| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
14.21% ±2.35% |
|
›
🥈
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
13.12% ±2.74% |
|
›
🥉
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
11.99% ±2.12% |
|
›
4
|
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
10.96% ±2.17% |
|
›
5
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
10.91% ±2.14% |
|
›
6
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
10.17% ±0.90% |
|
›
7
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
9.53% ±3.07% |
|
›
8
|
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
8.90% ±1.47% |
|
›
9
|
GPT 5.5 (High)
OpenAI · Proprietary
|
7.73% ±1.43% |
|
›
10
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
7.60% ±1.03% |
|
›
11
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
7.53% ±1.51% |
|
›
12
|
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
7.08% ±1.99% |
|
›
13
|
Hy4 preview
腾讯 · Apache 2.0
|
6.86% ±2.57% |
|
›
14
|
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
6.86% ±1.76% |
|
›
15
|
Grok 4.5
SpaceXAI · Proprietary
|
6.61% ±1.60% |
|
›
16
|
Claude Opus 4.7
Anthropic · Proprietary
|
6.47% ±2.00% |
|
›
17
|
Claude Opus 4.8
Anthropic · Proprietary
|
5.83% ±2.99% |
|
›
18
|
GPT 5.5
OpenAI · Proprietary
|
5.54% ±1.20% |
|
›
19
|
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
5.47% ±1.61% |
|
›
20
|
Qwen3.8 Max
阿里巴巴 · Proprietary
|
5.30% ±1.51% |
|
›
21
|
GLM 5.3 (Max)
智谱 ZAI · MIT
|
5.10% ±1.04% |
|
›
22
|
GLM 5.3 Flash
智谱 ZAI · MIT
|
4.72% ±1.58% |
|
›
23
|
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
4.38% ±2.36% |
|
›
24
|
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
4.35% ±1.02% |
|
›
25
|
Claude Opus 4.6
Anthropic · Proprietary
|
3.90% ±1.85% |
|
›
26
|
GPT 5.4 (High)
OpenAI · Proprietary
|
3.68% ±1.24% |
|
›
27
|
Gemini 3.8 Flash (High)
Google · Proprietary
|
3.55% ±2.72% |
|
›
28
|
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
3.12% ±1.68% |
|
›
29
|
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
2.08% ±1.49% |
|
›
30
|
Kimi K2.6
月之暗面 · Modified MIT
|
0.74% ±4.03% |
|
›
31
|
Kimi K2.7 Code
月之暗面 · Modified MIT
|
0.18% ±3.37% |
|
›
32
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
0.62% ±1.15% |
|
›
33
|
Hy3
腾讯 · Apache 2.0
|
0.72% ±2.05% |
|
›
34
|
DeepSeek V4 Pro
DeepSeek · MIT
|
0.88% ±1.38% |
|
›
35
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
0.90% ±1.70% |
|
›
36
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.20% ±1.51% |
|
›
37
|
Qwen3.7 Max
阿里巴巴 · Proprietary
|
1.23% ±1.17% |
|
›
38
|
Muse Spark 1.1
Meta · Proprietary
|
2.35% ±0.90% |
|
›
39
|
GLM 5.1
智谱 ZAI · MIT
|
2.41% ±1.28% |
|
›
40
|
Mimo V2.5 Pro
小米 · MIT
|
2.85% ±1.27% |
|
›
41
|
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
3.60% ±1.76% |
|
›
42
|
Minimax M3
MiniMax · MiniMax Community License
|
4.04% ±1.32% |
|
›
43
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
5.39% ±1.32% |
|
›
44
|
Gemini 3.5 Flash (High)
Google · Proprietary
|
5.63% ±1.15% |
|
›
45
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
6.04% ±1.56% |
|
›
46
|
Inkling Small
Thinky · Apache 2.0
|
6.12% ±2.46% |
|
›
47
|
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
6.17% ±2.10% |
|
›
48
|
Mistral Medium 3.5
Mistral · Modified MIT
|
6.22% ±2.39% |
|
›
49
|
Inkling
Thinky · Apache 2.0
|
7.43% ±1.62% |
|
›
50
|
Solar Pro 4
Upstage · Proprietary
|
7.72% ±4.73% |
|
›
51
|
Minimax M2.7
MiniMax · Modified MIT
|
11.17% ±1.77% |
|
›
52
|
Grok 4.3 (High)
SpaceXAI · Proprietary
|
13.65% ±1.79% |
|
›
53
|
Gemini 3.5 Flash Lite
Google · Proprietary
|
13.87% ±1.83% |
|
›
54
|
Grok Build 0.1
SpaceXAI · Proprietary
|
14.40% ±1.88% |
|
›
55
|
Gemini 3 Flash
Google · Proprietary
|
14.73% ±1.49% |
|
›
56
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
16.04% ±3.89% |
|
›
57
|
Grok 4.3
SpaceXAI · Proprietary
|
19.95% ±2.72% |
|
›
58
|
Gemma 4 31B
Google · Apache 2.0
|
25.67% ±3.79% |
没有找到相关模型