| 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 - 6 |
OpenAI
Top Model: GPT 5.5 (High)
|
9.22%±1.29% | 6.13%±2.30% | 14.52%±4.76% | 9.59%±2.39% | 14.13%±1.34% | 1.75%±0.21% | 26.8K |
| 🥈 | 2 1 - 8 |
Anthropic
Top Model: Claude Opus 4.7 (Thinking)
|
8.26%±1.21% | 7.86%±2.25% | 9.12%±4.42% | 9.21%±2.28% | 13.44%±1.04% | 1.69%±0.22% | 26.7K |
| 🥉 | 8 7 - 10 |
智谱 ZAI
Top Model: GLM 5.1
|
1.87%±1.39% | 4.57%±2.78% | 0.14%±4.88% | 3.01%±2.91% | 6.18%±1.50% | 1.75%±0.21% | 22.0K |
| 4 | 9 8 - 14 |
DeepSeek
Top Model: DeepSeek V4 Pro
|
0.36%±1.39% | 2.78%±2.69% | 1.66%±4.94% | 3.91%±2.88% | 1.16%±1.26% | 0.18%±0.42% | 22.3K |
| 5 | 10 8 - 19 |
Google
Top Model: Gemini 3.5 Flash
|
0.39%±1.24% | 2.02%±2.65% | 2.64%±4.12% | 1.77%±2.37% | 2.79%±1.62% | 1.71%±0.21% | 19.9K |
| 6 | 12 9 - 13 |
月之暗面
Top Model: Kimi K2.6
|
1.15%±1.26% | 0.10%±2.57% | 5.48%±4.26% | 3.91%±2.68% | 1.77%±1.75% | 1.75%±0.21% | 23.4K |
| 7 | 14 13 - 15 |
阿里巴巴
Top Model: Qwen 3.6 Plus
|
4.01%±1.43% | 1.39%±2.81% | 5.90%±5.00% | 10.96%±3.07% | 0.08%±1.75% | 1.88%±0.64% | 21.6K |
| 8 | 15 14 - 20 |
xAI
Top Model: Grok Build 0.1
|
5.31%±1.26% | 6.33%±2.92% | 15.85%±3.92% | 7.00%±2.87% | 6.15%±1.57% | 3.53%±0.64% | 15.7K |
| 9 | 16 16 - 18 |
MiniMax
Top Model: Minimax M2.7
|
8.39%±1.24% | 10.80%±2.96% | 20.06%±3.74% | 10.05%±2.61% | 2.77%±2.05% | 1.75%±0.21% | 22.2K |
没有找到匹配的模型,换个关键词试试?No matching models found. Try a different keyword?
OpenAI
Anthropic
智谱 ZAI
DeepSeek
Google
月之暗面
阿里巴巴
xAI
MiniMax