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
🥇 13
9 - 20
Hy4 preview
腾讯 · Apache 2.0
4.25%±0.88% 7.65%±1.72% 7.70%±3.17% 0.55%±1.84% 6.46%±0.50% 0.01%±0.32% 53.1K
🥈 14
10 - 19
Kimi K3 (Max)
月之暗面 · Kimi K3 license
4.24%±0.53% 9.50%±1.10% 7.72%±1.82% 0.44%±1.13% 4.05%±0.49% 0.35%±0.03% 129.6K
🥉 17
10 - 20
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
3.96%±0.57% 12.41%±1.11% 2.95%±1.99% 3.29%±1.35% 7.50%±0.33% 0.22%±0.04% 85.5K
4 18
10 - 21
GLM 5.2 (Max)
智谱 ZAI · MIT
3.91%±0.69% 3.91%±1.46% 9.93%±2.40% 4.29%±1.32% 1.09%±0.69% 0.35%±0.03% 83.8K
5 19
10 - 22
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
3.19%±0.80% 4.00%±1.66% 5.70%±2.84% 0.64%±1.70% 5.27%±0.63% 0.34%±0.03% 48.4K
6 20
11 - 23
GLM 5.3 (Max)
智谱 ZAI · MIT
2.96%±0.63% 6.33%±1.41% 5.96%±2.19% 2.95%±1.24% 0.79%±0.57% 0.35%±0.03% 81.3K
7 27
23 - 30
GLM 5.3 Flash
智谱 ZAI · MIT
0.05%±0.50% 6.84%±1.12% 0.30%±1.64% 0.88%±1.05% 5.75%±0.55% 0.35%±0.03% 74.6K
8 29
25 - 32
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
0.83%±0.64% 5.91%±1.41% 3.03%±2.21% 3.44%±1.47% 2.68%±0.42% 0.90%±0.09% 79.4K
9 30
25 - 32
DeepSeek V4 Pro
DeepSeek · MIT
1.13%±0.97% 3.55%±2.27% 1.56%±3.32% 2.66%±1.83% 2.27%±0.90% 0.17%±0.12% 35.7K
10 32
28 - 32
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
1.47%±0.60% 2.65%±1.37% 2.51%±2.00% 0.97%±1.30% 6.24%±0.59% 0.27%±0.12% 54.8K
11 36
35 - 41
Hy3
腾讯 · Apache 2.0
5.65%±1.16% 10.94%±2.65% 7.34%±3.45% 1.36%±2.45% 5.77%±2.27% 2.86%±1.01% 29.0K
12 37
36 - 41
Mimo V2.5 Pro
小米 · MIT
6.52%±0.86% 10.98%±2.19% 10.49%±2.49% 4.40%±1.69% 5.81%±1.51% 0.92%±0.27% 44.4K
13 38
36 - 41
Minimax M3
MiniMax · MiniMax Community License
6.77%±0.84% 14.27%±2.28% 13.18%±2.44% 6.96%±1.72% 0.63%±0.96% 0.09%±0.19% 40.9K
14 42
41 - 44
Inkling Small
Thinky · Apache 2.0
9.59%±1.35% 21.34%±4.01% 20.37%±3.63% 11.62%±3.14% 5.79%±1.23% 0.42%±0.33% 13.1K
15 43
42 - 44
Inkling
Thinky · Apache 2.0
10.87%±0.98% 21.63%±2.77% 21.89%±2.48% 11.75%±2.19% 0.93%±1.59% 0.02%±0.13% 42.7K
16 44
42 - 44
Mistral Medium 3.5
Mistral · Modified MIT
11.65%±1.46% 15.84%±3.68% 15.12%±4.02% 6.88%±3.25% 18.11%±2.71% 2.30%±0.73% 10.8K
🔍

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