| 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 - 6 |
Anthropic
Top Model: Claude Opus 5 (High)
|
12.01%±1.45% | 15.13%±3.03% | 19.31%±5.29% | 10.73%±2.79% | 13.74%±0.79% | 1.14%±0.19% | 19.7K |
| 🥈 | 4 1 - 10 |
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
|
10.80%±1.80% | 9.72%±3.67% | 23.35%±6.69% | 9.13%±3.69% | 10.56%±1.26% | 1.23%±0.19% | 18.1K |
| 🥉 | 5 1 - 9 |
月之暗面
Top Model: Kimi K3 (Max)
|
10.54%±1.04% | 15.42%±2.05% | 20.30%±3.77% | 7.70%±1.91% | 8.04%±0.83% | 1.23%±0.19% | 28.4K |
| 4 | 14 8 - 17 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
6.71%±0.89% | 8.51%±1.87% | 11.57%±3.15% | 6.13%±1.58% | 6.12%±1.08% | 1.23%±0.19% | 53.3K |
| 5 | 16 8 - 19 |
SpaceXAI
Top Model: Grok 4.5
|
6.00%±1.20% | 6.24%±2.69% | 4.82%±4.26% | 6.71%±2.29% | 10.98%±1.22% | 1.23%±0.19% | 29.8K |
| 6 | 19 16 - 23 |
DeepSeek
Top Model: Deepseek V4 Flash (High) (20260731)
|
3.89%±0.82% | 8.68%±1.95% | 2.27%±2.70% | 3.00%±1.58% | 4.29%±0.71% | 1.22%±0.19% | 35.4K |
| 7 | 21 16 - 23 |
Google
Top Model: Gemini 3.7 Flash (High)
|
3.36%±1.26% | 10.03%±2.96% | 0.05%±4.00% | 3.57%±2.64% | 2.05%±1.50% | 1.19%±0.20% | 12.3K |
| 8 | 24 22 - 28 |
Meta
Top Model: Muse Spark 1.1
|
1.06%±0.60% | 7.02%±1.40% | 5.13%±1.77% | 3.21%±1.14% | 5.41%±1.24% | 1.20%±0.19% | 72.1K |
| 9 | 27 22 - 32 |
阿里巴巴
Top Model: Qwen3.7 Max
|
0.09%±0.85% | 0.40%±2.11% | 4.75%±2.63% | 0.05%±1.52% | 5.05%±1.38% | 0.60%±0.27% | 30.6K |
| 10 | 32 23 - 37 |
腾讯
Top Model: Hy3
|
1.14%±1.28% | 2.16%±2.81% | 2.40%±4.42% | 8.24%±2.36% | 3.62%±1.60% | 1.29%±0.72% | 18.2K |
| 11 | 33 30 - 37 |
小米
Top Model: Mimo V2.5 Pro
|
2.24%±0.90% | 3.36%±2.20% | 7.05%±2.73% | 2.19%±1.62% | 1.42%±1.61% | 0.01%±0.34% | 31.3K |
| 12 | 37 30 - 37 |
MiniMax
Top Model: Minimax M3
|
2.54%±0.84% | 5.73%±2.20% | 8.26%±2.60% | 5.09%±1.58% | 5.66%±0.83% | 0.70%±0.33% | 31.0K |
| 13 | 39 38 - 40 |
Thinky
Top Model: Inkling
|
6.67%±0.92% | 12.22%±2.58% | 16.32%±2.62% | 12.01%±1.85% | 6.62%±1.07% | 0.58%±0.27% | 35.6K |
| 14 | 40 37 - 43 |
Mistral
Top Model: Mistral Medium 3.5
|
6.90%±2.02% | 9.55%±4.63% | 9.52%±5.75% | 10.84%±4.05% | 1.63%±3.58% | 2.98%±2.19% | 5.7K |
| 15 | 44 41 - 47 |
Upstage
Top Model: Solar Pro 4
|
11.54%±2.16% | 7.79%±5.75% | 21.14%±5.71% | 13.13%±4.04% | 16.02%±5.04% | 0.40%±0.61% | 4.6K |
| 16 | 47 44 - 48 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
14.62%±2.52% | 15.63%±5.40% | 14.20%±6.73% | 19.89%±4.72% | 23.93%±7.10% | 0.54%±0.36% | 12.0K |
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
月之暗面
智谱 ZAI
SpaceXAI
DeepSeek
Google
Meta
阿里巴巴
腾讯
小米
MiniMax
Mistral
NVIDIA