| 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 - 7 |
OpenAI
Top Model: GPT 5.5 (High)
|
10.66%±1.60% | 7.06%±2.70% | 14.95%±5.98% | 12.03%±3.06% | 17.73%±1.85% | 1.52%±0.21% | 24.9K |
| 🥈 | 2 1 - 8 |
Anthropic
Top Model: Claude Opus 4.7 (Thinking)
|
9.47%±1.50% | 7.95%±2.71% | 12.18%±5.52% | 9.04%±2.90% | 16.69%±1.51% | 1.49%±0.21% | 24.9K |
| 🥉 | 8 7 - 10 |
智谱 ZAI
Top Model: GLM 5.1
|
3.38%±2.00% | 4.63%±3.41% | 3.79%±7.15% | 3.41%±4.15% | 10.37%±2.22% | 1.52%±0.21% | 20.1K |
| 4 | 9 8 - 17 |
Google
Top Model: Gemini 3.1 Pro Preview
|
1.38%±1.45% | 0.64%±2.79% | 1.52%±4.57% | 4.33%±2.65% | 0.95%±2.78% | 1.34%±0.32% | 24.8K |
| 5 | 11 9 - 13 |
月之暗面
Top Model: Kimi K2.6
|
0.56%±1.64% | 0.88%±3.39% | 3.70%±5.68% | 8.44%±3.42% | 8.68%±2.30% | 1.52%±0.21% | 21.6K |
| 6 | 12 10 - 15 |
DeepSeek
Top Model: DeepSeek V4 Pro
|
1.88%±1.79% | 1.57%±3.43% | 1.44%±6.27% | 1.26%±3.62% | 2.78%±2.31% | 5.48%±1.25% | 20.3K |
| 7 | 13 11 - 14 |
阿里巴巴
Top Model: Qwen 3.6 Plus
|
3.40%±1.91% | 0.48%±3.61% | 5.74%±6.33% | 10.84%±4.14% | 2.37%±2.99% | 2.32%±0.95% | 19.8K |
| 8 | 15 14 - 17 |
MiniMax
Top Model: Minimax M2.7
|
8.52%±1.76% | 8.00%±3.63% | 15.73%±5.28% | 17.56%±3.60% | 2.84%±4.08% | 1.52%±0.21% | 20.4K |
| 9 | 18 18 - 18 |
xAI
Top Model: Grok 4.3
|
25.14%±2.26% | 16.12%±3.03% | 17.51%±3.70% | 3.90%±2.78% | 89.43%±9.34% | 1.24%±0.35% | 24.0K |
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
Google
月之暗面
DeepSeek
阿里巴巴
MiniMax
xAI