| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
19.11% ±4.31% |
|
›
🥈
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
13.90% ±2.28% |
|
›
🥉
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
13.08% ±2.75% |
|
›
4
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
11.35% ±1.99% |
|
›
5
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
10.85% ±2.09% |
|
›
6
|
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
10.78% ±2.12% |
|
›
7
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
9.27% ±0.94% |
|
›
8
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
8.87% ±2.81% |
|
›
9
|
Hy4 preview
腾讯 · Apache 2.0
|
8.48% ±2.07% |
|
›
10
|
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
7.71% ±1.24% |
|
›
11
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
7.68% ±1.03% |
|
›
12
|
GPT 5.5 (High)
OpenAI · Proprietary
|
7.25% ±1.46% |
|
›
13
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
7.20% ±1.49% |
|
›
14
|
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
6.61% ±2.05% |
|
›
15
|
Grok 4.5
SpaceXAI · Proprietary
|
6.26% ±1.64% |
|
›
16
|
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
5.92% ±1.64% |
|
›
17
|
Claude Opus 4.7
Anthropic · Proprietary
|
5.86% ±2.07% |
|
›
18
|
Qwen3.8 Max
阿里巴巴 · Proprietary
|
5.64% ±1.45% |
|
›
19
|
Claude Opus 4.8
Anthropic · Proprietary
|
5.46% ±2.95% |
|
›
20
|
GLM 5.3 (Max)
智谱 ZAI · MIT
|
5.17% ±0.98% |
|
›
21
|
GPT 5.5
OpenAI · Proprietary
|
4.99% ±1.22% |
|
›
22
|
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
4.84% ±1.02% |
|
›
23
|
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
4.44% ±1.64% |
|
›
24
|
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
4.33% ±1.83% |
|
›
25
|
GLM 5.3 Flash
智谱 ZAI · MIT
|
3.79% ±1.33% |
|
›
26
|
GPT 5.4 (High)
OpenAI · Proprietary
|
3.48% ±1.28% |
|
›
27
|
Claude Opus 4.6
Anthropic · Proprietary
|
3.45% ±1.91% |
|
›
28
|
Gemini 3.8 Flash (High)
Google · Proprietary
|
3.05% ±2.74% |
|
›
29
|
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
2.58% ±1.54% |
|
›
30
|
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
2.12% ±1.34% |
|
›
31
|
Kimi K2.6
月之暗面 · Modified MIT
|
0.26% ±4.19% |
|
›
32
|
DeepSeek V4 Pro
DeepSeek · MIT
|
0.13% ±1.44% |
|
›
33
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
0.41% ±1.58% |
|
›
34
|
Kimi K2.7 Code
月之暗面 · Modified MIT
|
0.79% ±3.51% |
|
›
35
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
1.17% ±1.17% |
|
›
36
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
1.17% ±1.72% |
|
›
37
|
Hy3
腾讯 · Apache 2.0
|
1.45% ±2.03% |
|
›
38
|
Qwen3.7 Max
阿里巴巴 · Proprietary
|
1.84% ±1.22% |
|
›
39
|
GLM 5.1
智谱 ZAI · MIT
|
3.06% ±1.35% |
|
›
40
|
Muse Spark 1.1
Meta · Proprietary
|
3.20% ±0.90% |
|
›
41
|
Mimo V2.5 Pro
小米 · MIT
|
3.39% ±1.30% |
|
›
42
|
Minimax M3
MiniMax · MiniMax Community License
|
3.95% ±1.34% |
|
›
43
|
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
4.36% ±1.75% |
|
›
44
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
5.66% ±1.36% |
|
›
45
|
Gemini 3.5 Flash (High)
Google · Proprietary
|
6.26% ±1.22% |
|
›
46
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
6.62% ±1.55% |
|
›
47
|
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
6.68% ±2.14% |
|
›
48
|
Inkling Small
Thinky · Apache 2.0
|
6.90% ±2.34% |
|
›
49
|
Inkling
Thinky · Apache 2.0
|
7.23% ±1.60% |
|
›
50
|
Mistral Medium 3.5
Mistral · Modified MIT
|
7.64% ±2.32% |
|
›
51
|
Solar Pro 4
Upstage · Proprietary
|
8.37% ±4.96% |
|
›
52
|
Minimax M2.7
MiniMax · Modified MIT
|
12.17% ±1.78% |
|
›
53
|
Grok 4.3 (High)
SpaceXAI · Proprietary
|
14.37% ±1.92% |
|
›
54
|
Gemini 3.5 Flash Lite
Google · Proprietary
|
14.57% ±1.85% |
|
›
55
|
Grok Build 0.1
SpaceXAI · Proprietary
|
15.66% ±2.06% |
|
›
56
|
Gemini 3 Flash
Google · Proprietary
|
15.66% ±1.61% |
|
›
57
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
16.72% ±3.98% |
|
›
58
|
Grok 4.3
SpaceXAI · Proprietary
|
21.27% ±3.06% |
|
›
59
|
Gemma 4 31B
Google · Apache 2.0
|
26.66% ±3.99% |
没有找到相关模型