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)
13.68%±1.59% 17.21%±2.59% 27.74%±5.97% 11.27%±3.24% 10.16%±1.40% 2.00%±0.24% 16.2K
🥈 2
1 - 7
OpenAI
Top Model: GPT 5.5 (xHigh)
11.03%±2.52% 5.69%±4.32% 27.74%±9.54% 5.05%±5.05% 14.67%±1.76% 2.00%±0.24% 5.9K
🥉 12
10 - 12
智谱 ZAI
Top Model: GLM 5.1
2.88%±1.21% 5.16%±2.46% 1.22%±4.21% 1.09%±2.46% 4.94%±1.38% 2.00%±0.24% 27.5K
4 13
13 - 17
DeepSeek
Top Model: DeepSeek V4 Pro
0.22%±1.18% 2.42%±2.50% 1.35%±4.12% 2.74%±2.46% 2.15%±1.10% 0.61%±0.37% 26.8K
5 14
13 - 17
Google
Top Model: Gemini 3.5 Flash
0.06%±1.06% 2.85%±2.38% 1.65%±3.55% 0.24%±2.02% 3.08%±1.27% 1.94%±0.24% 25.5K
6 15
13 - 18
月之暗面
Top Model: Kimi K2.6
0.63%±1.09% 0.62%±2.34% 4.08%±3.66% 3.14%±2.25% 1.45%±1.49% 2.00%±0.24% 29.0K
7 18
18 - 20
阿里巴巴
Top Model: Qwen 3.6 Plus
4.52%±1.21% 1.74%±2.51% 8.04%±4.02% 9.57%±2.61% 1.79%±1.75% 1.47%±0.59% 27.1K
8 19
18 - 22
xAI
Top Model: Grok Build 0.1
6.28%±1.11% 6.19%±2.62% 12.45%±3.51% 9.84%±2.37% 1.93%±1.60% 4.85%±0.69% 22.5K
9 20
15 - 24
NVIDIA
Top Model: Nemotron 3 Ultra
6.81%±5.22% 3.00%±8.86% 2.58%±19.26% 23.87%±10.36% 11.75%±9.55% 2.00%±0.24% 2.7K
10 21
19 - 23
MiniMax
Top Model: Minimax M2.7
7.43%±1.10% 10.72%±2.65% 16.78%±3.36% 9.09%±2.16% 2.51%±1.77% 1.96%±0.25% 27.8K
🔍

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