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)
14.17%±1.54% 16.48%±2.55% 29.65%±5.72% 13.39%±2.94% 9.46%±1.84% 1.86%±0.23% 16.2K
🥈 3
2 - 10
OpenAI
Top Model: GPT 5.5 (xHigh)
8.27%±1.73% 4.42%±3.17% 17.52%±6.44% 3.12%±3.44% 14.42%±1.24% 1.86%±0.23% 10.8K
🥉 10
3 - 13
智谱 ZAI
Top Model: GLM 5.2 (Max)
4.37%±2.48% 9.43%±4.52% 14.88%±9.11% 6.00%±4.50% 1.69%±3.28% 1.86%±0.23% 9.2K
4 14
14 - 19
DeepSeek
Top Model: DeepSeek V4 Pro
0.10%±1.41% 0.44%±3.07% 0.07%±4.86% 2.81%±3.04% 2.93%±1.33% 0.74%±0.32% 28.0K
5 15
14 - 18
Google
Top Model: Gemini 3.5 Flash
0.04%±1.00% 1.98%±2.24% 2.29%±3.28% 0.23%±1.88% 2.98%±1.31% 1.69%±0.26% 30.3K
6 16
14 - 19
月之暗面
Top Model: Kimi K2.6
0.50%±1.09% 0.36%±2.28% 1.70%±3.64% 2.82%±2.20% 0.22%±1.66% 1.86%±0.23% 33.9K
7 20
15 - 20
MiniMax
Top Model: Minimax M3
2.79%±1.70% 2.30%±3.91% 9.39%±5.50% 7.62%±3.78% 3.52%±1.40% 1.86%±0.23% 9.9K
8 21
19 - 22
阿里巴巴
Top Model: Qwen 3.6 Plus
4.24%±1.20% 2.84%±2.44% 5.58%±4.08% 8.94%±2.46% 2.42%±1.62% 1.41%±0.56% 31.9K
9 22
20 - 24
xAI
Top Model: Grok Build 0.1
6.20%±1.10% 6.78%±2.57% 11.49%±3.54% 8.64%±2.24% 1.65%±1.60% 2.42%±0.47% 27.2K
10 26
20 - 26
NVIDIA
Top Model: Nemotron 3 Ultra
8.65%±4.12% 4.39%±7.57% 5.54%±14.18% 22.66%±8.28% 12.31%±7.55% 1.63%±0.51% 3.9K
🔍

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