| 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)
|
12.99%±1.71% | 15.45%±3.56% | 19.69%±6.32% | 14.42%±3.25% | 14.45%±0.90% | 0.94%±0.16% | 20.5K |
| 🥈 | 4 1 - 8 |
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
|
10.24%±1.48% | 9.83%±3.07% | 21.35%±5.47% | 9.69%±2.92% | 9.28%±1.09% | 1.02%±0.16% | 27.5K |
| 🥉 | 6 4 - 8 |
月之暗面
Top Model: Kimi K3 (Max)
|
9.22%±0.61% | 17.88%±1.22% | 17.03%±2.15% | 1.99%±1.23% | 8.20%±0.53% | 1.02%±0.16% | 92.3K |
| 4 | 11 7 - 18 |
阿里巴巴
Top Model: Qwen3.8 Max
|
6.66%±1.18% | 12.73%±2.49% | 8.05%±4.20% | 4.71%±2.40% | 7.77%±1.00% | 0.07%±0.28% | 16.5K |
| 5 | 12 7 - 18 |
DeepSeek
Top Model: DeepSeek V4 Pro (High) (0813)
|
6.58%±1.09% | 13.63%±2.20% | 5.80%±3.69% | 2.50%±2.45% | 9.98%±0.88% | 1.02%±0.16% | 20.4K |
| 6 | 14 7 - 18 |
SpaceXAI
Top Model: Grok 4.5
|
6.48%±1.18% | 4.99%±2.59% | 6.95%±4.18% | 8.68%±2.22% | 10.75%±1.26% | 1.02%±0.16% | 32.9K |
| 7 | 16 8 - 18 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
5.94%±0.79% | 7.82%±1.74% | 9.28%±2.74% | 5.88%±1.49% | 5.72%±0.93% | 1.02%±0.16% | 61.3K |
| 8 | 28 22 - 31 |
Google
Top Model: Gemini 3.7 Flash (High)
|
1.33%±0.87% | 9.82%±2.06% | 1.75%±2.81% | 4.42%±1.86% | 2.08%±0.99% | 0.95%±0.17% | 24.4K |
| 9 | 29 21 - 32 |
Meta
Top Model: Muse Spark 1.2 (xHigh)
|
1.32%±1.11% | 6.70%±2.74% | 6.39%±3.35% | 4.81%±2.39% | 10.09%±1.33% | 1.01%±0.16% | 18.4K |
| 10 | 35 27 - 42 |
腾讯
Top Model: Hy3
|
1.19%±1.28% | 2.86%±2.87% | 2.96%±4.07% | 0.46%±2.60% | 0.97%±2.07% | 1.57%±0.64% | 22.2K |
| 11 | 39 33 - 42 |
小米
Top Model: Mimo V2.5 Pro
|
2.68%±0.93% | 3.82%±2.29% | 7.44%±2.81% | 2.31%±1.75% | 0.30%±1.47% | 0.14%±0.34% | 34.9K |
| 12 | 40 34 - 42 |
MiniMax
Top Model: Minimax M3
|
2.79%±0.89% | 5.87%±2.30% | 8.82%±2.73% | 5.50%±1.77% | 5.69%±0.83% | 0.55%±0.26% | 34.3K |
| 13 | 43 41 - 46 |
Mistral
Top Model: Mistral Medium 3.5
|
5.76%±1.82% | 13.60%±4.36% | 12.05%±4.98% | 2.10%±4.20% | 2.53%±2.78% | 2.71%±1.64% | 6.7K |
| 14 | 44 41 - 46 |
Thinky
Top Model: Inkling Small
|
6.18%±1.89% | 18.21%±5.24% | 18.38%±5.05% | 6.52%±4.96% | 11.94%±1.54% | 0.27%±0.46% | 9.2K |
| 15 | 46 43 - 52 |
Upstage
Top Model: Solar Pro 4
|
9.38%±3.04% | 7.68%±6.45% | 13.96%±8.08% | 4.15%±6.54% | 20.46%±7.63% | 0.68%±1.91% | 5.8K |
| 16 | 52 46 - 52 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
12.92%±2.46% | 15.58%±5.19% | 14.62%±6.39% | 7.70%±5.10% | 27.03%±6.89% | 0.33%±0.34% | 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
阿里巴巴
DeepSeek
SpaceXAI
智谱 ZAI
Google
Meta
腾讯
小米
MiniMax
Mistral
NVIDIA