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
8 - 18
Kimi K3 (Max)
月之暗面 · Kimi K3 license
4.55%±0.54% 9.96%±1.10% 8.23%±1.85% 0.16%±1.13% 4.34%±0.45% 0.36%±0.03% 127.6K
🥈 11
7 - 20
Hy4 preview
腾讯 · Apache 2.0
4.37%±0.91% 7.71%±1.78% 8.03%±3.26% 0.45%±1.90% 6.52%±0.51% 0.02%±0.33% 50.6K
🥉 14
9 - 18
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
4.10%±0.60% 13.10%±1.14% 3.22%±2.09% 3.47%±1.42% 7.42%±0.35% 0.22%±0.04% 79.8K
4 15
9 - 20
GLM 5.2 (Max)
智谱 ZAI · MIT
3.99%±0.69% 3.85%±1.46% 10.13%±2.42% 4.47%±1.32% 1.14%±0.69% 0.36%±0.03% 83.2K
5 18
9 - 22
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
3.28%±0.80% 4.21%±1.66% 5.74%±2.84% 0.75%±1.69% 5.34%±0.62% 0.35%±0.03% 48.4K
6 19
11 - 22
GLM 5.3 (Max)
智谱 ZAI · MIT
2.86%±0.63% 6.11%±1.42% 5.67%±2.18% 2.95%±1.24% 0.76%±0.56% 0.36%±0.03% 80.7K
7 26
22 - 29
GLM 5.3 Flash
智谱 ZAI · MIT
0.17%±0.52% 6.99%±1.15% 0.04%±1.69% 0.79%±1.08% 5.66%±0.56% 0.36%±0.03% 71.6K
8 27
24 - 31
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
0.55%±0.65% 6.48%±1.40% 2.11%±2.26% 3.68%±1.47% 2.56%±0.42% 0.88%±0.09% 77.9K
9 29
24 - 31
DeepSeek V4 Pro
DeepSeek · MIT
1.10%±0.97% 3.43%±2.27% 1.70%±3.31% 2.54%±1.83% 2.35%±0.89% 0.17%±0.12% 35.7K
10 31
27 - 31
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
1.45%±0.60% 2.78%±1.37% 2.72%±1.98% 0.86%±1.31% 6.19%±0.59% 0.26%±0.11% 53.7K
11 35
34 - 40
Hy3
腾讯 · Apache 2.0
5.63%±1.16% 10.86%±2.65% 7.16%±3.47% 1.60%±2.43% 5.66%±2.26% 2.89%±1.02% 28.9K
12 36
35 - 40
Mimo V2.5 Pro
小米 · MIT
6.45%±0.86% 10.82%±2.19% 10.40%±2.50% 4.30%±1.70% 5.83%±1.52% 0.89%±0.26% 44.1K
13 37
35 - 40
Minimax M3
MiniMax · MiniMax Community License
6.58%±0.84% 13.76%±2.27% 12.93%±2.45% 7.01%±1.71% 0.87%±0.92% 0.08%±0.19% 40.8K
14 41
41 - 43
Inkling Small
Thinky · Apache 2.0
9.61%±1.36% 21.18%±4.00% 20.23%±3.66% 11.94%±3.14% 5.71%±1.23% 0.43%±0.33% 13.0K
15 42
41 - 43
Inkling
Thinky · Apache 2.0
10.80%±0.98% 21.44%±2.76% 21.85%±2.49% 11.73%±2.18% 1.04%±1.57% 0.02%±0.13% 42.7K
16 43
41 - 43
Mistral Medium 3.5
Mistral · Modified MIT
11.61%±1.47% 16.07%±3.69% 14.91%±4.05% 6.85%±3.26% 17.90%±2.70% 2.34%±0.75% 10.7K
🔍

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