| 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 - 1 |
Anthropic
Top Model: Claude Fable 5 (High)
|
13.34%±1.55% | 16.12%±2.68% | 30.63%±5.69% | 9.21%±2.92% | 9.40%±1.83% | 1.31%±0.13% | 16.1K |
| 🥈 | 3 2 - 9 |
OpenAI
Top Model: GPT 5.5 (xHigh)
|
8.21%±1.02% | 5.84%±1.96% | 13.63%±3.72% | 5.78%±2.02% | 14.50%±1.02% | 1.31%±0.13% | 24.4K |
| 🥉 | 7 2 - 10 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
6.93%±1.40% | 9.13%±2.66% | 15.45%±5.27% | 3.58%±2.59% | 5.19%±1.27% | 1.31%±0.13% | 21.9K |
| 4 | 14 14 - 20 |
月之暗面
Top Model: Kimi K2.7 Code
|
0.77%±1.24% | 0.82%±2.62% | 2.63%±4.26% | 1.65%±2.52% | 1.72%±2.19% | 1.31%±0.13% | 26.2K |
| 5 | 15 14 - 20 |
Google
Top Model: Gemini 3.1 Pro Preview
|
1.09%±0.70% | 0.16%±1.58% | 1.88%±2.23% | 1.37%±1.31% | 6.34%±1.27% | 1.26%±0.14% | 49.9K |
| 6 | 17 14 - 20 |
DeepSeek
Top Model: DeepSeek V4 Flash
|
1.57%±1.08% | 4.27%±2.02% | 1.61%±3.83% | 9.19%±2.19% | 4.02%±1.54% | 0.50%±0.32% | 39.0K |
| 7 | 19 14 - 21 |
MiniMax
Top Model: Minimax M3
|
2.28%±1.01% | 2.14%±2.34% | 7.20%±3.50% | 5.11%±1.98% | 1.75%±1.00% | 1.31%±0.13% | 31.9K |
| 8 | 21 19 - 21 |
阿里巴巴
Top Model: Qwen 3.6 Plus
|
4.20%±0.99% | 1.26%±1.97% | 3.80%±3.47% | 10.58%±1.94% | 3.03%±1.25% | 2.36%±0.47% | 42.0K |
| 9 | 22 22 - 26 |
xAI
Top Model: Grok 4.3 (High)
|
7.19%±0.84% | 9.41%±1.95% | 14.44%±2.35% | 6.79%±1.53% | 5.73%±1.88% | 0.44%±0.22% | 29.6K |
| 10 | 26 22 - 27 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
8.87%±3.19% | 5.53%±5.67% | 3.94%±10.80% | 17.20%±6.19% | 15.30%±6.34% | 2.37%±1.65% | 7.0K |
没有找到匹配的模型,换个关键词试试?No matching models found. Try a different keyword?
Anthropic
OpenAI
智谱 ZAI
月之暗面
Google
DeepSeek
MiniMax
阿里巴巴
xAI
NVIDIA