| 排名 ⇕ | 厂商 ⇕ | |
|---|---|---|
|
›
🥇
|
Anthropic
Claude Opus 5 (High) · Proprietary
|
13.77% ±1.81% |
|
›
🥈
|
OpenAI
GPT 5.6 Sol (xHigh) · Proprietary
|
9.76% ±1.53% |
|
›
🥉
|
月之暗面
Kimi K3 (Max) · Kimi K3 license
|
8.74% ±0.66% |
|
›
4
|
智谱 ZAI
GLM 5.2 (Max) · MIT · SiliconFlow
|
6.08% ±0.78% |
|
›
5
|
SpaceXAI
Grok 4.5 · Proprietary
|
6.06% ±1.15% |
|
›
6
|
阿里巴巴
Qwen3.8 Max · Proprietary
|
6.01% ±1.13% |
|
›
7
|
DeepSeek
DeepSeek V4 Pro (High) (0813) · MIT
|
5.90% ±1.09% |
|
›
8
|
Meta
Muse Spark 1.2 (xHigh) · Proprietary
|
0.97% ±1.12% |
|
›
9
|
Google
Gemini 3.7 Flash (High) · Proprietary
|
0.96% ±0.90% |
|
›
10
|
腾讯
Hy3 · Apache 2.0
|
1.64% ±1.32% |
|
›
11
|
小米
Mimo V2.5 Pro · MIT
|
3.56% ±0.96% |
|
›
12
|
MiniMax
Minimax M3 · MiniMax Community License
|
3.61% ±0.92% |
|
›
13
|
Thinky
Inkling Small · Apache 2.0
|
5.30% ±1.82% |
|
›
14
|
Mistral
Mistral Medium 3.5 · Modified MIT
|
6.12% ±1.67% |
|
›
15
|
Upstage
Solar Pro 4 · Proprietary
|
9.19% ±3.33% |
|
›
16
|
NVIDIA
Nemotron 3 Ultra · OpenMDW-1.1
|
13.57% ±2.56% |
没有找到相关模型