| 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 - 4 |
Anthropic
Top Model: Claude Fable 5.1 (Max)
|
14.55%±1.92% | 17.46%±2.90% | 33.73%±7.89% | 8.95%±2.83% | 12.31%±0.96% | 0.32%±0.03% | 14.6K |
| 🥈 | 3 1 - 7 |
OpenAI
Top Model: GPT 6 Astra (Max)
|
12.18%±2.28% | 12.03%±4.03% | 34.70%±9.48% | 8.24%±2.73% | 5.59%±1.63% | 0.32%±0.03% | 11.1K |
| 🥉 | 8 1 - 13 |
Google
Top Model: Gemini 4 Argon (High)
|
11.58%±6.42% | 14.04%±9.96% | 38.08%±26.33% | 12.36%±4.79% | 6.85%±9.76% | 0.26%±0.04% | 1.1K |
| 4 | 12 10 - 20 |
腾讯
Top Model: Hy4 preview
|
4.24%±0.85% | 6.37%±1.74% | 7.67%±3.20% | 0.92%±1.07% | 6.26%±0.55% | 0.00%±0.30% | 53.7K |
| 5 | 13 10 - 19 |
Meta
Top Model: Muse Spark 1.3 (Max)
|
4.19%±0.59% | 6.25%±1.29% | 3.27%±2.09% | 5.50%±0.75% | 5.62%±0.59% | 0.32%±0.03% | 61.4K |
| 6 | 15 11 - 19 |
DeepSeek
Top Model: Deepseek V4.1 Flash (Max)
|
4.01%±0.50% | 8.65%±1.10% | 2.21%±1.83% | 1.19%±0.69% | 7.77%±0.33% | 0.20%±0.04% | 95.9K |
| 7 | 16 11 - 20 |
月之暗面
Top Model: Kimi K3 (Max)
|
3.98%±0.53% | 7.32%±1.18% | 6.61%±1.89% | 1.42%±0.73% | 4.25%±0.50% | 0.32%±0.03% | 129.9K |
| 8 | 17 4 - 29 |
SpaceXAI
Top Model: Grok 4.7 (xHigh)
|
4.13%±3.18% | 13.14%±5.76% | 3.57%±13.42% | 3.68%±4.48% | 7.37%±3.12% | 0.26%±0.04% | 3.6K |
| 9 | 18 11 - 23 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
3.64%±0.74% | 5.23%±1.54% | 10.17%±2.67% | 1.77%±0.95% | 0.68%±0.83% | 0.32%±0.03% | 83.7K |
| 10 | 20 13 - 24 |
阿里巴巴
Top Model: Qwen3.8 Max
|
2.80%±0.65% | 5.24%±1.46% | 4.21%±2.35% | 3.05%±0.86% | 2.65%±0.71% | 1.13%±0.21% | 49.2K |
| 11 | 38 36 - 42 |
MiniMax
Top Model: Minimax M3
|
6.71%±0.89% | 13.06%±2.49% | 14.31%±2.56% | 6.93%±1.46% | 0.87%±1.06% | 0.12%±0.18% | 40.8K |
| 12 | 39 37 - 42 |
小米
Top Model: Mimo V2.5 Pro
|
7.23%±0.91% | 9.40%±2.34% | 11.77%±2.66% | 7.43%±1.39% | 6.54%±1.61% | 1.00%±0.27% | 44.4K |
| 13 | 43 41 - 45 |
Thinky
Top Model: Inkling Small
|
9.80%±1.42% | 19.51%±4.33% | 21.63%±3.68% | 13.12%±2.78% | 5.64%±1.37% | 0.37%±0.29% | 13.0K |
| 14 | 45 43 - 45 |
Mistral
Top Model: Mistral Medium 3.5
|
11.74%±1.50% | 13.52%±3.80% | 16.67%±3.93% | 5.72%±2.23% | 20.42%±3.34% | 2.35%±0.80% | 10.8K |
| 15 | 46 46 - 46 |
Upstage
Top Model: Solar Pro 4
|
15.77%±1.91% | 20.84%±5.48% | 22.11%±4.67% | 9.10%±3.11% | 25.09%±3.90% | 1.71%±0.66% | 9.2K |
没有找到匹配的模型,换个关键词试试?No matching models found. Try a different keyword?
Anthropic
OpenAI
Google
腾讯
Meta
DeepSeek
月之暗面
SpaceXAI
智谱 ZAI
阿里巴巴
MiniMax
小米
Mistral