| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
12.17% ±3.23% |
|
›
🥈
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.19% ±2.88% |
|
›
🥉
|
Claude Opus 5.5 (High)
Anthropic · Proprietary
|
10.18% ±4.08% |
|
›
4
|
GPT 6 Astra (Max)
OpenAI · Proprietary
|
8.48% ±3.97% |
|
›
5
|
GPT 6 Sol (Max)
OpenAI · Proprietary
|
8.46% ±4.60% |
|
›
6
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
8.28% ±2.22% |
|
›
7
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
8.03% ±2.51% |
|
›
8
|
Gemini 3.8 Flash (High)
Google · Proprietary
|
5.38% ±1.75% |
|
›
9
|
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
5.31% ±2.29% |
|
›
10
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
4.91% ±2.37% |
|
›
11
|
Hy4 preview
腾讯 · Apache 2.0
|
3.44% ±1.73% |
|
›
12
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
3.23% ±1.72% |
|
›
13
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
3.20% ±2.79% |
|
›
14
|
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.08% ±1.25% |
|
›
15
|
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
2.99% ±3.23% |
|
›
16
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
2.75% ±1.31% |
|
›
17
|
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
2.60% ±1.17% |
|
›
18
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
2.51% ±0.99% |
|
›
19
|
GLM 5.3 (Max)
智谱 ZAI · MIT
|
2.18% ±1.23% |
|
›
20
|
Muse Spark 1.3 (Max)
Meta · Proprietary
|
2.16% ±1.12% |
|
›
21
|
Grok 4.5
SpaceXAI · Proprietary
|
1.76% ±1.76% |
|
›
22
|
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
1.70% ±3.37% |
|
›
23
|
GPT 6 Luna (Max)
OpenAI · Proprietary
|
1.70% ±3.51% |
|
›
24
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
1.67% ±1.32% |
|
›
25
|
GPT 5.5
OpenAI · Proprietary
|
1.64% ±1.60% |
|
›
26
|
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
1.09% ±1.88% |
|
›
27
|
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.35% ±2.13% |
|
›
28
|
GPT 5.4 (High)
OpenAI · Proprietary
|
0.42% ±1.61% |
|
›
29
|
GLM 5.3 Flash
智谱 ZAI · MIT
|
0.59% ±1.00% |
|
›
30
|
DeepSeek V4 Pro
DeepSeek · MIT
|
0.72% ±1.90% |
|
›
31
|
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
1.14% ±1.33% |
|
›
32
|
Muse Spark 1.1
Meta · Proprietary
|
1.37% ±0.90% |
|
›
33
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.63% ±1.41% |
|
›
34
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
1.92% ±1.87% |
|
›
35
|
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.30% ±1.80% |
|
›
36
|
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
3.37% ±1.22% |
|
›
37
|
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
4.33% ±1.16% |
|
›
38
|
Mimo V2.5 Pro
小米 · MIT
|
4.44% ±1.94% |
|
›
39
|
Hy3
腾讯 · Apache 2.0
|
5.24% ±2.01% |
|
›
40
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
5.30% ±1.64% |
|
›
41
|
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
5.92% ±2.25% |
|
›
42
|
Minimax M3
MiniMax · MiniMax Community License
|
7.76% ±1.58% |
|
›
43
|
Inkling Small
Thinky · Apache 2.0
|
9.38% ±2.64% |
|
›
44
|
Inkling
Thinky · Apache 2.0
|
9.69% ±2.03% |
|
›
45
|
Mistral Medium 3.5
Mistral · Modified MIT
|
13.02% ±2.81% |
|
›
46
|
Solar Pro 4
Upstage · Proprietary
|
16.24% ±4.36% |
没有找到相关模型