| 排名 ⇕ | 模型 ⇕ | |
|---|---|---|
|
›
🥇
|
Claude Opus 5 (High)
Anthropic · Proprietary
|
12.47% ±1.54% |
|
›
🥈
|
Claude Opus 5 (Max)
Anthropic · Proprietary
|
12.00% ±1.80% |
|
›
🥉
|
Claude Fable 5 (High)
Anthropic · Proprietary
|
11.57% ±1.70% |
|
›
4
|
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
10.41% ±0.62% |
|
›
5
|
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
9.74% ±1.39% |
|
›
6
|
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
9.55% ±1.51% |
|
›
7
|
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
8.51% ±0.93% |
|
›
8
|
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
8.12% ±1.24% |
|
›
9
|
GPT 5.5 (High)
OpenAI · Proprietary
|
7.74% ±0.84% |
|
›
10
|
Claude Opus 4.7
Anthropic · Proprietary
|
7.40% ±1.25% |
|
›
11
|
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
6.62% ±2.19% |
|
›
12
|
Claude Opus 4.6
Anthropic · Proprietary
|
6.60% ±1.20% |
|
›
13
|
GPT 5.5
OpenAI · Proprietary
|
6.38% ±0.80% |
|
›
14
|
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
6.26% ±1.28% |
|
›
15
|
Qwen3.8 Max
阿里巴巴 · Proprietary
|
6.20% ±1.36% |
|
›
16
|
Grok 4.5
SpaceXAI · Proprietary
|
6.17% ±1.16% |
|
›
17
|
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.82% ±0.87% |
|
›
18
|
GPT 5.4 (High)
OpenAI · Proprietary
|
4.98% ±0.80% |
|
›
19
|
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
4.04% ±1.87% |
|
›
20
|
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
3.99% ±0.79% |
|
›
21
|
Gemini 3.7 Flash (High)
Google · Proprietary
|
3.32% ±1.02% |
|
›
22
|
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
3.19% ±1.19% |
|
›
23
|
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.88% ±1.19% |
|
›
24
|
Claude Opus 4.8
Anthropic · Proprietary
|
2.51% ±2.25% |
|
›
25
|
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
2.06% ±1.14% |
|
›
26
|
Muse Spark 1.1
Meta · Proprietary
|
0.93% ±0.61% |
|
›
27
|
Kimi K2.7 Code
月之暗面 · Modified MIT
|
0.43% ±2.07% |
|
›
28
|
DeepSeek V4 Pro
DeepSeek · MIT
|
0.05% ±0.88% |
|
›
29
|
GLM 5.1
智谱 ZAI · MIT
|
0.00% ±0.75% |
|
›
30
|
Gemini 3.5 Flash (High)
Google · Proprietary
|
0.68% ±0.61% |
|
›
31
|
Qwen3.7 Max
阿里巴巴 · Proprietary
|
0.75% ±0.85% |
|
›
32
|
Gemini 3.1 Pro Preview
Google · Proprietary
|
0.88% ±0.68% |
|
›
33
|
Kimi K2.6
月之暗面 · Modified MIT
|
1.10% ±2.23% |
|
›
34
|
Mimo V2.5 Pro
小米 · MIT
|
2.25% ±0.88% |
|
›
35
|
Hy3
腾讯 · Apache 2.0
|
2.38% ±1.24% |
|
›
36
|
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
2.51% ±1.28% |
|
›
37
|
Gemini 3.6 Flash (High)
Google · Proprietary
|
3.04% ±1.23% |
|
›
38
|
Minimax M3
MiniMax · MiniMax Community License
|
3.15% ±0.83% |
|
›
39
|
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
3.86% ±1.40% |
|
›
40
|
Inkling Small
Thinky · Apache 2.0
|
6.82% ±1.75% |
|
›
41
|
Inkling
Thinky · Apache 2.0
|
7.19% ±0.93% |
|
›
42
|
Mistral Medium 3.5
Mistral · Modified MIT
|
7.60% ±1.88% |
|
›
43
|
Grok 4.3 (High)
SpaceXAI · Proprietary
|
9.02% ±0.84% |
|
›
44
|
Gemini 3 Flash
Google · Proprietary
|
9.13% ±0.82% |
|
›
45
|
Grok Build 0.1
SpaceXAI · Proprietary
|
9.48% ±0.90% |
|
›
46
|
Solar Pro 4
Upstage · Proprietary
|
10.82% ±2.39% |
|
›
47
|
Gemini 3.5 Flash Lite
Google · Proprietary
|
10.82% ±1.23% |
|
›
48
|
Minimax M2.7
MiniMax · Modified MIT
|
11.86% ±1.09% |
|
›
49
|
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
15.36% ±2.34% |
|
›
50
|
Grok 4.3
SpaceXAI · Proprietary
|
16.45% ±1.22% |
|
›
51
|
Gemma 4 31B
Google · Apache 2.0
|
19.82% ±2.57% |
没有找到相关模型