排名 ⇕ 厂商 ⇕
› 🥇
Anthropic Claude Fable 5.1 (Max) · Proprietary
14.51% ±1.90%
› 🥈
OpenAI GPT 6 Astra (Max) · Proprietary
12.55% ±2.18%
› 🥉
月之暗面 Kimi K3 (Max) · Kimi K3 license
6.59% ±0.70%
› 4
腾讯 Hy4 preview · Apache 2.0
5.37% ±1.40%
› 5
智谱 ZAI GLM 5.2 (Max) · MIT · SiliconFlow
4.64% ±0.75%
› 6
DeepSeek DeepSeek V4 Pro (High) (0813) · MIT
4.43% ±0.92%
› 7
Google Gemini 3.8 Flash (High) · Proprietary
7.36% ±3.73%
› 8
SpaceXAI Grok 4.5 · Proprietary
4.26% ±2.01%
› 9
阿里巴巴 Qwen3.8 Max · Proprietary
3.93% ±2.01%
› 10
Meta Muse Spark 1.2 (xHigh) · Proprietary
1.56% ±1.23%
› 11
小米 Mimo V2.5 Pro · MIT
5.08% ±0.99%
› 12
MiniMax Minimax M3 · MiniMax Community License
5.26% ±0.95%
› 13
Thinky Inkling Small · Apache 2.0
6.89% ±1.64%
› 14
Mistral Mistral Medium 3.5 · Modified MIT
9.35% ±1.51%
› 15
Upstage Solar Pro 4 · Proprietary
11.29% ±3.75%

没有找到相关模型