| 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)
|
11.99%±1.37% | 16.04%±2.79% | 19.46%±5.19% | 10.29%±2.51% | 13.07%±0.78% | 1.07%±0.16% | 19.5K |
| 🥈 | 4 1 - 10 |
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
|
10.28%±1.72% | 9.06%±3.48% | 22.70%±6.42% | 8.42%±3.50% | 10.07%±1.23% | 1.16%±0.16% | 17.8K |
| 🥉 | 5 1 - 9 |
月之暗面
Top Model: Kimi K3 (Max)
|
10.08%±1.07% | 14.97%±2.09% | 19.68%±3.85% | 7.45%±1.97% | 7.13%±0.89% | 1.16%±0.16% | 26.2K |
| 4 | 12 7 - 17 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
6.75%±0.90% | 9.21%±1.83% | 12.39%±3.21% | 5.62%±1.59% | 5.37%±1.12% | 1.16%±0.16% | 50.1K |
| 5 | 15 9 - 20 |
SpaceXAI
Top Model: Grok 4.5
|
5.57%±1.27% | 5.00%±2.82% | 5.29%±4.52% | 4.82%±2.39% | 11.57%±1.09% | 1.16%±0.16% | 27.7K |
| 6 | 21 17 - 22 |
DeepSeek
Top Model: Deepseek V4 Flash (High) (20260731)
|
2.84%±1.10% | 8.53%±2.54% | 0.46%±3.64% | 0.43%±2.19% | 3.64%±1.01% | 1.15%±0.16% | 18.9K |
| 7 | 22 21 - 28 |
Meta
Top Model: Muse Spark 1.1
|
0.91%±0.62% | 6.14%±1.43% | 4.86%±1.85% | 3.71%±1.18% | 5.89%±1.28% | 1.11%±0.16% | 62.7K |
| 8 | 25 22 - 31 |
阿里巴巴
Top Model: Qwen3.7 Max
|
0.16%±0.88% | 0.24%±2.11% | 5.07%±2.72% | 0.21%±1.55% | 4.20%±1.49% | 0.51%±0.26% | 27.4K |
| 9 | 28 23 - 31 |
Google
Top Model: Gemini 3.1 Pro Preview
|
0.54%±0.71% | 1.71%±1.57% | 2.91%±2.23% | 2.78%±1.23% | 11.13%±1.34% | 1.01%±0.20% | 79.4K |
| 10 | 30 22 - 35 |
腾讯
Top Model: Hy3
|
1.12%±1.42% | 2.20%±3.04% | 3.70%±4.91% | 9.01%±2.60% | 2.82%±1.82% | 0.89%±0.63% | 14.8K |
| 11 | 32 29 - 36 |
小米
Top Model: Mimo V2.5 Pro
|
2.42%±0.92% | 3.88%±2.24% | 7.27%±2.82% | 2.19%±1.68% | 1.30%±1.45% | 0.08%±0.35% | 27.8K |
| 12 | 33 29 - 36 |
MiniMax
Top Model: Minimax M3
|
2.47%±0.85% | 5.15%±2.21% | 9.10%±2.65% | 4.19%±1.64% | 5.48%±0.82% | 0.59%±0.33% | 27.7K |
| 13 | 37 36 - 39 |
Thinky
Top Model: Inkling
|
6.60%±0.89% | 11.06%±2.48% | 16.01%±2.60% | 12.57%±1.77% | 6.15%±1.08% | 0.48%±0.24% | 32.6K |
| 14 | 38 36 - 42 |
Mistral
Top Model: Mistral Medium 3.5
|
6.82%±2.16% | 10.43%±5.02% | 8.71%±6.47% | 11.31%±4.31% | 0.13%±2.86% | 3.53%±2.85% | 4.8K |
| 15 | 44 42 - 46 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
13.75%±2.33% | 16.20%±5.23% | 14.76%±6.61% | 19.08%±4.76% | 19.00%±5.52% | 0.30%±0.41% | 11.6K |
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
Meta
阿里巴巴
Google
腾讯
小米
MiniMax
Mistral
NVIDIA