| 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)
|
12.34%±1.53% | 15.49%±3.15% | 19.85%±5.51% | 10.95%±2.98% | 14.31%±0.81% | 1.09%±0.17% | 19.8K |
| 🥈 | 4 1 - 6 |
月之暗面
Top Model: Kimi K3 (Max)
|
10.53%±0.62% | 17.84%±1.24% | 18.60%±2.24% | 6.20%±1.13% | 8.79%±0.54% | 1.19%±0.17% | 82.6K |
| 🥉 | 5 1 - 11 |
OpenAI
Top Model: GPT 5.6 Sol (xHigh)
|
9.80%±1.39% | 10.12%±2.86% | 22.03%±5.09% | 6.01%±2.88% | 9.67%±1.03% | 1.19%±0.17% | 26.2K |
| 4 | 14 8 - 19 |
阿里巴巴
Top Model: Qwen3.8 Max
|
6.29%±1.39% | 11.52%±3.10% | 6.81%±4.88% | 4.51%±2.73% | 8.41%±1.16% | 0.20%±0.34% | 11.5K |
| 5 | 15 8 - 19 |
SpaceXAI
Top Model: Grok 4.5
|
6.08%±1.15% | 5.58%±2.57% | 5.33%±4.10% | 6.71%±2.17% | 11.61%±1.14% | 1.19%±0.17% | 30.8K |
| 6 | 17 8 - 18 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
6.06%±0.86% | 7.31%±1.86% | 10.14%±3.00% | 5.53%±1.51% | 6.14%±1.12% | 1.19%±0.17% | 54.5K |
| 7 | 20 14 - 23 |
DeepSeek
Top Model: Deepseek V4 Flash (High) (20260731)
|
4.15%±0.79% | 8.61%±1.89% | 2.03%±2.66% | 3.75%±1.50% | 5.17%±0.64% | 1.19%±0.17% | 41.7K |
| 8 | 21 16 - 24 |
Google
Top Model: Gemini 3.7 Flash (High)
|
3.44%±1.05% | 9.84%±2.50% | 0.62%±3.47% | 2.57%±2.08% | 3.00%±1.17% | 1.17%±0.17% | 17.4K |
| 9 | 26 23 - 28 |
Meta
Top Model: Muse Spark 1.1
|
0.90%±0.61% | 6.42%±1.43% | 5.51%±1.81% | 3.46%±1.15% | 5.91%±1.13% | 1.16%±0.17% | 75.8K |
| 10 | 34 28 - 37 |
小米
Top Model: Mimo V2.5 Pro
|
2.22%±0.88% | 3.41%±2.19% | 7.77%±2.68% | 1.68%±1.61% | 1.71%±1.45% | 0.05%±0.32% | 32.5K |
| 11 | 35 27 - 37 |
腾讯
Top Model: Hy3
|
2.26%±1.25% | 2.26%±2.87% | 1.97%±4.14% | 8.74%±2.37% | 2.99%±1.73% | 1.29%±0.64% | 19.6K |
| 12 | 38 31 - 37 |
MiniMax
Top Model: Minimax M3
|
3.14%±0.83% | 6.61%±2.22% | 9.35%±2.53% | 6.31%±1.55% | 5.90%±0.83% | 0.68%±0.30% | 32.1K |
| 13 | 40 37 - 42 |
Thinky
Top Model: Inkling Small
|
6.69%±1.76% | 18.02%±4.91% | 14.30%±5.38% | 12.41%±3.96% | 10.89%±1.61% | 0.38%±0.50% | 8.5K |
| 14 | 42 38 - 44 |
Mistral
Top Model: Mistral Medium 3.5
|
7.52%±1.89% | 11.26%±4.52% | 10.94%±5.41% | 11.58%±3.86% | 1.42%±3.08% | 2.38%±1.77% | 6.0K |
| 15 | 46 40 - 47 |
Upstage
Top Model: Solar Pro 4
|
10.88%±2.33% | 6.43%±5.68% | 17.97%±6.19% | 15.46%±4.76% | 13.51%±4.49% | 1.03%±3.09% | 5.2K |
| 16 | 49 46 - 49 |
NVIDIA
Top Model: Nemotron 3 Ultra
|
15.32%±2.34% | 15.55%±4.99% | 15.24%±6.10% | 20.34%±4.36% | 25.76%±6.85% | 0.29%±0.42% | 12.1K |
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
阿里巴巴
SpaceXAI
智谱 ZAI
DeepSeek
Google
Meta
小米
腾讯
MiniMax
Mistral
NVIDIA