| 排名Rank | 综合排名 / 区间Overall Rank / Range | 模型Model | 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 - 1 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
14.17%±1.54% | 16.48%±2.55% | 29.65%±5.72% | 13.39%±2.94% | 9.46%±1.84% | 1.86%±0.23% | 16.2K |
| 🥈 | 2 2 - 7 |
Claude Opus 4.8 (Thinking)
Anthropic · Proprietary
|
9.04%±1.19% | 10.75%±2.15% | 14.36%±4.30% | 10.48%±2.23% | 9.08%±1.24% | 0.56%±1.20% | 27.2K |
| 🥉 | 3 2 - 10 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
8.27%±1.73% | 4.42%±3.17% | 17.52%±6.44% | 3.12%±3.44% | 14.42%±1.24% | 1.86%±0.23% | 10.8K |
| 4 | 4 2 - 10 |
Claude Opus 4.7
Anthropic · Proprietary
|
8.12%±1.51% | 4.63%±3.07% | 10.73%±5.33% | 11.69%±2.94% | 11.74%±1.45% | 1.81%±0.23% | 29.3K |
| 5 | 5 2 - 10 |
Claude Opus 4.7 (Thinking)
Anthropic · Proprietary
|
8.09%±1.48% | 4.51%±3.04% | 12.40%±5.31% | 8.66%±2.93% | 13.08%±0.99% | 1.82%±0.23% | 29.2K |
| 6 | 6 2 - 10 |
GPT 5.5 (High)
OpenAI · Proprietary
|
7.78%±1.07% | 5.93%±2.03% | 10.90%±3.80% | 7.56%±2.06% | 12.64%±1.19% | 1.86%±0.23% | 37.2K |
| 7 | 7 3 - 10 |
GPT 5.5
OpenAI · Proprietary
|
6.73%±1.03% | 4.75%±1.97% | 8.13%±3.71% | 7.86%±1.96% | 11.07%±1.27% | 1.86%±0.23% | 37.6K |
| 8 | 8 2 - 10 |
Claude Opus 4.6
Anthropic · Proprietary
|
6.73%±1.42% | 6.17%±2.98% | 7.40%±4.64% | 8.13%±2.83% | 10.11%±2.16% | 1.86%±0.23% | 29.3K |
| 9 | 9 3 - 10 |
GPT 5.4 (High)
OpenAI · Proprietary
|
6.54%±1.07% | 4.63%±2.12% | 6.55%±3.84% | 7.53%±2.12% | 12.14%±1.01% | 1.86%±0.23% | 37.4K |
| 10 | 10 3 - 13 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
4.37%±2.48% | 9.43%±4.52% | 14.88%±9.11% | 6.00%±4.50% | 1.69%±3.28% | 1.86%±0.23% | 9.2K |
| 11 | 11 10 - 13 |
Claude Opus 4.8
Anthropic · Proprietary
|
3.60%±1.55% | 7.31%±2.45% | 12.53%±4.73% | 6.05%±2.49% | 8.01%±1.40% | 15.90%±4.11% | 24.8K |
| 12 | 12 10 - 13 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
3.22%±1.38% | 2.69%±3.03% | 2.54%±4.19% | 3.98%±2.73% | 10.12%±2.45% | 1.85%±0.23% | 29.2K |
| 13 | 13 10 - 13 |
GLM 5.1
智谱 ZAI · MIT
|
2.66%±1.14% | 3.42%±2.37% | 1.34%±3.99% | 1.24%±2.33% | 5.44%±1.09% | 1.86%±0.23% | 32.4K |
| 14 | 14 14 - 19 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.10%±1.41% | 0.44%±3.07% | 0.07%±4.86% | 2.81%±3.04% | 2.93%±1.33% | 0.74%±0.32% | 28.0K |
| 15 | 15 14 - 18 |
Gemini 3.5 Flash
Google · Proprietary
|
0.04%±1.00% | 1.98%±2.24% | 2.29%±3.28% | 0.23%±1.88% | 2.98%±1.31% | 1.69%±0.26% | 30.3K |
| 16 | 16 14 - 19 |
Kimi K2.6
月之暗面 · Modified MIT
|
0.50%±1.09% | 0.36%±2.28% | 1.70%±3.64% | 2.82%±2.20% | 0.22%±1.66% | 1.86%±0.23% | 33.9K |
| 17 | 17 14 - 19 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
0.78%±0.94% | 0.09%±2.09% | 1.97%±3.02% | 2.23%±1.74% | 5.87%±1.52% | 1.80%±0.24% | 37.4K |
| 18 | 18 14 - 19 |
DeepSeek V4 Flash
DeepSeek · MIT
|
1.18%±1.33% | 4.14%±2.56% | 1.50%±4.60% | 6.59%±2.76% | 2.42%±1.80% | 0.48%±0.38% | 32.6K |
| 19 | 19 14 - 23 |
Kimi K2.7 Code
月之暗面 · Modified MIT
|
2.71%±2.39% | 3.82%±4.53% | 5.17%±7.84% | 12.25%±4.81% | 1.83%±4.94% | 1.86%±0.23% | 14.7K |
| 20 | 20 15 - 20 |
Minimax M3
MiniMax · Proprietary
|
2.79%±1.70% | 2.30%±3.91% | 9.39%±5.50% | 7.62%±3.78% | 3.52%±1.40% | 1.86%±0.23% | 9.9K |
| 21 | 21 19 - 22 |
Qwen 3.6 Plus
阿里巴巴 · Proprietary
|
4.24%±1.20% | 2.84%±2.44% | 5.58%±4.08% | 8.94%±2.46% | 2.42%±1.62% | 1.41%±0.56% | 31.9K |
| 22 | 22 20 - 24 |
Grok Build 0.1
xAI · Proprietary
|
6.20%±1.10% | 6.78%±2.57% | 11.49%±3.54% | 8.64%±2.24% | 1.65%±1.60% | 2.42%±0.47% | 27.2K |
| 23 | 23 21 - 25 |
Grok 4.3 (High)
xAI · Proprietary
|
7.21%±1.23% | 10.75%±2.83% | 15.89%±3.35% | 4.46%±2.25% | 4.44%±3.11% | 0.49%±0.55% | 15.6K |
| 24 | 24 21 - 25 |
Minimax M2.7
MiniMax · Modified MIT
|
7.81%±1.05% | 13.51%±2.58% | 15.50%±3.20% | 8.77%±2.04% | 3.05%±1.71% | 1.79%±0.25% | 32.6K |
| 25 | 25 22 - 25 |
Gemini 3 Flash
Google · Proprietary
|
8.47%±1.01% | 11.23%±2.19% | 13.73%±2.67% | 4.25%±1.78% | 14.72%±2.96% | 1.58%±0.30% | 37.5K |
| 26 | 26 20 - 26 |
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
8.65%±4.12% | 4.39%±7.57% | 5.54%±14.18% | 22.66%±8.28% | 12.31%±7.55% | 1.63%±0.51% | 3.9K |
| 27 | 27 25 - 27 |
Gemma 4 31B
Google · Apache 2.0
|
12.73%±1.97% | 5.87%±2.40% | 7.22%±3.58% | 6.20%±2.20% | 27.61%±6.38% | 16.73%±5.59% | 26.5K |
| 28 | 28 26 - 27 |
Grok 4.3
xAI · Proprietary
|
15.78%±1.46% | 12.19%±2.26% | 14.66%±2.76% | 4.01%±1.81% | 48.86%±5.94% | 0.79%±0.43% | 36.7K |
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
智谱 ZAI
DeepSeek
Google
月之暗面
MiniMax
阿里巴巴
xAI
NVIDIA