| 排名Rank | 综合排名 / 区间Overall Rank / Range | 模型Model | 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 | |
|---|---|---|---|---|---|---|---|---|---|
| 🥇 | 8 6 - 12 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
6.39%±0.68% | 14.80%±1.40% | 12.30%±2.39% | 0.29%±1.37% | 4.15%±0.55% | 0.38%±0.04% | 104.5K |
| 🥈 | 11 7 - 17 |
Hy4 preview
腾讯 · Apache 2.0
|
4.96%±1.13% | 12.26%±2.18% | 8.52%±4.21% | 2.92%±2.42% | 6.72%±0.60% | 0.23%±0.07% | 29.9K |
| 🥉 | 12 6 - 20 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
4.87%±1.84% | 13.75%±3.76% | 5.23%±6.30% | 1.91%±4.61% | 7.03%±1.00% | 0.26%±0.08% | 8.4K |
| 4 | 13 9 - 17 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
4.52%±0.74% | 8.19%±1.59% | 10.41%±2.58% | 3.04%±1.36% | 0.57%±0.80% | 0.38%±0.04% | 75.1K |
| 5 | 15 9 - 20 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
4.09%±0.84% | 9.55%±1.72% | 6.47%±3.00% | 1.17%±1.75% | 5.23%±0.63% | 0.37%±0.04% | 45.6K |
| 6 | 18 12 - 22 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.08%±0.65% | 11.66%±1.38% | 6.43%±2.24% | 0.82%±1.24% | 2.24%±0.62% | 0.38%±0.04% | 70.9K |
| 7 | 21 16 - 24 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
1.99%±0.77% | 6.43%±1.69% | 3.95%±2.65% | 1.52%±1.59% | 0.74%±0.62% | 0.35%±0.05% | 64.2K |
| 8 | 23 19 - 27 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
1.33%±0.73% | 12.36%±1.58% | 1.85%±2.40% | 2.32%±1.56% | 5.59%±0.73% | 0.38%±0.04% | 39.2K |
| 9 | 26 22 - 30 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
0.06%±0.85% | 11.70%±1.72% | 1.97%±2.91% | 5.90%±1.93% | 2.68%±0.52% | 0.88%±0.11% | 46.9K |
| 10 | 27 22 - 30 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.15%±1.10% | 0.07%±2.73% | 3.50%±3.72% | 1.14%±2.12% | 3.94%±0.86% | 0.10%±0.12% | 34.9K |
| 11 | 28 24 - 30 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
0.44%±0.80% | 7.17%±1.82% | 0.81%±2.71% | 2.20%±1.66% | 6.15%±0.76% | 0.22%±0.13% | 33.2K |
| 12 | 33 31 - 38 |
Hy3
腾讯 · Apache 2.0
|
4.86%±1.30% | 8.63%±3.02% | 6.98%±3.97% | 2.10%±2.66% | 3.64%±2.25% | 2.95%±1.27% | 26.9K |
| 13 | 36 33 - 39 |
Mimo V2.5 Pro
小米 · MIT
|
5.52%±0.98% | 7.84%±2.56% | 9.58%±2.90% | 4.23%±1.89% | 5.23%±1.72% | 0.71%±0.28% | 39.9K |
| 14 | 37 33 - 39 |
Minimax M3
MiniMax · MiniMax Community License
|
5.63%±0.96% | 10.83%±2.59% | 11.92%±2.84% | 7.14%±1.98% | 1.70%±1.05% | 0.05%±0.12% | 38.4K |
| 15 | 39 34 - 41 |
Inkling Small
Thinky · Apache 2.0
|
7.84%±1.55% | 20.83%±4.53% | 18.42%±4.42% | 7.45%±3.60% | 7.84%±1.16% | 0.35%±0.37% | 12.5K |
| 16 | 40 39 - 41 |
Inkling
Thinky · Apache 2.0
|
9.55%±1.06% | 19.08%±3.22% | 23.14%±2.72% | 8.42%±2.44% | 2.85%±1.39% | 0.03%±0.15% | 42.1K |
| 17 | 41 39 - 41 |
Mistral Medium 3.5
Mistral · Modified MIT
|
10.27%±1.45% | 16.74%±3.76% | 15.03%±3.96% | 3.94%±3.22% | 13.30%±2.44% | 2.34%±0.85% | 10.0K |
| 18 | 42 42 - 43 |
Minimax M2.7
MiniMax · Modified MIT
|
13.59%±1.24% | 17.02%±3.11% | 19.96%±3.17% | 6.43%±2.64% | 24.75%±2.80% | 0.19%±0.17% | 37.5K |
没有找到匹配的模型,换个关键词试试?No matching models found. Try a different keyword?
月之暗面
腾讯
DeepSeek
智谱 ZAI
阿里巴巴
小米
MiniMax
Mistral