| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
14.07% ±1.56% |
|
›
🥈
|
Claude Opus 4.8 (Thinking)
Anthropic · Proprietary
|
9.90% ±1.31% |
|
›
🥉
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
8.39% ±0.94% |
|
›
4
|
Claude Opus 4.7
Anthropic · Proprietary
|
8.16% ±1.24% |
|
›
5
|
Claude Opus 4.7 (Thinking)
Anthropic · Proprietary
|
8.07% ±1.25% |
|
›
6
|
Claude Sonnet 5 (Thinking)
Anthropic · Proprietary
|
7.38% ±1.30% |
|
›
7
|
GPT 5.5 (High)
OpenAI · Proprietary
|
7.16% ±0.76% |
|
›
8
|
GPT 5.4 (High)
OpenAI · Proprietary
|
6.73% ±0.78% |
|
›
9
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
6.72% ±1.24% |
|
›
10
|
GPT 5.5
OpenAI · Proprietary
|
6.55% ±0.74% |
|
›
11
|
Claude Opus 4.6
Anthropic · Proprietary
|
6.23% ±1.20% |
|
›
12
|
Claude Opus 4.8
Anthropic · Proprietary
|
4.69% ±1.56% |
|
›
13
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.53% ±1.09% |
|
›
14
|
GLM 5.1
智谱 ZAI · MIT
|
1.67% ±0.89% |
|
›
15
|
kimi-k2.7-code
月之暗面 · Modified MIT
|
0.74% ±3.33% |
|
›
16
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
0.55% ±0.70% |
|
›
17
|
DeepSeek V4 Flash
DeepSeek · MIT
|
1.00% ±1.26% |
|
›
18
|
Kimi K2.7 Code
月之暗面 · Modified MIT
|
1.22% ±1.32% |
|
›
19
|
kimi-k2.6
月之暗面 · Modified MIT
|
1.62% ±3.53% |
|
›
20
|
Kimi K2.6
月之暗面 · Modified MIT
|
1.84% ±0.92% |
|
›
21
|
Minimax M3
MiniMax · Fireworks
|
2.45% ±1.09% |
|
›
22
|
DeepSeek V4 Pro
DeepSeek · MIT
|
2.67% ±1.28% |
|
›
23
|
minimax-m3
MiniMax · MiniMax Community License
|
4.48% ±2.44% |
|
›
24
|
Qwen 3.6 Plus
阿里巴巴 · Proprietary
|
4.77% ±1.04% |
|
›
25
|
gemini-3.5-flash
Google · Proprietary
|
6.58% ±2.71% |
|
›
26
|
Grok 4.3 (High)
xAI · Proprietary
|
7.66% ±0.82% |
|
›
27
|
Grok Build 0.1
xAI · Proprietary
|
7.85% ±0.81% |
|
›
28
|
Minimax M2.7
MiniMax · Modified MIT
|
8.15% ±0.80% |
|
›
29
|
Gemini 3 Flash
Google · Proprietary
|
8.26% ±0.79% |
|
›
30
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
11.26% ±2.94% |
|
›
31
|
minimax-m2.7
MiniMax · Modified MIT
|
12.58% ±2.83% |
|
›
32
|
Gemma 4 31B
Google · Apache 2.0
|
13.07% ±1.49% |
|
›
33
|
Grok 4.3
xAI · Proprietary
|
15.71% ±1.02% |
没有找到相关模型