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
6 - 14
GLM 5.2 (Max)
智谱 ZAI · MIT
6.50%±1.00% 8.65%±1.97% 12.94%±3.63% 4.71%±1.79% 4.78%±1.15% 1.39%±0.17% 38.2K
17 17
15 - 20
GLM 5.1
智谱 ZAI · MIT
1.43%±0.78% 1.12%±1.74% 0.99%±2.69% 0.15%±1.53% 3.79%±0.89% 1.39%±0.17% 57.5K
22 22
17 - 29
Kimi K2.7 Code
月之暗面 · Modified MIT
1.02%±1.69% 3.79%±3.49% 0.95%±6.00% 8.37%±3.29% 2.86%±2.78% 1.39%±0.17% 10.1K
24 24
18 - 27
DeepSeek V4 Pro
DeepSeek · MIT
1.19%±1.06% 4.80%±2.70% 5.65%±3.42% 2.11%±2.05% 5.76%±1.02% 0.87%±0.26% 16.5K
25 25
18 - 29
Hy3
腾讯 · Apache 2.0
2.23%±2.87% 4.65%±6.11% 2.87%±9.99% 7.10%±5.95% 2.56%±3.98% 0.89%±0.82% 3.5K
26 26
19 - 29
Kimi K2.6
月之暗面 · Modified MIT
2.57%±1.75% 1.67%±3.51% 3.04%±5.45% 6.72%±3.26% 6.17%±3.87% 1.39%±0.17% 10.1K
27 27
23 - 29
Minimax M3
MiniMax · MiniMax Community License
3.10%±1.05% 7.49%±2.73% 9.67%±3.33% 5.43%±2.14% 6.15%±0.95% 0.93%±0.38% 16.0K
28 28
24 - 29
Mimo V2.5 Pro
小米 · MIT
3.39%±1.11% 5.88%±2.73% 10.33%±3.35% 2.94%±2.14% 1.69%±1.91% 0.49%±0.34% 16.5K
29 29
24 - 29
DeepSeek V4 Flash
DeepSeek · MIT
3.49%±1.06% 6.55%±2.78% 9.75%±3.31% 4.16%±2.06% 3.46%±1.15% 0.46%±0.40% 16.0K
30 30
30 - 33
Inkling
Thinky · Apache 2.0
6.41%±1.31% 7.19%±3.50% 19.01%±3.70% 11.60%±3.00% 6.12%±1.58% 0.40%±0.49% 10.7K
35 35
35 - 37
Minimax M2.7
MiniMax · Modified MIT
12.47%±1.34% 17.13%±3.13% 15.66%±3.70% 17.46%±2.45% 13.35%±3.31% 1.23%±0.20% 16.2K
36 36
35 - 38
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
13.50%±2.38% 15.08%±5.11% 12.20%±7.28% 21.37%±4.80% 18.77%±5.33% 0.09%±0.67% 10.3K
37 37
35 - 38
Gemma 4 31B
Google · Apache 2.0
14.51%±1.60% 2.31%±1.74% 4.49%±2.62% 6.87%±1.53% 33.53%±5.14% 25.33%±5.11% 54.8K
🔍

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