| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
13.99% ±2.06% |
|
›
🥈
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
11.59% ±1.82% |
|
›
🥉
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
11.53% ±2.37% |
|
›
4
|
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
10.33% ±1.78% |
|
›
5
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
10.01% ±1.83% |
|
›
6
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
9.29% ±0.78% |
|
›
7
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
8.61% ±2.57% |
|
›
8
|
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
7.72% ±1.21% |
|
›
9
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
7.56% ±1.25% |
|
›
10
|
Grok 4.5
SpaceXAI · Proprietary
|
6.90% ±1.39% |
|
›
11
|
Claude Opus 4.7
Anthropic · Proprietary
|
6.83% ±1.80% |
|
›
12
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
6.82% ±0.89% |
|
›
13
|
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
6.82% ±1.70% |
|
›
14
|
GPT 5.5 (High)
OpenAI · Proprietary
|
6.79% ±1.23% |
|
›
15
|
GPT 5.5
OpenAI · Proprietary
|
5.60% ±1.04% |
|
›
16
|
Gemini 3.8 Flash (High)
Google · Proprietary
|
5.60% ±2.20% |
|
›
17
|
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
5.31% ±1.48% |
|
›
18
|
Qwen3.8 Max
阿里巴巴 · Proprietary
|
5.05% ±1.33% |
|
›
19
|
Hy4 preview
腾讯 · Apache 2.0
|
5.02% ±2.13% |
|
›
20
|
GLM 5.3 Flash
智谱 ZAI · MIT
|
4.76% ±1.40% |
|
›
21
|
Claude Opus 4.6
Anthropic · Proprietary
|
4.49% ±1.60% |
|
›
22
|
GLM 5.3 (Max)
智谱 ZAI · MIT
|
4.09% ±0.88% |
|
›
23
|
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
3.88% ±0.90% |
|
›
24
|
GPT 5.4 (High)
OpenAI · Proprietary
|
3.60% ±1.03% |
|
›
25
|
Claude Opus 4.8
Anthropic · Proprietary
|
3.43% ±3.40% |
|
›
26
|
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
3.42% ±1.36% |
|
›
27
|
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
3.28% ±1.94% |
|
›
28
|
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
2.64% ±1.42% |
|
›
29
|
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
1.55% ±1.26% |
|
›
30
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
0.63% ±1.46% |
|
›
31
|
Kimi K2.6
月之暗面 · Modified MIT
|
0.52% ±3.12% |
|
›
32
|
DeepSeek V4 Pro
DeepSeek · MIT
|
0.36% ±1.21% |
|
›
33
|
Kimi K2.7 Code
月之暗面 · Modified MIT
|
0.30% ±3.05% |
|
›
34
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
0.43% ±1.01% |
|
›
35
|
Hy3
腾讯 · Apache 2.0
|
0.55% ±1.65% |
|
›
36
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.22% ±1.27% |
|
›
37
|
Qwen3.7 Max
阿里巴巴 · Proprietary
|
1.41% ±1.05% |
|
›
38
|
GLM 5.1
智谱 ZAI · MIT
|
1.87% ±1.06% |
|
›
39
|
Muse Spark 1.1
Meta · Proprietary
|
2.30% ±0.74% |
|
›
40
|
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
3.32% ±1.48% |
|
›
41
|
Mimo V2.5 Pro
小米 · MIT
|
3.54% ±1.08% |
|
›
42
|
Minimax M3
MiniMax · MiniMax Community License
|
3.79% ±1.10% |
|
›
43
|
Gemini 3.5 Flash (High)
Google · Proprietary
|
3.98% ±0.95% |
|
›
44
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
4.21% ±1.31% |
|
›
45
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
4.31% ±1.10% |
|
›
46
|
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
5.22% ±1.80% |
|
›
47
|
Inkling Small
Thinky · Apache 2.0
|
5.86% ±2.13% |
|
›
48
|
Mistral Medium 3.5
Mistral · Modified MIT
|
7.11% ±1.96% |
|
›
49
|
Inkling
Thinky · Apache 2.0
|
7.30% ±1.32% |
|
›
50
|
Solar Pro 4
Upstage · Proprietary
|
7.84% ±3.87% |
|
›
51
|
Minimax M2.7
MiniMax · Modified MIT
|
10.05% ±1.36% |
|
›
52
|
Grok 4.3 (High)
SpaceXAI · Proprietary
|
12.20% ±1.31% |
|
›
53
|
Grok Build 0.1
SpaceXAI · Proprietary
|
12.37% ±1.37% |
|
›
54
|
Gemini 3.5 Flash Lite
Google · Proprietary
|
12.46% ±1.55% |
|
›
55
|
Gemini 3 Flash
Google · Proprietary
|
13.51% ±1.33% |
|
›
56
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
15.16% ±3.10% |
|
›
57
|
Grok 4.3
SpaceXAI · Proprietary
|
19.67% ±1.91% |
|
›
58
|
Gemma 4 31B
Google · Apache 2.0
|
23.31% ±3.25% |
没有找到相关模型