| 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 - 4 |
Anthropic
Top Model: Claude Fable 5.1 (Max)
|
13.85%±1.92% | 22.39%±3.04% | 36.35%±7.68% | 0.91%±3.86% | 11.07%±1.00% | 0.37%±0.04% | 12.4K |
| 🥈 | 2 1 - 8 |
OpenAI
Top Model: GPT 6 Astra (Max)
|
12.91%±5.25% | 22.20%±7.09% | 45.41%±21.23% | 10.10%±9.32% | 6.73%±3.74% | 0.33%±0.06% | 3.7K |
| 🥉 | 8 6 - 13 |
月之暗面
Top Model: Kimi K3 (Max)
|
6.46%±0.70% | 15.11%±1.43% | 12.49%±2.43% | 0.02%±1.39% | 4.29%±0.56% | 0.38%±0.04% | 101.0K |
| 4 | 10 6 - 18 |
腾讯
Top Model: Hy4 preview
|
5.23%±1.31% | 11.82%±2.51% | 9.50%±4.85% | 2.65%±2.83% | 7.24%±0.67% | 0.25%±0.07% | 19.6K |
| 5 | 12 9 - 18 |
智谱 ZAI
Top Model: GLM 5.2 (Max)
|
4.56%±0.74% | 8.10%±1.58% | 10.71%±2.57% | 3.16%±1.36% | 0.46%±0.85% | 0.38%±0.04% | 73.4K |
| 6 | 13 8 - 23 |
Meta
Top Model: Muse Spark 1.3 (Max)
|
4.23%±1.77% | 8.37%±3.65% | 5.26%±5.80% | 1.38%±4.47% | 5.75%±1.31% | 0.38%±0.04% | 8.8K |
| 7 | 14 9 - 20 |
DeepSeek
Top Model: DeepSeek V4 Pro (High) (0813)
|
4.14%±0.92% | 10.70%±1.87% | 6.03%±3.27% | 1.61%±1.93% | 5.20%±0.72% | 0.38%±0.04% | 39.0K |
| 8 | 15 5 - 22 |
阿里巴巴
Top Model: Qwen3.8 Max
|
4.66%±1.98% | 10.84%±3.79% | 10.14%±7.34% | 0.22%±3.91% | 2.84%±2.32% | 0.72%±0.41% | 10.1K |
| 9 | 16 1 - 20 |
Google
Top Model: Gemini 3.8 Flash (High)
|
7.19%±3.77% | 11.70%±6.19% | 28.54%±13.11% | 8.73%±11.31% | 4.39%±2.56% | 0.08%±0.35% | 2.9K |
| 10 | 17 5 - 25 |
SpaceXAI
Top Model: Grok 4.5
|
4.29%±2.03% | 4.03%±4.26% | 2.32%±7.52% | 5.06%±4.02% | 9.72%±1.80% | 0.33%±0.06% | 15.9K |
| 11 | 34 33 - 39 |
MiniMax
Top Model: Minimax M3
|
5.38%±0.95% | 10.21%±2.57% | 11.54%±2.86% | 6.82%±1.91% | 1.66%±1.01% | 0.03%±0.13% | 37.9K |
| 12 | 37 33 - 39 |
小米
Top Model: Mimo V2.5 Pro
|
5.42%±0.98% | 7.28%±2.54% | 10.16%±2.87% | 3.78%±1.90% | 5.17%±1.79% | 0.74%±0.30% | 38.9K |
| 13 | 39 33 - 41 |
Thinky
Top Model: Inkling Small
|
7.09%±1.58% | 19.89%±4.54% | 17.32%±4.62% | 5.97%±3.71% | 8.11%±1.14% | 0.38%±0.38% | 12.4K |
| 14 | 41 39 - 41 |
Mistral
Top Model: Mistral Medium 3.5
|
10.12%±1.47% | 16.44%±3.77% | 14.95%±4.01% | 4.37%±3.28% | 12.44%±2.43% | 2.41%±0.89% | 9.9K |
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
腾讯
智谱 ZAI
Meta
DeepSeek
阿里巴巴
Google
SpaceXAI
MiniMax
小米
Mistral