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
🥉 3
1 - 9
Kimi K3 (Max)
月之暗面 · Kimi K3 license
9.75%±1.17% 14.83%±2.42% 16.22%±4.17% 9.17%±2.18% 7.18%±1.05% 1.35%±0.19% 19.2K
10 10
4 - 14
GLM 5.2 (Max)
智谱 ZAI · MIT
7.12%±0.95% 9.07%±1.93% 13.85%±3.43% 5.86%±1.69% 5.46%±1.09% 1.35%±0.19% 42.9K
20 20
19 - 27
GLM 5.1
智谱 ZAI · MIT
0.72%±0.79% 1.47%±1.75% 0.88%±2.61% 0.26%±1.45% 0.90%±1.30% 0.62%±0.33% 62.3K
21 21
16 - 29
Kimi K2.7 Code
月之暗面 · Modified MIT
0.38%±1.80% 4.36%±3.62% 3.28%±6.37% 3.89%±3.60% 3.22%±2.88% 1.35%±0.19% 10.3K
25 25
19 - 31
DeepSeek V4 Pro
DeepSeek · MIT
0.72%±0.95% 4.01%±2.43% 5.05%±3.06% 0.45%±1.75% 5.15%±0.98% 0.78%±0.25% 21.1K
27 27
19 - 32
Kimi K2.6
月之暗面 · Modified MIT
1.00%±1.92% 2.91%±3.65% 1.26%±6.11% 4.42%±3.72% 6.08%±3.90% 1.35%±0.19% 10.4K
28 28
19 - 32
Hy3
腾讯 · Apache 2.0
1.08%±1.92% 2.28%±4.08% 3.41%±6.70% 8.16%±3.52% 1.34%±2.72% 0.30%±0.55% 8.1K
30 30
24 - 32
Minimax M3
MiniMax · MiniMax Community License
2.55%±0.93% 6.18%±2.44% 9.17%±2.95% 4.52%±1.83% 6.28%±0.86% 0.84%±0.37% 20.7K
31 31
24 - 32
Mimo V2.5 Pro
小米 · MIT
2.57%±1.00% 4.11%±2.47% 8.63%±3.08% 1.93%±1.90% 1.35%±1.66% 0.49%±0.31% 21.1K
32 32
26 - 32
DeepSeek V4 Flash
DeepSeek · MIT
2.95%±0.95% 4.97%±2.52% 8.99%±2.95% 3.75%±1.79% 3.79%±1.00% 0.85%±0.41% 20.5K
34 34
33 - 35
Inkling
Thinky · Apache 2.0
5.62%±0.88% 6.67%±2.38% 15.95%±2.62% 12.15%±1.84% 6.25%±1.02% 0.41%±0.29% 24.7K
39 39
38 - 40
Minimax M2.7
MiniMax · Modified MIT
11.11%±1.19% 14.73%±2.83% 14.54%±3.42% 14.17%±2.21% 13.21%±2.82% 1.10%±0.26% 20.9K
40 40
38 - 42
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
13.08%±2.31% 14.76%±5.15% 14.01%±6.87% 20.68%±4.91% 16.17%±5.19% 0.20%±0.53% 10.8K
42 42
40 - 42
Gemma 4 31B
Google · Apache 2.0
15.91%±1.91% 1.21%±1.81% 3.94%±2.69% 8.32%±1.61% 37.64%±6.35% 28.43%±6.20% 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?