| 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)
|
14.51%±1.90% | 23.19%±2.61% | 39.46%±7.40% | 1.21%±4.21% | 10.71%±1.13% | 0.39%±0.04% | 11.8K |
| 🥈 | 2 1 - 5 |
OpenAI
Top Model: GPT 6 Astra (Max)
|
12.55%±2.18% | 21.85%±2.92% | 40.61%±8.16% | 5.46%±5.71% | 5.33%±1.35% | 0.39%±0.04% | 8.9K |
| 🥉 | 8 6 - 12 |
月之暗面
Top Model: Kimi K3 (Max)
|
6.59%±0.70% | 15.43%±1.43% | 12.90%±2.43% | 0.15%±1.38% | 4.39%±0.56% | 0.39%±0.04% | 99.8K |
| 4 | 10 6 - 17 |
腾讯
Top Model: Hy4 preview
|
5.37%±1.40% | 12.00%±2.70% | 8.98%±5.24% | 1.92%±3.01% | 7.52%±0.70% | 0.29%±0.07% | 17.1K |
| 5 | 12 9 - 17 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
4.64%±0.75% | 8.06%±1.61% | 11.03%±2.61% | 2.92%±1.37% | 0.79%±0.87% | 0.39%±0.04% | 71.8K |
| 6 | 13 9 - 18 |
DeepSeek
Top Model: DeepSeek V4 Pro (High) (0813)
|
4.43%±0.92% | 11.13%±1.88% | 6.03%±3.27% | 1.09%±1.94% | 5.68%±0.70% | 0.39%±0.04% | 37.3K |
| 7 | 14 1 - 19 |
Google
Top Model: Gemini 3.8 Flash (High)
|
7.36%±3.73% | 12.16%±6.16% | 28.49%±13.08% | 8.41%±10.99% | 4.45%±2.53% | 0.10%±0.35% | 2.9K |
| 8 | 15 5 - 25 |
SpaceXAI
Top Model: Grok 4.5
|
4.26%±2.01% | 5.15%±4.22% | 1.55%±7.40% | 4.79%±4.01% | 9.44%±1.83% | 0.35%±0.07% | 15.7K |
| 9 | 16 5 - 25 |
阿里巴巴
Top Model: Qwen3.8 Max
|
3.93%±2.01% | 9.72%±3.92% | 7.88%±7.40% | 0.03%±3.96% | 2.75%±2.42% | 0.72%±0.43% | 9.7K |
| 10 | 29 26 - 31 |
Meta
Top Model: Muse Spark 1.2 (xHigh)
|
1.56%±1.23% | 3.02%±2.99% | 8.20%±4.01% | 8.30%±2.59% | 5.31%±1.54% | 0.39%±0.04% | 23.2K |
| 11 | 33 32 - 38 |
小米
Top Model: Mimo V2.5 Pro
|
5.08%±0.99% | 7.14%±2.55% | 9.35%±2.94% | 3.64%±1.91% | 4.54%±1.75% | 0.72%±0.30% | 38.4K |
| 12 | 35 32 - 38 |
MiniMax
Top Model: Minimax M3
|
5.26%±0.95% | 9.85%±2.59% | 11.42%±2.85% | 6.98%±1.90% | 1.93%±0.98% | 0.03%±0.13% | 37.5K |
| 13 | 38 32 - 41 |
Thinky
Top Model: Inkling Small
|
6.89%±1.64% | 19.61%±4.69% | 16.64%±4.81% | 6.21%±3.86% | 8.39%±1.15% | 0.41%±0.40% | 12.0K |
| 14 | 40 38 - 41 |
Mistral
Top Model: Mistral Medium 3.5
|
9.35%±1.51% | 16.67%±3.86% | 13.60%±4.21% | 3.20%±3.34% | 10.73%±2.30% | 2.53%±0.96% | 9.4K |
| 15 | 41 38 - 43 |
Upstage
Top Model: Solar Pro 4
|
11.29%±3.75% | 9.99%±7.81% | 14.57%±9.94% | 2.12%±7.53% | 28.58%±10.00% | 1.20%±1.63% | 5.8K |
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
月之暗面
腾讯
智谱 ZAI
DeepSeek
Google
SpaceXAI
阿里巴巴
Meta
小米
MiniMax
Mistral