排名 模型
🥇
gemini-3-pro Google · Proprietary
1366±34.9
🥈
gemini-3-flash Google · Proprietary
1358±42.5
🥉
gemini-3-flash (thinking-minimal) Google · Proprietary
1344±46.3
4
gemini-3.1-pro-preview Google · Proprietary
1339±58.9
5
kimi-k2.5-thinking 月之暗面 · Modified MIT
1320±56.3
6
grok-4-0709 xAI · Proprietary
1286±30.4
7
gemini-2.5-pro Google · Proprietary
1283±20.0
8
qwen3-vl-235b-a22b-instruct 阿里巴巴 · Apache 2.0
1265±40.5
9
gpt-5-high OpenAI · Proprietary
1263±26.3
10
chatgpt-4o-latest-20250326 OpenAI · Proprietary
1253±28.8
11
gpt-5.1-high OpenAI · Proprietary
1252±50.6
12
gemini-2.5-flash Google · Proprietary
1245±23.0
13
o3-2025-04-16 OpenAI · Proprietary
1237±25.4
14
gpt-5-mini-high OpenAI · Proprietary
1223±32.0
15
o4-mini-2025-04-16 OpenAI · Proprietary
1218±27.8
16
gpt-5-chat OpenAI · Proprietary
1218±28.8
17
gpt-4.1-2025-04-14 OpenAI · Proprietary
1206±27.9
18
gpt-5.2-high OpenAI · Proprietary
1203±63.0
19
gemma-3-27b-it Google · Gemma
1199±30.1
20
gpt-5.1 OpenAI · Proprietary
1197±42.8
21
gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary
1188±27.6
22
gpt-4.1-mini-2025-04-14 OpenAI · Proprietary
1188±28.3
23
gpt-5.2 OpenAI · Proprietary
1165±59.5
24
mistral-medium-2508 Mistral · Proprietary
1154±27.9
25
mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0
1153±36.3
26
mistral-small-2506 Mistral · Apache 2.0
1152±38.1
27
mistral-medium-2505 Mistral · Proprietary
1140±36.8

没有找到相关模型