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
🥇 7
5 - 12
Kimi K3 (Max)
月之暗面 · Kimi K3 license
7.96%±0.68% 16.58%±1.40% 14.03%±2.36% 1.24%±1.35% 7.16%±0.58% 0.78%±0.13% 97.9K
🥈 10
5 - 20
Hy4 preview
腾讯 · Apache 2.0
6.92%±1.51% 13.56%±2.96% 10.26%±5.61% 0.10%±3.21% 10.20%±0.79% 0.66%±0.14% 14.4K
🥉 12
8 - 21
GLM 5.2 (Max)
智谱 ZAI · MIT
6.03%±0.76% 8.63%±1.64% 11.73%±2.67% 4.48%±1.38% 4.51%±0.77% 0.78%±0.13% 69.4K
4 18
8 - 23
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
5.43%±0.90% 11.75%±1.91% 5.24%±3.13% 0.67%±1.95% 8.70%±0.71% 0.78%±0.13% 34.4K
5 22
15 - 30
GLM 5.3 (Max)
智谱 ZAI · MIT
3.80%±0.71% 12.10%±1.52% 5.75%±2.41% 0.63%±1.37% 0.28%±0.75% 0.78%±0.13% 53.9K
6 23
12 - 30
GLM 5.3 Flash
智谱 ZAI · MIT
3.67%±1.03% 14.14%±2.16% 5.45%±3.49% 0.23%±2.12% 2.24%±1.02% 0.78%±0.13% 19.0K
7 24
18 - 31
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
3.29%±0.80% 8.46%±1.76% 3.90%±2.76% 0.02%±1.60% 3.33%±0.65% 0.76%±0.13% 57.2K
8 27
18 - 35
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
2.61%±1.21% 12.46%±2.49% 0.24%±4.15% 1.18%±2.74% 1.90%±0.70% 0.39%±0.21% 20.3K
9 30
26 - 36
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
1.03%±0.99% 6.98%±2.26% 0.78%±3.28% 0.39%±2.02% 2.31%±0.90% 0.08%±0.22% 22.6K
10 31
21 - 40
Kimi K2.7 Code
月之暗面 · Modified MIT
0.75%±2.65% 1.15%±5.92% 0.99%±9.03% 4.68%±5.64% 3.86%±2.97% 0.78%±0.13% 11.1K
11 32
27 - 36
DeepSeek V4 Pro
DeepSeek · MIT
0.58%±1.08% 0.91%±2.76% 3.07%±3.61% 0.89%±2.05% 5.80%±0.90% 0.12%±0.19% 32.2K
12 36
24 - 46
Kimi K2.6
月之暗面 · Modified MIT
0.29%±2.80% 5.43%±6.19% 5.02%±9.28% 7.73%±5.90% 9.57%±5.32% 0.78%±0.13% 11.3K
13 39
35 - 47
GLM 5.1
智谱 ZAI · MIT
2.22%±0.99% 0.17%±2.15% 2.28%±2.74% 1.27%±1.82% 6.23%±2.38% 1.50%±0.63% 72.0K
14 40
35 - 48
Hy3
腾讯 · Apache 2.0
2.50%±1.32% 5.97%±3.05% 3.83%±4.22% 0.15%±2.66% 0.90%±2.30% 1.64%±0.58% 24.9K
15 44
38 - 48
Minimax M3
MiniMax · MiniMax Community License
3.76%±0.94% 8.25%±2.54% 9.86%±2.86% 5.48%±1.86% 4.42%±0.90% 0.39%±0.19% 36.7K
16 45
38 - 48
Mimo V2.5 Pro
小米 · MIT
3.81%±0.98% 5.56%±2.51% 8.84%±2.92% 2.64%±1.87% 1.66%±1.73% 0.36%±0.32% 37.6K
17 48
40 - 51
Inkling Small
Thinky · Apache 2.0
5.43%±1.73% 19.38%±4.89% 15.30%±5.08% 3.93%±4.09% 11.58%±1.21% 0.10%±0.46% 11.3K
18 49
47 - 51
Mistral Medium 3.5
Mistral · Modified MIT
7.16%±1.56% 14.49%±3.95% 12.61%±4.41% 0.50%±3.50% 6.13%±2.31% 2.08%±1.01% 8.8K
19 50
48 - 51
Inkling
Thinky · Apache 2.0
7.47%±1.07% 16.01%±3.17% 20.15%±2.88% 8.29%±2.44% 6.73%±1.19% 0.35%±0.21% 40.8K
20 54
51 - 57
Minimax M2.7
MiniMax · Modified MIT
11.71%±1.19% 15.18%±3.02% 19.07%±3.00% 5.33%±2.53% 19.57%±2.82% 0.61%±0.17% 37.0K
21 57
51 - 57
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
14.43%±2.68% 15.71%±5.60% 14.99%±7.00% 9.71%±5.29% 31.95%±7.75% 0.23%±0.27% 12.3K
22 59
58 - 59
Gemma 4 31B
Google · Apache 2.0
23.70%±3.85% 3.41%±2.40% 4.53%±3.12% 10.70%±2.39% 71.50%±17.41% 28.37%±6.71% 56.7K
🔍

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