| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Fable 5
Anthropic · Proprietary
|
11.20% ±3.92% |
|
›
🥈
|
Claude Opus 4.7 (Thinking)
Anthropic · Proprietary
|
8.42% ±1.24% |
|
›
🥉
|
Claude Opus 4.8 (Thinking)
Anthropic · Proprietary
|
9.06% ±1.57% |
|
›
4
|
GPT 5.5 (High)
OpenAI · Proprietary
|
9.11% ±1.26% |
|
›
5
|
GPT 5.4 (High)
OpenAI · Proprietary
|
7.97% ±1.33% |
|
›
6
|
Claude Opus 4.6
Anthropic · Proprietary
|
8.15% ±1.21% |
|
›
7
|
GPT 5.5
OpenAI · Proprietary
|
7.94% ±1.24% |
|
›
8
|
Claude Opus 4.7
Anthropic · Proprietary
|
7.25% ±1.26% |
|
›
9
|
Claude Opus 4.8
Anthropic · Proprietary
|
4.35% ±1.98% |
|
›
10
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
3.86% ±1.15% |
|
›
12
|
Gemini 3.5 Flash
Google · Proprietary
|
0.33% ±1.19% |
|
›
16
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
1.39% ±1.07% |
|
›
17
|
Qwen 3.6 Plus
阿里巴巴 · Proprietary
|
4.13% ±1.39% |
|
›
18
|
Grok Build 0.1
xAI · Proprietary
|
5.15% ±1.19% |
|
›
20
|
Grok 4.3 (High)
xAI · Proprietary
|
9.23% ±1.95% |
|
›
21
|
Gemini 3 Flash
Google · Proprietary
|
10.12% ±1.20% |
|
›
23
|
Grok 4.3
xAI · Proprietary
|
22.66% ±2.02% |
没有找到相关模型