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 - 4
Anthropic
Top Model: Claude Fable 5 (High)
13.22%±1.98% 11.71%±3.77% 24.97%±7.41% 15.64%±3.76% 12.67%±1.31% 1.08%±0.12% 23.5K
🥈 3
1 - 9
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
9.86%±1.66% 7.64%±3.30% 21.97%±6.41% 9.95%±2.77% 8.64%±1.22% 1.08%±0.12% 15.5K
🥉 4
1 - 10
月之暗面
Top Model: Kimi K3
9.62%±1.87% 14.42%±3.44% 20.62%±6.90% 5.58%±4.07% 6.41%±1.52% 1.08%±0.12% 8.3K
4 11
6 - 15
智谱 ZAI
Top Model: GLM 5.2 (Max)
6.47%±1.02% 8.53%±2.02% 12.29%±3.67% 5.59%±1.82% 4.85%±1.17% 1.08%±0.12% 37.2K
5 13
6 - 15
SpaceXAI
Top Model: Grok 4.5
6.42%±1.28% 6.21%±2.67% 9.01%±4.72% 4.95%±2.21% 10.86%±1.01% 1.08%±0.12% 20.9K
6 18
16 - 22
Meta
Top Model: Muse Spark 1.1
1.22%±0.95% 4.97%±2.15% 2.32%±2.96% 4.01%±1.80% 6.39%±1.67% 1.06%±0.12% 24.9K
7 19
17 - 25
阿里巴巴
Top Model: Qwen3.7 Max
0.33%±1.10% 1.91%±2.71% 4.71%±3.60% 0.62%±2.09% 7.09%±1.45% 0.55%±0.27% 15.0K
8 20
18 - 25
Google
Top Model: Gemini 3.1 Pro Preview
0.19%±0.68% 2.13%±1.50% 1.08%±2.23% 3.26%±1.23% 8.41%±1.16% 1.01%±0.13% 66.6K
9 24
19 - 27
DeepSeek
Top Model: DeepSeek V4 Pro
0.84%±1.09% 3.42%±2.76% 5.50%±3.51% 1.45%±2.12% 5.63%±1.02% 0.56%±0.24% 15.5K
10 26
22 - 28
MiniMax
Top Model: Minimax M3
2.74%±1.08% 7.09%±2.81% 9.27%±3.42% 4.25%±2.21% 6.12%±0.95% 0.77%±0.21% 15.0K
11 27
22 - 29
小米
Top Model: Mimo V2.5 Pro
2.98%±1.13% 6.30%±2.84% 8.88%±3.51% 2.50%±2.21% 2.53%±1.68% 0.22%±0.32% 15.5K
12 29
27 - 32
Thinky
Top Model: Inkling
5.70%±1.60% 5.61%±4.17% 17.97%±4.56% 10.42%±3.69% 6.41%±1.92% 0.92%±0.58% 7.6K
13 35
34 - 37
NVIDIA
Top Model: Nemotron 3 Ultra
12.90%±2.43% 14.43%±5.14% 10.80%±7.44% 19.21%±4.85% 19.61%±5.56% 0.46%±0.69% 10.1K
🔍

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