| 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)
|
14.07%±1.56% | 16.51%±2.73% | 30.91%±5.69% | 12.65%±2.93% | 8.99%±1.84% | 1.26%±0.15% | 16.1K |
| 🥈 | 3 2 - 8 |
OpenAI
Top Model: GPT 5.5 (xHigh)
|
8.39%±0.94% | 6.48%±1.82% | 13.32%±3.38% | 6.41%±1.92% | 14.46%±0.89% | 1.26%±0.15% | 30.3K |
| 🥉 | 9 3 - 11 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
6.72%±1.24% | 9.41%±2.32% | 14.85%±4.50% | 3.25%±2.46% | 4.83%±1.24% | 1.26%±0.15% | 27.2K |
| 4 | 15 11 - 22 |
月之暗面
Top Model: kimi-k2.7-code
|
0.74%±3.33% | 9.36%±5.66% | 2.99%±10.97% | 11.45%±9.87% | 1.52%±2.87% | 1.26%±0.15% | 3.1K |
| 5 | 16 14 - 19 |
Google
Top Model: Gemini 3.1 Pro Preview
|
0.55%±0.70% | 0.22%±1.57% | 0.34%±2.21% | 3.07%±1.30% | 6.89%±1.23% | 1.21%±0.15% | 55.6K |
| 6 | 17 14 - 22 |
DeepSeek
Top Model: DeepSeek V4 Flash
|
1.00%±1.26% | 4.48%±2.43% | 4.30%±4.46% | 8.47%±2.42% | 4.91%±1.79% | 0.39%±0.32% | 40.1K |
| 7 | 21 15 - 22 |
MiniMax
Top Model: Minimax M3
|
2.45%±1.09% | 3.53%±2.66% | 7.43%±3.66% | 4.94%±2.19% | 2.38%±0.97% | 1.26%±0.15% | 34.0K |
| 8 | 24 20 - 24 |
阿里巴巴
Top Model: Qwen 3.6 Plus
|
4.77%±1.04% | 1.99%±2.20% | 5.39%±3.48% | 10.30%±2.12% | 3.95%±1.38% | 2.24%±0.47% | 43.5K |
| 9 | 26 23 - 29 |
xAI
Top Model: Grok 4.3 (High)
|
7.66%±0.82% | 8.84%±1.85% | 14.45%±2.16% | 6.58%±1.48% | 9.09%±2.11% | 0.68%±0.19% | 35.6K |
| 10 | 30 24 - 31 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
11.26%±2.94% | 8.88%±5.48% | 6.49%±9.33% | 19.94%±5.80% | 19.71%±6.92% | 1.28%±1.13% | 8.3K |
没有找到匹配的模型,换个关键词试试?No matching models found. Try a different keyword?
Anthropic
OpenAI
智谱 ZAI
月之暗面
Google
DeepSeek
MiniMax
阿里巴巴
xAI
NVIDIA