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 - 3
Anthropic
Top Model: Claude Fable 5.1 (Max)
15.87%±2.84% 22.45%±3.71% 42.45%±10.94% 0.58%±6.77% 13.11%±1.33% 0.78%±0.13% 6.8K
🥈 5
3 - 10
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
9.31%±1.49% 6.68%±3.13% 22.07%±5.50% 8.88%±2.84% 8.14%±0.96% 0.78%±0.13% 29.7K
🥉 7
5 - 12
月之暗面
Top Model: Kimi K3 (Max)
7.96%±0.68% 16.58%±1.40% 14.03%±2.36% 1.24%±1.35% 7.16%±0.58% 0.78%±0.13% 97.9K
4 10
5 - 20
腾讯
Top Model: Hy4 preview
6.92%±1.51% 13.56%±2.96% 10.26%±5.61% 0.10%±3.21% 10.20%±0.79% 0.66%±0.14% 14.4K
5 12
8 - 21
智谱 ZAI
Top Model: GLM 5.2 (Max)
6.03%±0.76% 8.63%±1.64% 11.73%±2.67% 4.48%±1.38% 4.51%±0.77% 0.78%±0.13% 69.4K
6 13
8 - 23
SpaceXAI
Top Model: Grok 4.5
5.73%±1.15% 6.30%±2.55% 5.07%±4.02% 6.84%±2.28% 9.65%±1.19% 0.78%±0.13% 35.2K
7 16
4 - 33
阿里巴巴
Top Model: Qwen3.8 Max
4.96%±2.06% 10.42%±3.99% 7.86%±7.62% 1.85%±4.00% 4.83%±2.47% 0.18%±0.41% 9.0K
8 17
1 - 23
Google
Top Model: Gemini 3.8 Flash (High)
7.95%±3.65% 12.71%±6.22% 28.01%±13.09% 7.27%±10.36% 5.78%±2.49% 0.50%±0.38% 2.9K
9 18
8 - 23
DeepSeek
Top Model: DeepSeek V4 Pro (High) (0813)
5.43%±0.90% 11.75%±1.91% 5.24%±3.13% 0.67%±1.95% 8.70%±0.71% 0.78%±0.13% 34.4K
10 34
27 - 37
Meta
Top Model: Muse Spark 1.2 (xHigh)
0.46%±1.18% 6.60%±2.81% 6.33%±3.75% 6.19%±2.50% 7.46%±1.56% 0.77%±0.13% 20.8K
11 44
38 - 48
MiniMax
Top Model: Minimax M3
3.76%±0.94% 8.25%±2.54% 9.86%±2.86% 5.48%±1.86% 4.42%±0.90% 0.39%±0.19% 36.7K
12 45
38 - 48
小米
Top Model: Mimo V2.5 Pro
3.81%±0.98% 5.56%±2.51% 8.84%±2.92% 2.64%±1.87% 1.66%±1.73% 0.36%±0.32% 37.6K
13 48
40 - 51
Thinky
Top Model: Inkling Small
5.43%±1.73% 19.38%±4.89% 15.30%±5.08% 3.93%±4.09% 11.58%±1.21% 0.10%±0.46% 11.3K
14 49
47 - 51
Mistral
Top Model: Mistral Medium 3.5
7.16%±1.56% 14.49%±3.95% 12.61%±4.41% 0.50%±3.50% 6.13%±2.31% 2.08%±1.01% 8.8K
15 51
48 - 57
Upstage
Top Model: Solar Pro 4
9.87%±3.56% 8.60%±7.42% 13.71%±9.54% 1.32%±7.15% 24.95%±9.44% 0.79%±1.64% 5.8K
16 57
51 - 57
NVIDIA
Top Model: Nemotron 3 Ultra
14.43%±2.68% 15.71%±5.60% 14.99%±7.00% 9.71%±5.29% 31.95%±7.75% 0.23%±0.27% 12.3K
🔍

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