| 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 - 5 |
Anthropic
Top Model: Claude Opus 5 (High)
|
12.73%±1.63% | 15.97%±3.34% | 19.13%±5.89% | 13.36%±3.16% | 14.22%±0.84% | 0.99%±0.17% | 20.1K |
| 🥈 | 4 1 - 8 |
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
|
10.31%±1.45% | 10.02%±2.99% | 22.22%±5.29% | 9.16%±2.93% | 9.06%±1.14% | 1.08%±0.17% | 27.0K |
| 🥉 | 6 3 - 8 |
月之暗面
Top Model: Kimi K3 (Max)
|
9.53%±0.61% | 18.24%±1.20% | 17.56%±2.15% | 2.31%±1.24% | 8.47%±0.52% | 1.08%±0.17% | 89.8K |
| 4 | 11 7 - 17 |
DeepSeek
Top Model: DeepSeek V4 Pro (High) (0813)
|
6.97%±1.11% | 13.49%±2.26% | 6.38%±3.79% | 3.16%±2.46% | 10.74%±0.76% | 1.08%±0.17% | 18.8K |
| 5 | 13 7 - 19 |
阿里巴巴
Top Model: Qwen3.8 Max
|
6.46%±1.23% | 12.52%±2.65% | 6.81%±4.36% | 4.66%±2.51% | 8.22%±1.03% | 0.08%±0.30% | 14.7K |
| 6 | 14 8 - 19 |
SpaceXAI
Top Model: Grok 4.5
|
6.38%±1.18% | 4.72%±2.60% | 6.65%±4.18% | 8.49%±2.22% | 10.98%±1.30% | 1.08%±0.17% | 32.1K |
| 7 | 15 8 - 20 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
5.86%±0.83% | 7.25%±1.80% | 8.97%±2.83% | 6.12%±1.56% | 5.89%±1.01% | 1.08%±0.17% | 58.7K |
| 8 | 27 19 - 31 |
Meta
Top Model: Muse Spark 1.2 (xHigh)
|
1.60%±1.10% | 7.06%±2.70% | 6.19%±3.35% | 4.34%±2.36% | 10.42%±1.29% | 1.07%±0.17% | 18.4K |
| 9 | 28 21 - 30 |
Google
Top Model: Gemini 3.7 Flash (High)
|
1.57%±0.88% | 9.97%±2.07% | 2.04%±2.78% | 3.59%±1.91% | 2.47%±0.98% | 1.01%±0.17% | 24.1K |
| 10 | 32 24 - 36 |
腾讯
Top Model: Hy3
|
0.42%±1.30% | 1.68%±2.82% | 0.79%±4.24% | 0.78%±2.64% | 1.02%±2.13% | 1.44%±0.61% | 21.3K |
| 11 | 38 33 - 42 |
小米
Top Model: Mimo V2.5 Pro
|
2.79%±0.91% | 3.50%±2.25% | 8.15%±2.71% | 2.67%±1.74% | 0.41%±1.49% | 0.02%±0.32% | 34.1K |
| 12 | 39 34 - 42 |
MiniMax
Top Model: Minimax M3
|
3.10%±0.87% | 6.61%±2.29% | 9.60%±2.60% | 5.61%±1.75% | 5.69%±0.84% | 0.63%±0.27% | 33.6K |
| 13 | 42 36 - 44 |
Mistral
Top Model: Mistral Medium 3.5
|
5.22%±1.85% | 11.91%±4.41% | 12.18%±5.09% | 2.73%±4.19% | 2.11%±2.92% | 2.64%±1.80% | 6.4K |
| 14 | 43 37 - 44 |
Thinky
Top Model: Inkling Small
|
5.42%±1.85% | 17.40%±5.09% | 16.12%±5.27% | 5.25%±4.74% | 11.49%±1.64% | 0.19%±0.56% | 8.8K |
| 15 | 45 41 - 50 |
Upstage
Top Model: Solar Pro 4
|
8.79%±2.64% | 6.24%±6.11% | 15.29%±7.42% | 8.52%±6.22% | 12.92%±4.38% | 0.95%±2.33% | 5.4K |
| 16 | 51 44 - 50 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
12.67%±2.43% | 15.58%±5.09% | 14.23%±6.30% | 7.56%±5.06% | 26.33%±6.80% | 0.35%±0.35% | 12.3K |
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
DeepSeek
阿里巴巴
SpaceXAI
智谱 ZAI
Meta
Google
腾讯
小米
MiniMax
Mistral
NVIDIA