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
10 10
7 - 13
GLM 5.2 (Max)
智谱 ZAI · MIT
4.51%±1.77% 9.96%±3.23% 12.69%±6.49% 5.45%±3.38% 3.60%±1.98% 1.75%±0.21% 13.4K
13 13
10 - 13
GLM 5.1
智谱 ZAI · MIT
2.07%±0.96% 3.30%±1.98% 0.53%±3.31% 0.35%±1.97% 5.12%±1.06% 1.75%±0.21% 35.3K
16 16
14 - 20
DeepSeek V4 Pro
DeepSeek · MIT
0.76%±1.25% 0.75%±2.76% 1.84%±4.32% 3.64%±2.57% 2.27%±1.15% 0.13%±0.34% 28.7K
17 17
14 - 20
Kimi K2.6
月之暗面 · Modified MIT
1.01%±0.88% 0.43%±1.88% 2.97%±2.91% 3.51%±1.76% 0.11%±1.35% 1.75%±0.21% 36.9K
18 18
14 - 20
Kimi K2.7 Code
月之暗面 · Modified MIT
1.11%±1.55% 3.22%±2.83% 0.45%±5.13% 7.31%±3.08% 2.77%±3.18% 1.75%±0.21% 16.3K
19 19
14 - 20
DeepSeek V4 Flash
DeepSeek · MIT
1.70%±1.09% 4.35%±2.10% 1.60%±3.76% 7.95%±2.24% 3.00%±1.55% 0.29%±0.42% 35.5K
24 24
21 - 27
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
7.36%±3.74% 5.54%±6.82% 2.30%±13.04% 19.65%±7.29% 10.21%±6.70% 0.90%±0.99% 4.7K
25 25
22 - 26
Minimax M2.7
MiniMax · Modified MIT
7.83%±0.87% 12.51%±2.09% 15.42%±2.57% 9.29%±1.71% 3.58%±1.56% 1.65%±0.23% 35.5K
27 27
26 - 27
Gemma 4 31B
Google · Apache 2.0
12.72%±1.68% 5.55%±2.04% 7.94%±2.97% 6.03%±1.89% 27.58%±5.60% 16.50%±4.61% 29.5K
🔍

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