| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
12.86% ±3.75% |
|
›
🥈
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
11.59% ±3.85% |
|
›
🥉
|
Gemini 3.8 Flash (High)
Google · Proprietary
|
8.31% ±3.63% |
|
›
4
|
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
8.09% ±2.83% |
|
›
5
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
7.99% ±3.07% |
|
›
6
|
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
6.90% ±2.61% |
|
›
7
|
Claude Opus 4.6
Anthropic · Proprietary
|
6.24% ±2.67% |
|
›
8
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
6.16% ±2.19% |
|
›
9
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
5.97% ±3.04% |
|
›
10
|
Claude Opus 4.7
Anthropic · Proprietary
|
5.71% ±2.65% |
|
›
11
|
Grok 4.5
SpaceXAI · Proprietary
|
5.37% ±2.02% |
|
›
12
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
4.62% ±1.21% |
|
›
13
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
4.43% ±3.81% |
|
›
14
|
Qwen3.8 Max
阿里巴巴 · Proprietary
|
4.38% ±2.09% |
|
›
15
|
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
3.50% ±2.45% |
|
›
16
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
3.48% ±2.24% |
|
›
17
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
3.48% ±1.50% |
|
›
18
|
GPT 5.5
OpenAI · Proprietary
|
3.18% ±1.69% |
|
›
19
|
Kimi K2.7 Code
月之暗面 · Modified MIT
|
3.17% ±4.68% |
|
›
20
|
Hy4 preview
腾讯 · Apache 2.0
|
3.06% ±3.50% |
|
›
21
|
GPT 5.5 (High)
OpenAI · Proprietary
|
2.57% ±1.82% |
|
›
22
|
DeepSeek V4 Pro
DeepSeek · MIT
|
2.52% ±2.10% |
|
›
23
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
2.44% ±1.91% |
|
›
24
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.37% ±2.45% |
|
›
25
|
Claude Opus 4.8
Anthropic · Proprietary
|
2.31% ±3.66% |
|
›
26
|
GLM 5.3 Flash
智谱 ZAI · MIT
|
1.34% ±2.30% |
|
›
27
|
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
1.30% ±1.92% |
|
›
28
|
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
1.07% ±2.51% |
|
›
29
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
1.06% ±2.35% |
|
›
30
|
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
0.98% ±2.24% |
|
›
31
|
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.76% ±2.36% |
|
›
32
|
GLM 5.1
智谱 ZAI · MIT
|
0.31% ±1.92% |
|
›
33
|
Muse Spark 1.1
Meta · Proprietary
|
0.31% ±1.26% |
|
›
34
|
GPT 5.4 (High)
OpenAI · Proprietary
|
0.27% ±1.68% |
|
›
35
|
GLM 5.3 (Max)
智谱 ZAI · MIT
|
0.10% ±1.54% |
|
›
36
|
Kimi K2.6
月之暗面 · Modified MIT
|
0.43% ±5.90% |
|
›
37
|
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
0.61% ±1.55% |
|
›
38
|
Gemini 3.5 Flash (High)
Google · Proprietary
|
0.79% ±1.68% |
|
›
39
|
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
1.42% ±2.70% |
|
›
40
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
2.01% ±1.69% |
|
›
41
|
Qwen3.7 Max
阿里巴巴 · Proprietary
|
2.10% ±2.07% |
|
›
42
|
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
2.37% ±2.15% |
|
›
43
|
Hy3
腾讯 · Apache 2.0
|
2.77% ±2.32% |
|
›
44
|
Inkling Small
Thinky · Apache 2.0
|
2.78% ±3.57% |
|
›
45
|
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
2.88% ±2.48% |
|
›
46
|
Mimo V2.5 Pro
小米 · MIT
|
3.62% ±2.38% |
|
›
47
|
Gemini 3.5 Flash Lite
Google · Proprietary
|
4.27% ±2.84% |
|
›
48
|
Minimax M3
MiniMax · MiniMax Community License
|
4.92% ±1.72% |
|
›
49
|
Grok Build 0.1
SpaceXAI · Proprietary
|
5.00% ±1.92% |
|
›
50
|
Inkling
Thinky · Apache 2.0
|
6.25% ±2.02% |
|
›
51
|
Gemini 3 Flash
Google · Proprietary
|
7.83% ±2.09% |
|
›
52
|
Mistral Medium 3.5
Mistral · Modified MIT
|
7.95% ±3.43% |
|
›
53
|
Solar Pro 4
Upstage · Proprietary
|
8.85% ±5.76% |
|
›
54
|
Minimax M2.7
MiniMax · Modified MIT
|
10.34% ±2.44% |
|
›
55
|
Grok 4.3 (High)
SpaceXAI · Proprietary
|
10.37% ±2.44% |
|
›
56
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
10.91% ±4.19% |
|
›
57
|
Gemma 4 31B
Google · Apache 2.0
|
19.33% ±4.55% |
|
›
58
|
Grok 4.3
SpaceXAI · Proprietary
|
21.01% ±4.50% |
没有找到相关模型