| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
13.34% ±1.55% |
|
›
🥈
|
Claude Opus 4.8 (Thinking)
Anthropic · Proprietary
|
9.37% ±1.29% |
|
›
🥉
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
8.21% ±1.02% |
|
›
4
|
Claude Opus 4.7
Anthropic · Proprietary
|
8.16% ±1.28% |
|
›
5
|
Claude Opus 4.7 (Thinking)
Anthropic · Proprietary
|
8.07% ±1.23% |
|
›
6
|
GPT 5.5 (High)
OpenAI · Proprietary
|
7.13% ±0.78% |
|
›
8
|
GPT 5.4 (High)
OpenAI · Proprietary
|
6.65% ±0.79% |
|
›
9
|
Claude Opus 4.6
Anthropic · Proprietary
|
6.47% ±1.21% |
|
›
10
|
GPT 5.5
OpenAI · Proprietary
|
6.22% ±0.77% |
|
›
11
|
Claude Opus 4.8
Anthropic · Proprietary
|
3.74% ±1.49% |
|
›
12
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.18% ±1.11% |
|
›
15
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
1.09% ±0.70% |
|
›
16
|
Gemini 3.5 Flash
Google · Proprietary
|
1.13% ±0.74% |
|
›
19
|
Minimax M3
MiniMax · Proprietary
|
2.28% ±1.01% |
|
›
21
|
Qwen 3.6 Plus
阿里巴巴 · Proprietary
|
4.20% ±0.99% |
|
›
22
|
Grok 4.3 (High)
xAI · Proprietary
|
7.19% ±0.84% |
|
›
23
|
Grok Build 0.1
xAI · Proprietary
|
7.81% ±0.82% |
|
›
24
|
Gemini 3 Flash
Google · Proprietary
|
8.24% ±0.81% |
|
›
28
|
Grok 4.3
xAI · Proprietary
|
16.76% ±1.07% |
没有找到相关模型