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
5 5
1 - 10
Kimi K3 (Max)
月之暗面 · Kimi K3 license
9.91%±1.19% 14.23%±2.46% 17.45%±4.26% 9.67%±2.19% 6.86%±1.03% 1.32%±0.19% 19.6K
12 12
6 - 15
GLM 5.2 (Max)
智谱 ZAI · MIT
7.08%±0.96% 9.08%±1.94% 13.79%±3.42% 5.96%±1.69% 5.23%±1.09% 1.32%±0.19% 43.3K
22 22
21 - 30
GLM 5.1
智谱 ZAI · MIT
0.44%±0.79% 1.04%±1.76% 0.54%±2.60% 0.15%±1.45% 0.28%±1.31% 0.50%±0.33% 62.6K
23 23
17 - 31
Kimi K2.7 Code
月之暗面 · Modified MIT
0.44%±1.82% 4.73%±3.63% 3.42%±6.42% 3.71%±3.65% 3.56%±2.87% 1.32%±0.19% 10.4K
26 26
21 - 33
DeepSeek V4 Pro
DeepSeek · MIT
0.78%±0.94% 3.61%±2.41% 5.37%±3.02% 0.39%±1.74% 4.77%±0.98% 0.72%±0.26% 21.5K
27 27
21 - 34
Hy3
腾讯 · Apache 2.0
1.03%±1.88% 1.55%±3.99% 2.83%±6.51% 8.17%±3.49% 1.44%±2.58% 0.33%±0.52% 8.5K
29 29
21 - 34
Kimi K2.6
月之暗面 · Modified MIT
1.09%±1.95% 3.10%±3.68% 1.58%±6.21% 4.90%±3.76% 6.56%±3.93% 1.32%±0.19% 10.4K
32 32
26 - 34
Mimo V2.5 Pro
小米 · MIT
2.52%±1.01% 3.81%±2.46% 8.05%±3.13% 2.11%±1.89% 1.09%±1.64% 0.30%±0.37% 21.4K
33 33
26 - 34
Minimax M3
MiniMax · MiniMax Community License
2.55%±0.93% 5.67%±2.43% 9.01%±2.95% 4.56%±1.83% 5.71%±0.93% 0.77%±0.37% 21.0K
34 34
28 - 35
DeepSeek V4 Flash
DeepSeek · MIT
2.96%±0.95% 4.90%±2.51% 8.38%±2.97% 3.98%±1.78% 3.40%±0.98% 0.92%±0.42% 20.8K
36 36
35 - 36
Inkling
Thinky · Apache 2.0
5.71%±0.87% 7.07%±2.35% 15.75%±2.56% 12.07%±1.80% 5.92%±1.03% 0.41%±0.28% 25.7K
41 41
40 - 42
Minimax M2.7
MiniMax · Modified MIT
11.59%±1.17% 14.67%±2.82% 15.74%±3.27% 14.94%±2.22% 13.69%±2.81% 1.08%±0.26% 21.2K
42 42
40 - 44
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
13.14%±2.33% 15.00%±5.18% 13.58%±6.94% 20.73%±4.93% 16.58%±5.20% 0.19%±0.53% 10.8K
44 44
42 - 44
Gemma 4 31B
Google · Apache 2.0
16.10%±1.94% 1.00%±1.81% 3.90%±2.70% 8.47%±1.62% 38.46%±6.49% 28.69%±6.28% 55.9K
🔍

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