| 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)
|
12.10%±1.40% | 16.42%±2.75% | 21.37%±5.40% | 9.08%±2.52% | 12.53%±0.79% | 1.09%±0.16% | 19.1K |
| 🥈 | 4 1 - 9 |
月之暗面
Top Model: Kimi K3 (Max)
|
10.18%±1.10% | 15.49%±2.14% | 19.71%±4.00% | 7.50%±2.04% | 7.04%±0.91% | 1.17%±0.16% | 24.6K |
| 🥉 | 5 1 - 11 |
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
|
10.09%±1.69% | 8.97%±3.44% | 21.32%±6.29% | 9.28%±3.36% | 9.73%±1.21% | 1.17%±0.16% | 17.5K |
| 4 | 12 6 - 16 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
6.66%±0.92% | 9.06%±1.85% | 12.63%±3.31% | 5.64%±1.62% | 4.83%±1.13% | 1.17%±0.16% | 48.3K |
| 5 | 14 9 - 20 |
SpaceXAI
Top Model: Grok 4.5
|
5.56%±1.30% | 4.22%±2.88% | 6.06%±4.68% | 4.97%±2.43% | 11.36%±1.10% | 1.17%±0.16% | 26.7K |
| 6 | 21 17 - 26 |
DeepSeek
Top Model: Deepseek V4 Flash (High) (20260731)
|
1.98%±1.43% | 6.99%±3.24% | 1.54%±4.79% | 2.31%±3.30% | 2.53%±1.22% | 1.15%±0.16% | 12.5K |
| 7 | 22 20 - 29 |
Meta
Top Model: Muse Spark 1.1
|
0.60%±0.65% | 5.88%±1.47% | 4.86%±1.91% | 4.53%±1.23% | 5.39%±1.40% | 1.13%±0.16% | 57.9K |
| 8 | 25 21 - 31 |
阿里巴巴
Top Model: Qwen3.7 Max
|
0.19%±0.89% | 0.43%±2.16% | 6.00%±2.77% | 0.67%±1.60% | 4.27%±1.46% | 0.53%±0.26% | 25.8K |
| 9 | 26 22 - 31 |
Google
Top Model: Gemini 3.1 Pro Preview
|
0.45%±0.71% | 1.80%±1.56% | 2.67%±2.27% | 3.10%±1.24% | 10.87%±1.32% | 1.04%±0.20% | 77.6K |
| 10 | 30 22 - 36 |
腾讯
Top Model: Hy3
|
1.40%±1.52% | 2.71%±3.19% | 4.05%±5.24% | 9.48%±2.78% | 1.82%±2.01% | 0.67%±0.66% | 13.4K |
| 11 | 32 28 - 36 |
MiniMax
Top Model: Minimax M3
|
2.31%±0.86% | 4.43%±2.23% | 9.54%±2.71% | 3.54%±1.69% | 5.31%±0.85% | 0.67%±0.31% | 26.1K |
| 12 | 33 28 - 36 |
小米
Top Model: Mimo V2.5 Pro
|
2.44%±0.94% | 4.11%±2.27% | 7.18%±2.95% | 2.35%±1.74% | 1.47%±1.38% | 0.02%±0.35% | 26.4K |
| 13 | 37 36 - 38 |
Thinky
Top Model: Inkling
|
6.37%±0.90% | 9.72%±2.48% | 16.41%±2.63% | 12.20%±1.80% | 6.00%±1.11% | 0.50%±0.23% | 30.9K |
| 14 | 43 42 - 45 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
13.96%±2.36% | 16.07%±5.21% | 14.57%±6.75% | 20.33%±4.80% | 19.03%±5.81% | 0.22%±0.44% | 11.4K |
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
月之暗面
OpenAI
智谱 ZAI
SpaceXAI
DeepSeek
Meta
阿里巴巴
Google
腾讯
MiniMax
小米
NVIDIA