4.1-thinking
xAI · Proprietary
|
1206±19.5 |
|
›
51
|
grok-4.1-thinking
xAI · Proprietary
|
1206±19.5 |
|
›
52
|
gemini-2.5-pro
Google · Proprietary
|
1202±12.9 |
|
›
52
|
gemini-2.5-pro
Google · Proprietary
|
1202±12.9 |
|
›
53
|
devstral-2
Mistral · Modified MIT
|
1198±16.6 |
|
›
53
|
devstral-2
Mistral · Modified MIT
|
1198±16.6 |
|
›
54
|
mercury-2
Inception AI · Proprietary
|
1183±20.8 |
|
›
54
|
mercury-2
Inception AI · Proprietary
|
1183±20.8 |
|
›
55
|
grok-4-fast-reasoning
xAI · Proprietary
|
1147±23.0 |
|
›
55
|
grok-4-fast-reasoning
xAI · Proprietary
|
1147±23.0 |
|
›
56
|
grok-code-fast-1
xAI · Proprietary
|
1138±21.9 |
|
›
56
|
grok-code-fast-1
xAI · Proprietary
|
1138±21.9 |
|
›
57
|
devstral-medium-2507
Mistral · Proprietary
|
1090±22.6 |
|
›
57
|
devstral-medium-2507
Mistral · Proprietary
|
1090±22.6 |
没有找到相关模型