| 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
|
13.34%±1.55% | 16.12%±2.68% | 30.63%±5.69% | 9.21%±2.92% | 9.40%±1.83% | 1.31%±0.13% | 16.1K |
| 🥈 | 2 2 - 6 |
Claude Opus 4.8 (Thinking)
Anthropic · Proprietary
|
9.37%±1.29% | 8.59%±2.39% | 17.48%±4.79% | 10.34%±2.39% | 9.85%±1.09% | 0.59%±0.49% | 30.5K |
| 🥉 | 3 2 - 9 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
8.21%±1.02% | 5.84%±1.96% | 13.63%±3.72% | 5.78%±2.02% | 14.50%±1.02% | 1.31%±0.13% | 24.4K |
| 4 | 4 2 - 10 |
Claude Opus 4.7
Anthropic · Proprietary
|
8.16%±1.28% | 5.46%±2.47% | 13.69%±4.65% | 9.10%±2.25% | 11.29%±1.64% | 1.26%±0.13% | 31.7K |
| 5 | 5 2 - 10 |
Claude Opus 4.7 (Thinking)
Anthropic · Proprietary
|
8.07%±1.23% | 4.98%±2.48% | 11.36%±4.43% | 9.30%±2.30% | 13.49%±0.95% | 1.20%±0.15% | 31.3K |
| 6 | 6 3 - 10 |
GPT 5.5 (High)
OpenAI · Proprietary
|
7.13%±0.78% | 6.59%±1.51% | 8.69%±2.79% | 6.06%±1.53% | 12.97%±0.93% | 1.31%±0.13% | 49.6K |
| 7 | 7 2 - 10 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
6.93%±1.40% | 9.13%±2.66% | 15.45%±5.27% | 3.58%±2.59% | 5.19%±1.27% | 1.31%±0.13% | 21.9K |
| 8 | 8 3 - 10 |
GPT 5.4 (High)
OpenAI · Proprietary
|
6.65%±0.79% | 6.59%±1.53% | 6.13%±2.85% | 7.95%±1.53% | 11.27%±0.94% | 1.31%±0.13% | 49.5K |
| 9 | 9 3 - 10 |
Claude Opus 4.6
Anthropic · Proprietary
|
6.47%±1.21% | 3.47%±2.51% | 9.40%±4.19% | 6.39%±2.27% | 11.81%±1.38% | 1.31%±0.13% | 31.2K |
| 10 | 10 4 - 10 |
GPT 5.5
OpenAI · Proprietary
|
6.22%±0.77% | 4.07%±1.51% | 7.20%±2.72% | 7.41%±1.42% | 11.13%±1.04% | 1.31%±0.13% | 49.9K |
| 11 | 11 11 - 13 |
Claude Opus 4.8
Anthropic · Proprietary
|
3.74%±1.49% | 4.68%±2.65% | 10.76%±4.80% | 6.99%±2.57% | 9.66%±1.12% | 13.41%±3.22% | 28.3K |
| 12 | 12 11 - 13 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.18%±1.11% | 0.86%±2.55% | 2.42%±3.60% | 1.26%±2.15% | 11.62%±1.52% | 1.30%±0.13% | 31.7K |
| 13 | 13 11 - 13 |
GLM 5.1
智谱 ZAI · MIT
|
1.40%±0.89% | 2.27%±1.90% | 0.26%±3.02% | 0.62%±1.82% | 4.31%±1.07% | 1.31%±0.13% | 40.3K |
| 14 | 14 14 - 20 |
Kimi K2.7 Code
月之暗面 · Modified MIT
|
0.77%±1.24% | 0.82%±2.62% | 2.63%±4.26% | 1.65%±2.52% | 1.72%±2.19% | 1.31%±0.13% | 26.2K |
| 15 | 15 14 - 20 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
1.09%±0.70% | 0.16%±1.58% | 1.88%±2.23% | 1.37%±1.31% | 6.34%±1.27% | 1.26%±0.14% | 49.9K |
| 16 | 16 14 - 20 |
Gemini 3.5 Flash
Google · Proprietary
|
1.13%±0.74% | 0.44%±1.64% | 3.28%±2.37% | 2.19%±1.42% | 0.73%±1.19% | 0.47%±0.29% | 44.0K |
| 17 | 17 14 - 20 |
DeepSeek V4 Flash
DeepSeek · MIT
|
1.57%±1.08% | 4.27%±2.02% | 1.61%±3.83% | 9.19%±2.19% | 4.02%±1.54% | 0.50%±0.32% | 39.0K |
| 18 | 18 14 - 20 |
Kimi K2.6
月之暗面 · Modified MIT
|
1.82%±0.84% | 1.72%±1.85% | 2.80%±2.76% | 4.14%±1.67% | 1.75%±1.43% | 1.31%±0.13% | 46.3K |
| 19 | 19 14 - 21 |
Minimax M3
MiniMax · Proprietary
|
2.28%±1.01% | 2.14%±2.34% | 7.20%±3.50% | 5.11%±1.98% | 1.75%±1.00% | 1.31%±0.13% | 31.9K |
| 20 | 20 14 - 21 |
DeepSeek V4 Pro
DeepSeek · MIT
|
2.67%±1.29% | 5.01%±2.94% | 4.52%±4.34% | 6.27%±2.73% | 2.58%±1.26% | 0.12%±0.36% | 29.0K |
| 21 | 21 19 - 21 |
Qwen 3.6 Plus
阿里巴巴 · Proprietary
|
4.20%±0.99% | 1.26%±1.97% | 3.80%±3.47% | 10.58%±1.94% | 3.03%±1.25% | 2.36%±0.47% | 42.0K |
| 22 | 22 22 - 26 |
Grok 4.3 (High)
xAI · Proprietary
|
7.19%±0.84% | 9.41%±1.95% | 14.44%±2.35% | 6.79%±1.53% | 5.73%±1.88% | 0.44%±0.22% | 29.6K |
| 23 | 23 22 - 26 |
Grok Build 0.1
xAI · Proprietary
|
7.81%±0.82% | 6.82%±1.96% | 14.22%±2.46% | 11.32%±1.77% | 6.28%±1.48% | 0.41%±0.20% | 40.8K |
| 24 | 24 22 - 26 |
Gemini 3 Flash
Google · Proprietary
|
8.24%±0.81% | 9.81%±1.64% | 10.72%±2.12% | 5.35%±1.37% | 16.08%±2.34% | 0.74%±0.48% | 49.9K |
| 25 | 25 22 - 26 |
Minimax M2.7
MiniMax · Modified MIT
|
8.28%±0.77% | 12.20%±1.89% | 15.89%±2.24% | 9.85%±1.52% | 4.70%±1.42% | 1.22%±0.14% | 43.5K |
| 26 | 26 22 - 27 |
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
8.87%±3.19% | 5.53%±5.67% | 3.94%±10.80% | 17.20%±6.19% | 15.30%±6.34% | 2.37%±1.65% | 7.0K |
| 27 | 27 26 - 27 |
Gemma 4 31B
Google · Apache 2.0
|
12.52%±1.49% | 4.08%±1.77% | 5.57%±2.64% | 5.60%±1.64% | 28.72%±4.94% | 18.65%±4.18% | 39.4K |
| 28 | 28 28 - 28 |
Grok 4.3
xAI · Proprietary
|
16.76%±1.07% | 13.02%±1.71% | 16.79%±1.93% | 8.07%±1.33% | 46.76%±4.34% | 0.86%±0.19% | 49.3K |
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
智谱 ZAI
月之暗面
Google
DeepSeek
MiniMax
阿里巴巴
xAI
NVIDIA