| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
12.99% ±1.71% |
|
›
🥈
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
12.73% ±1.96% |
|
›
🥉
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
11.70% ±1.62% |
|
›
4
|
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
10.24% ±1.48% |
|
›
5
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
9.90% ±1.56% |
|
›
6
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
9.22% ±0.61% |
|
›
7
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
7.92% ±0.99% |
|
›
8
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
7.65% ±2.25% |
|
›
9
|
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
7.03% ±1.30% |
|
›
10
|
Claude Opus 4.7
Anthropic · Proprietary
|
6.86% ±1.32% |
|
›
11
|
Qwen3.8 Max
阿里巴巴 · Proprietary
|
6.66% ±1.18% |
|
›
12
|
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
6.58% ±1.09% |
|
›
13
|
GPT 5.5 (High)
OpenAI · Proprietary
|
6.57% ±0.93% |
|
›
14
|
Grok 4.5
SpaceXAI · Proprietary
|
6.48% ±1.18% |
|
›
15
|
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
6.11% ±1.45% |
|
›
16
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.94% ±0.79% |
|
›
17
|
GPT 5.5
OpenAI · Proprietary
|
5.66% ±0.83% |
|
›
18
|
Claude Opus 4.6
Anthropic · Proprietary
|
5.54% ±1.26% |
|
›
19
|
GPT 5.4 (High)
OpenAI · Proprietary
|
4.10% ±0.84% |
|
›
20
|
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.91% ±0.92% |
|
›
21
|
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
3.41% ±1.38% |
|
›
22
|
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
3.07% ±0.77% |
|
›
23
|
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
3.00% ±1.19% |
|
›
24
|
Claude Opus 4.8
Anthropic · Proprietary
|
2.52% ±2.45% |
|
›
25
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
1.75% ±1.26% |
|
›
26
|
Kimi K2.7 Code
月之暗面 · Modified MIT
|
1.71% ±2.27% |
|
›
27
|
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
1.56% ±1.47% |
|
›
28
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
1.33% ±0.87% |
|
›
29
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.32% ±1.11% |
|
›
30
|
Kimi K2.6
月之暗面 · Modified MIT
|
0.65% ±2.47% |
|
›
31
|
Muse Spark 1.1
Meta · Proprietary
|
0.19% ±0.62% |
|
›
32
|
DeepSeek V4 Pro
DeepSeek · MIT
|
0.20% ±0.95% |
|
›
33
|
GLM 5.1
智谱 ZAI · MIT
|
0.79% ±0.84% |
|
›
34
|
Qwen3.7 Max
阿里巴巴 · Proprietary
|
1.04% ±0.91% |
|
›
35
|
Hy3
腾讯 · Apache 2.0
|
1.19% ±1.28% |
|
›
36
|
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
2.26% ±1.34% |
|
›
37
|
Gemini 3.5 Flash (High)
Google · Proprietary
|
2.44% ±0.72% |
|
›
38
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
2.62% ±0.78% |
|
›
39
|
Mimo V2.5 Pro
小米 · MIT
|
2.68% ±0.93% |
|
›
40
|
Minimax M3
MiniMax · MiniMax Community License
|
2.79% ±0.89% |
|
›
41
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
3.33% ±1.18% |
|
›
42
|
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
3.67% ±1.42% |
|
›
43
|
Mistral Medium 3.5
Mistral · Modified MIT
|
5.76% ±1.82% |
|
›
44
|
Inkling Small
Thinky · Apache 2.0
|
6.18% ±1.89% |
|
›
45
|
Inkling
Thinky · Apache 2.0
|
6.58% ±1.04% |
|
›
46
|
Solar Pro 4
Upstage · Proprietary
|
9.38% ±3.04% |
|
›
47
|
Grok Build 0.1
SpaceXAI · Proprietary
|
10.09% ±1.06% |
|
›
48
|
Grok 4.3 (High)
SpaceXAI · Proprietary
|
10.16% ±0.97% |
|
›
49
|
Minimax M2.7
MiniMax · Modified MIT
|
10.18% ±1.16% |
|
›
50
|
Gemini 3 Flash
Google · Proprietary
|
10.65% ±0.93% |
|
›
51
|
Gemini 3.5 Flash Lite
Google · Proprietary
|
10.89% ±1.37% |
|
›
52
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
12.92% ±2.46% |
|
›
53
|
Grok 4.3
SpaceXAI · Proprietary
|
17.94% ±1.44% |
|
›
54
|
Gemma 4 31B
Google · Apache 2.0
|
21.31% ±2.97% |
没有找到相关模型