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)
14.06%±1.56% 16.58%±2.73% 30.97%±5.69% 12.63%±2.93% 8.89%±1.85% 1.24%±0.15% 16.1K
🥈 3
2 - 8
OpenAI
Top Model: GPT 5.5 (xHigh)
8.52%±0.92% 6.91%±1.77% 13.02%±3.31% 6.93%±1.88% 14.48%±0.88% 1.24%±0.15% 31.5K
🥉 9
3 - 12
智谱 ZAI
Top Model: GLM 5.2 (Max)
6.62%±1.20% 8.88%±2.26% 14.70%±4.36% 3.41%±2.38% 4.88%±1.19% 1.24%±0.15% 28.4K
4 15
15 - 18
Google
Top Model: Gemini 3.1 Pro Preview
0.41%±0.69% 0.51%±1.55% 0.15%±2.20% 3.35%±1.29% 6.96%±1.21% 1.20%±0.15% 56.8K
5 16
15 - 20
月之暗面
Top Model: Kimi K2.7 Code
1.06%±1.35% 0.24%±2.93% 2.71%±4.50% 2.12%±2.69% 1.46%±2.27% 1.24%±0.15% 28.6K
6 17
15 - 20
DeepSeek
Top Model: DeepSeek V4 Flash
1.19%±1.28% 4.61%±2.50% 3.82%±4.51% 8.77%±2.48% 5.21%±1.81% 0.39%±0.31% 40.3K
7 19
16 - 20
MiniMax
Top Model: Minimax M3
2.26%±1.11% 2.96%±2.70% 7.22%±3.73% 4.98%±2.24% 2.63%±0.96% 1.24%±0.15% 34.3K
8 21
20 - 22
阿里巴巴
Top Model: Qwen 3.6 Plus
4.73%±1.06% 1.83%±2.22% 5.22%±3.50% 10.07%±2.16% 4.26%±1.40% 2.27%±0.47% 43.5K
9 22
22 - 26
xAI
Top Model: Grok 4.3 (High)
7.64%±0.80% 9.06%±1.82% 14.10%±2.12% 6.67%±1.46% 9.08%±2.08% 0.70%±0.18% 36.9K
10 27
24 - 28
NVIDIA
Top Model: Nemotron 3 Ultra
11.75%±2.88% 10.10%±5.46% 6.89%±9.08% 21.04%±5.64% 19.53%±6.77% 1.17%±1.07% 8.6K
🔍

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