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 - 1
Anthropic
Top Model: Claude Fable 5 (High)
14.10%±1.56% 16.88%±2.73% 30.94%±5.70% 12.56%±2.95% 8.91%±1.85% 1.24%±0.13% 16.1K
🥈 3
2 - 7
OpenAI
Top Model: GPT 5.5 (xHigh)
8.90%±0.91% 7.69%±1.73% 13.87%±3.31% 7.18%±1.84% 14.54%±0.85% 1.24%±0.13% 32.7K
🥉 10
4 - 12
智谱 ZAI
Top Model: GLM 5.2 (Max)
6.54%±1.17% 9.46%±2.21% 13.74%±4.23% 3.44%±2.30% 4.82%±1.17% 1.24%±0.13% 29.6K
4 15
13 - 22
阿里巴巴
Top Model: Qwen3.7 Max
0.36%±2.01% 1.43%±4.14% 0.52%±6.44% 5.20%±4.97% 7.91%±2.30% 1.02%±0.24% 6.3K
5 16
13 - 23
月之暗面
Top Model: Kimi K2.7 Code
0.13%±2.60% 7.70%±4.79% 0.63%±8.70% 6.82%±6.57% 0.86%±2.95% 1.24%±0.13% 4.9K
6 17
15 - 21
Google
Top Model: Gemini 3.1 Pro Preview
0.17%±0.70% 0.72%±1.54% 0.72%±2.24% 3.47%±1.28% 6.98%±1.22% 1.20%±0.14% 58.1K
7 19
14 - 23
DeepSeek
Top Model: DeepSeek V4 Pro
0.83%±1.86% 2.34%±4.09% 3.13%±5.85% 4.61%±4.73% 4.94%±1.34% 0.99%±0.22% 6.7K
8 22
16 - 24
MiniMax
Top Model: Minimax M3
3.08%±1.78% 7.66%±4.19% 9.93%±5.32% 5.24%±4.67% 6.46%±1.19% 0.99%±0.24% 6.4K
9 23
18 - 25
小米
Top Model: Mimo V2.5 Pro
3.71%±1.87% 6.18%±4.22% 10.28%±5.58% 5.48%±5.30% 2.77%±2.41% 0.63%±0.36% 6.8K
10 26
25 - 29
SpaceXAI
Top Model: Grok 4.3 (High)
7.65%±0.79% 8.92%±1.80% 14.41%±2.09% 6.78%±1.44% 8.88%±2.03% 0.74%±0.17% 38.0K
11 30
28 - 32
NVIDIA
Top Model: Nemotron 3 Ultra
11.87%±2.84% 11.23%±5.46% 7.15%±9.03% 20.97%±5.49% 18.97%±6.56% 1.01%±1.00% 8.8K
🔍

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