| 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 | |
|---|---|---|---|---|---|---|---|---|---|
| 🥇 | 4 1 - 7 |
OpenAI
Top Model: GPT 5.5 (High)
|
9.11%±1.26% | 6.57%±2.21% | 13.94%±4.66% | 8.61%±2.35% | 14.45%±1.30% | 2.00%±0.29% | 28.4K |
| 🥈 | 3 1 - 10 |
Anthropic
Top Model: Claude Opus 4.8 (Thinking)
|
9.06%±1.57% | 10.77%±2.54% | 15.16%±5.67% | 9.05%±2.89% | 10.29%±1.39% | 0.03%±2.30% | 19.0K |
| 🥉 | 11 8 - 13 |
智谱 ZAI
Top Model: GLM 5.1
|
1.86%±1.35% | 4.09%±2.67% | 0.79%±4.77% | 1.58%±2.80% | 5.59%±1.56% | 2.00%±0.29% | 23.4K |
| 4 | 13 10 - 16 |
DeepSeek
Top Model: DeepSeek V4 Pro
|
0.09%±1.34% | 2.77%±2.60% | 1.67%±4.81% | 3.76%±2.78% | 1.92%±1.20% | 0.29%±0.45% | 23.7K |
| 5 | 12 10 - 21 |
Google
Top Model: Gemini 3.5 Flash
|
0.33%±1.19% | 1.73%±2.54% | 2.84%±3.96% | 1.15%±2.30% | 2.09%±1.63% | 1.96%±0.29% | 21.3K |
| 6 | 14 10 - 15 |
月之暗面
Top Model: Kimi K2.6
|
0.60%±1.22% | 1.30%±2.47% | 5.62%±4.11% | 2.61%±2.60% | 1.95%±1.66% | 2.00%±0.29% | 24.9K |
| 7 | 17 15 - 17 |
阿里巴巴
Top Model: Qwen 3.6 Plus
|
4.13%±1.39% | 1.74%±2.74% | 6.31%±4.85% | 10.50%±2.99% | 0.51%±1.74% | 1.59%±0.65% | 23.1K |
| 8 | 18 16 - 22 |
xAI
Top Model: Grok Build 0.1
|
5.15%±1.19% | 6.05%±2.66% | 13.79%±3.78% | 7.63%±2.62% | 5.38%±1.52% | 3.66%±0.63% | 18.4K |
| 9 | 19 18 - 20 |
MiniMax
Top Model: Minimax M2.7
|
8.73%±1.21% | 10.95%±2.85% | 21.03%±3.50% | 10.68%±2.52% | 2.93%±2.26% | 1.95%±0.30% | 23.6K |
没有找到匹配的模型,换个关键词试试?No matching models found. Try a different keyword?
OpenAI
Anthropic
智谱 ZAI
DeepSeek
Google
月之暗面
阿里巴巴
xAI
MiniMax