| 排名 ⇕ | 厂商 ⇕ | |
|---|---|---|
|
›
🥇
|
Anthropic
Claude Fable 5.1 (Max) · Proprietary
|
15.87% ±2.84% |
|
›
🥈
|
OpenAI
GPT 5.6 Sol (xHigh) · Proprietary
|
9.31% ±1.49% |
|
›
🥉
|
月之暗面
Kimi K3 (Max) · Kimi K3 license
|
7.96% ±0.68% |
|
›
4
|
腾讯
Hy4 preview · Apache 2.0
|
6.92% ±1.51% |
|
›
5
|
智谱 ZAI
GLM 5.2 (Max) · MIT · SiliconFlow
|
6.03% ±0.76% |
|
›
6
|
SpaceXAI
Grok 4.5 · Proprietary
|
5.73% ±1.15% |
|
›
7
|
阿里巴巴
Qwen3.8 Max · Proprietary
|
4.96% ±2.06% |
|
›
8
|
Google
Gemini 3.8 Flash (High) · Proprietary
|
7.95% ±3.65% |
|
›
9
|
DeepSeek
DeepSeek V4 Pro (High) (0813) · MIT
|
5.43% ±0.90% |
|
›
10
|
Meta
Muse Spark 1.2 (xHigh) · Proprietary
|
0.46% ±1.18% |
|
›
11
|
MiniMax
Minimax M3 · MiniMax Community License
|
3.76% ±0.94% |
|
›
12
|
小米
Mimo V2.5 Pro · MIT
|
3.81% ±0.98% |
|
›
13
|
Thinky
Inkling Small · Apache 2.0
|
5.43% ±1.73% |
|
›
14
|
Mistral
Mistral Medium 3.5 · Modified MIT
|
7.16% ±1.56% |
|
›
15
|
Upstage
Solar Pro 4 · Proprietary
|
9.87% ±3.56% |
|
›
16
|
NVIDIA
Nemotron 3 Ultra · OpenMDW-1.1
|
14.43% ±2.68% |
没有找到相关模型