排名Rank 综合排名 / 区间Overall Rank / Range 模型Model 确认成功Confirmed Success 赞扬/抱怨Praise vs Complaint 可控性Steerability Bash 恢复Bash Recovery 工具幻觉Tool Hallucination 会话数Sessions
12 12
10 - 13
GLM 5.1
智谱 ZAI · MIT
2.72%±1.15% 3.66%±2.36% 1.78%±4.02% 1.04%±2.35% 5.25%±1.13% 1.88%±0.23% 32.0K
13 13
12 - 17
DeepSeek V4 Pro
DeepSeek · MIT
0.30%±1.39% 0.22%±2.99% 0.42%±4.81% 2.60%±2.97% 2.71%±1.34% 0.73%±0.33% 27.9K
15 15
13 - 17
Kimi K2.6
月之暗面 · Modified MIT
0.38%±1.10% 0.06%±2.29% 0.93%±3.69% 2.52%±2.20% 0.38%±1.72% 1.88%±0.23% 33.6K
17 17
13 - 18
DeepSeek V4 Flash
DeepSeek · MIT
1.09%±1.34% 4.06%±2.57% 1.96%±4.59% 6.29%±2.77% 1.80%±1.71% 0.52%±0.38% 32.3K
22 22
20 - 24
Minimax M2.7
MiniMax · Modified MIT
7.52%±1.07% 13.34%±2.58% 14.65%±3.29% 8.42%±2.05% 3.00%±1.73% 1.80%±0.25% 32.3K
24 24
18 - 25
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
8.89%±4.15% 4.47%±7.71% 6.28%±14.19% 22.74%±8.38% 12.82%±7.89% 1.88%±0.23% 3.9K
25 25
24 - 26
Gemma 4 31B
Google · Apache 2.0
12.78%±1.97% 5.87%±2.41% 7.88%±3.59% 6.23%±2.22% 26.70%±6.24% 17.21%±5.73% 26.2K
🔍

没有找到匹配的模型，换个关键词试试？No matching models found. Try a different keyword?