| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
15.87% ±2.84% |
|
›
🥈
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
12.68% ±1.73% |
|
›
🥉
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
11.67% ±1.96% |
|
›
4
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
10.23% ±1.46% |
|
›
5
|
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
9.31% ±1.49% |
|
›
6
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
9.17% ±1.48% |
|
›
7
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
7.96% ±0.68% |
|
›
8
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
7.41% ±1.95% |
|
›
9
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
7.21% ±1.08% |
|
›
10
|
Hy4 preview
腾讯 · Apache 2.0
|
6.92% ±1.51% |
|
›
11
|
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
6.03% ±1.49% |
|
›
12
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
6.03% ±0.76% |
|
›
13
|
Grok 4.5
SpaceXAI · Proprietary
|
5.73% ±1.15% |
|
›
14
|
Claude Opus 4.7
Anthropic · Proprietary
|
5.66% ±1.51% |
|
›
15
|
GPT 5.5 (High)
OpenAI · Proprietary
|
5.55% ±1.05% |
|
›
16
|
Qwen3.8 Max
阿里巴巴 · Proprietary
|
5.51% ±1.09% |
|
›
17
|
Gemini 3.8 Flash (High)
Google · Proprietary
|
5.47% ±1.92% |
|
›
18
|
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
5.43% ±0.90% |
|
›
19
|
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
4.98% ±1.20% |
|
›
20
|
Claude Opus 4.6
Anthropic · Proprietary
|
4.65% ±1.41% |
|
›
21
|
GPT 5.5
OpenAI · Proprietary
|
4.39% ±0.90% |
|
›
22
|
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.80% ±0.71% |
|
›
23
|
GLM 5.3 Flash
智谱 ZAI · MIT
|
3.67% ±1.03% |
|
›
24
|
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
3.29% ±0.80% |
|
›
25
|
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
3.04% ±1.20% |
|
›
26
|
GPT 5.4 (High)
OpenAI · Proprietary
|
2.99% ±0.90% |
|
›
27
|
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
2.61% ±1.21% |
|
›
28
|
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
2.09% ±1.12% |
|
›
29
|
Claude Opus 4.8
Anthropic · Proprietary
|
1.85% ±2.81% |
|
›
30
|
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
1.03% ±0.99% |
|
›
31
|
Kimi K2.7 Code
月之暗面 · Modified MIT
|
0.75% ±2.65% |
|
›
32
|
DeepSeek V4 Pro
DeepSeek · MIT
|
0.58% ±1.08% |
|
›
33
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
0.50% ±1.28% |
|
›
34
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
0.46% ±1.18% |
|
›
35
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
0.43% ±0.92% |
|
›
36
|
Kimi K2.6
月之暗面 · Modified MIT
|
0.29% ±2.80% |
|
›
37
|
Muse Spark 1.1
Meta · Proprietary
|
1.43% ±0.63% |
|
›
38
|
Qwen3.7 Max
阿里巴巴 · Proprietary
|
1.62% ±0.94% |
|
›
39
|
GLM 5.1
智谱 ZAI · MIT
|
2.22% ±0.99% |
|
›
40
|
Hy3
腾讯 · Apache 2.0
|
2.50% ±1.32% |
|
›
41
|
Gemini 3.5 Flash (High)
Google · Proprietary
|
3.48% ±0.86% |
|
›
42
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
3.58% ±1.15% |
|
›
43
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
3.73% ±0.94% |
|
›
44
|
Minimax M3
MiniMax · MiniMax Community License
|
3.76% ±0.94% |
|
›
45
|
Mimo V2.5 Pro
小米 · MIT
|
3.81% ±0.98% |
|
›
46
|
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
3.87% ±1.27% |
|
›
47
|
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
4.71% ±1.52% |
|
›
48
|
Inkling Small
Thinky · Apache 2.0
|
5.43% ±1.73% |
|
›
49
|
Mistral Medium 3.5
Mistral · Modified MIT
|
7.16% ±1.56% |
|
›
50
|
Inkling
Thinky · Apache 2.0
|
7.47% ±1.07% |
|
›
51
|
Solar Pro 4
Upstage · Proprietary
|
9.87% ±3.56% |
|
›
52
|
Grok 4.3 (High)
SpaceXAI · Proprietary
|
11.57% ±1.17% |
|
›
53
|
Gemini 3.5 Flash Lite
Google · Proprietary
|
11.64% ±1.39% |
|
›
54
|
Minimax M2.7
MiniMax · Modified MIT
|
11.71% ±1.19% |
|
›
55
|
Gemini 3 Flash
Google · Proprietary
|
12.11% ±1.14% |
|
›
56
|
Grok Build 0.1
SpaceXAI · Proprietary
|
12.95% ±1.35% |
|
›
57
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
14.43% ±2.68% |
|
›
58
|
Grok 4.3
SpaceXAI · Proprietary
|
20.26% ±1.89% |
|
›
59
|
Gemma 4 31B
Google · Apache 2.0
|
23.70% ±3.85% |
没有找到相关模型