| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
13.68% ±1.59% |
|
›
🥈
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
11.03% ±2.52% |
|
›
🥉
|
Claude Opus 4.8 (Thinking)
Anthropic · Proprietary
|
9.05% ±1.34% |
|
›
4
|
Claude Opus 4.7 (Thinking)
Anthropic · Proprietary
|
8.45% ±1.26% |
|
›
5
|
GPT 5.5 (High)
OpenAI · Proprietary
|
7.80% ±1.10% |
|
›
6
|
Claude Opus 4.7
Anthropic · Proprietary
|
7.68% ±1.27% |
|
›
7
|
Claude Opus 4.6
Anthropic · Proprietary
|
7.65% ±1.26% |
|
›
8
|
GPT 5.4 (High)
OpenAI · Proprietary
|
6.80% ±1.14% |
|
›
9
|
GPT 5.5
OpenAI · Proprietary
|
6.57% ±1.07% |
|
›
10
|
Claude Opus 4.8
Anthropic · Proprietary
|
4.56% ±1.66% |
|
›
11
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
3.02% ±1.20% |
|
›
12
|
GLM 5.1
智谱 ZAI · MIT
|
2.88% ±1.21% |
|
›
13
|
DeepSeek V4 Pro
DeepSeek · MIT
|
0.22% ±1.18% |
|
›
14
|
Gemini 3.5 Flash
Google · Proprietary
|
0.06% ±1.06% |
|
›
15
|
Kimi K2.6
月之暗面 · Modified MIT
|
0.63% ±1.09% |
|
›
16
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
0.66% ±0.96% |
|
›
17
|
DeepSeek V4 Flash
DeepSeek · MIT
|
0.80% ±1.38% |
|
›
18
|
Qwen 3.6 Plus
阿里巴巴 · Proprietary
|
4.52% ±1.21% |
|
›
19
|
Grok Build 0.1
xAI · Proprietary
|
6.28% ±1.11% |
|
›
20
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
6.81% ±5.22% |
|
›
21
|
Minimax M2.7
MiniMax · Modified MIT
|
7.43% ±1.10% |
|
›
22
|
Grok 4.3 (High)
xAI · Proprietary
|
8.09% ±1.38% |
|
›
23
|
Gemini 3 Flash
Google · Proprietary
|
8.89% ±1.06% |
|
›
24
|
Gemma 4 31B
Google · Apache 2.0
|
12.55% ±1.89% |
|
›
25
|
Grok 4.3
xAI · Proprietary
|
18.30% ±1.61% |
没有找到相关模型