排名Rank 综合排名 / 区间Overall Rank / Range 厂商Lab 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
🥇 1
1 - 2
Anthropic
Top Model: Claude Fable 5 (High)
12.94%±2.10% 17.55%±3.21% 28.86%±7.97% 5.39%±4.14% 10.87%±1.76% 2.05%±0.26% 11.7K
🥈 2
1 - 9
OpenAI
Top Model: GPT 5.5 (xHigh)
10.56%±3.05% 5.36%±5.15% 29.39%±11.53% 1.86%±5.95% 14.11%±2.30% 2.05%±0.26% 4.5K
🥉 12
10 - 13
智谱 ZAI
Top Model: GLM 5.1
2.44%±1.23% 4.74%±2.52% 0.63%±4.28% 0.28%±2.51% 5.06%±1.46% 2.05%±0.26% 26.2K
4 13
12 - 17
DeepSeek
Top Model: DeepSeek V4 Pro
0.05%±1.21% 2.55%±2.50% 1.58%±4.24% 3.30%±2.48% 1.99%±1.13% 0.57%±0.39% 26.5K
5 14
13 - 17
Google
Top Model: Gemini 3.5 Flash
0.21%±1.08% 2.76%±2.42% 2.15%±3.59% 0.98%±2.06% 2.84%±1.34% 1.99%±0.27% 24.2K
6 15
13 - 17
月之暗面
Top Model: Kimi K2.6
0.45%±1.10% 0.24%±2.39% 4.00%±3.73% 2.78%±2.30% 2.25%±1.39% 2.05%±0.26% 27.6K
7 18
18 - 19
阿里巴巴
Top Model: Qwen 3.6 Plus
4.12%±1.25% 1.82%±2.56% 7.04%±4.18% 8.97%±2.69% 1.65%±1.80% 1.12%±0.57% 25.8K
8 19
18 - 20
xAI
Top Model: Grok Build 0.1
5.87%±1.14% 6.63%±2.65% 12.34%±3.59% 8.82%±2.38% 3.30%±1.56% 4.85%±0.72% 21.2K
9 20
19 - 22
MiniMax
Top Model: Minimax M2.7
7.86%±1.10% 10.66%±2.67% 18.85%±3.29% 9.10%±2.24% 2.68%±1.85% 2.01%±0.27% 26.5K
🔍

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