| 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 - 7 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
12.58%±2.19% | 10.26%±4.23% | 24.42%±7.82% | 12.93%±4.49% | 13.95%±1.22% | 1.32%±0.19% | 23.8K |
| 🥈 | 2 1 - 9 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
11.88%±2.81% | 17.56%±4.69% | 25.63%±9.98% | 1.81%±7.26% | 13.14%±1.15% | 1.27%±0.19% | 7.3K |
| 🥉 | 3 1 - 7 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
11.73%±1.66% | 16.60%±3.11% | 24.40%±6.28% | 5.49%±3.76% | 10.85%±1.14% | 1.30%±0.19% | 11.1K |
| 4 | 4 1 - 11 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
10.02%±1.63% | 8.61%±3.32% | 21.90%±6.10% | 8.96%±3.09% | 9.34%±1.18% | 1.32%±0.19% | 17.0K |
| 6 | 6 1 - 12 |
Claude Opus 4.8 (Thinking)
Anthropic · Proprietary
|
9.43%±1.64% | 8.75%±2.75% | 21.05%±5.25% | 9.77%±2.74% | 9.05%±2.26% | 1.44%±3.34% | 34.5K |
| 7 | 7 1 - 14 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
8.57%±2.00% | 7.95%±3.98% | 16.12%±7.51% | 6.74%±4.10% | 10.86%±0.97% | 1.18%±0.20% | 24.7K |
| 8 | 8 3 - 13 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
8.49%±0.95% | 5.82%±1.94% | 12.91%±3.38% | 8.24%±1.73% | 14.14%±1.19% | 1.32%±0.19% | 43.1K |
| 9 | 9 3 - 13 |
Claude Opus 4.7 (Thinking)
Anthropic · Proprietary
|
8.19%±1.26% | 6.19%±2.65% | 11.20%±4.39% | 9.65%±2.47% | 12.70%±1.12% | 1.20%±0.21% | 35.5K |
| 10 | 10 4 - 13 |
GPT 5.5 (High)
OpenAI · Proprietary
|
7.89%±0.88% | 5.63%±1.76% | 11.31%±3.13% | 9.18%±1.53% | 12.03%±1.04% | 1.32%±0.19% | 68.3K |
| 11 | 11 5 - 15 |
Claude Opus 4.7
Anthropic · Proprietary
|
7.37%±1.31% | 4.71%±2.72% | 12.28%±4.45% | 8.87%±2.47% | 9.74%±1.94% | 1.26%±0.19% | 36.0K |
| 13 | 13 7 - 18 |
Claude Opus 4.6
Anthropic · Proprietary
|
6.47%±1.31% | 3.42%±2.73% | 10.12%±4.32% | 7.24%±2.40% | 10.26%±2.04% | 1.32%±0.19% | 35.2K |
| 14 | 14 10 - 20 |
Grok 4.5
SpaceXAI · Proprietary
|
5.54%±1.34% | 4.65%±2.94% | 5.69%±4.70% | 5.14%±2.54% | 10.91%±1.24% | 1.32%±0.19% | 24.1K |
| 15 | 15 11 - 19 |
GPT 5.5
OpenAI · Proprietary
|
5.53%±0.82% | 3.67%±1.73% | 5.85%±2.84% | 5.85%±1.47% | 10.96%±1.04% | 1.32%±0.19% | 69.4K |
| 16 | 16 13 - 20 |
GPT 5.4 (High)
OpenAI · Proprietary
|
5.11%±0.84% | 4.87%±1.79% | 3.48%±2.92% | 6.53%±1.60% | 9.36%±0.95% | 1.32%±0.19% | 68.6K |
| 17 | 17 14 - 21 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
3.53%±1.47% | 0.31%±3.46% | 4.52%±4.97% | 3.29%±2.87% | 8.84%±1.49% | 1.32%±0.19% | 9.4K |
| 18 | 18 13 - 21 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
3.47%±1.72% | 0.31%±3.92% | 4.78%±6.01% | 0.62%±3.44% | 10.94%±1.26% | 1.32%±0.19% | 7.8K |
| 19 | 19 13 - 22 |
Claude Opus 4.8
Anthropic · Proprietary
|
3.34%±1.94% | 8.24%±2.82% | 12.75%±5.00% | 8.39%±2.76% | 9.22%±2.14% | 21.90%±6.41% | 32.6K |
| 20 | 20 15 - 21 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
3.18%±1.20% | 0.07%±2.76% | 0.88%±3.88% | 2.39%±2.33% | 11.46%±1.50% | 1.23%±0.22% | 36.0K |
| 21 | 21 20 - 29 |
Muse Spark 1.1
Meta · Proprietary
|
0.75%±0.72% | 5.65%±1.67% | 4.60%±2.20% | 4.78%±1.38% | 6.17%±1.22% | 1.30%±0.19% | 43.2K |
| 24 | 24 21 - 31 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
0.52%±0.70% | 2.69%±1.54% | 1.29%±2.21% | 2.37%±1.24% | 10.20%±1.34% | 1.26%±0.19% | 72.6K |
| 25 | 25 21 - 31 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
0.53%±0.97% | 1.95%±2.38% | 5.89%±3.03% | 0.20%±1.76% | 4.61%±1.66% | 0.80%±0.27% | 20.9K |
| 28 | 28 22 - 33 |
Gemini 3.5 Flash (High)
Google · Proprietary
|
1.03%±0.84% | 3.60%±1.85% | 3.56%±2.48% | 0.97%±1.50% | 2.35%±1.85% | 1.87%±0.44% | 46.0K |
| 30 | 30 21 - 35 |
gemini-3.6-flash
Google · Proprietary
|
1.59%±2.68% | 0.15%±6.40% | 6.20%±8.38% | 2.59%±6.28% | 0.61%±3.18% | 1.32%±0.19% | 2.5K |
| 31 | 31 23 - 34 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
1.65%±1.29% | 1.72%±3.36% | 7.98%±3.99% | 4.63%±2.74% | 5.85%±1.63% | 0.21%±0.46% | 14.1K |
| 35 | 35 33 - 36 |
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
5.34%±1.61% | 11.37%±4.02% | 7.47%±4.76% | 6.53%±3.13% | 2.21%±2.86% | 0.90%±0.40% | 10.0K |
| 37 | 37 37 - 40 |
Grok Build 0.1
SpaceXAI · Proprietary
|
7.99%±0.85% | 4.44%±1.81% | 10.55%±2.40% | 11.12%±1.58% | 14.73%±2.15% | 0.88%±0.19% | 64.2K |
| 38 | 38 37 - 40 |
Grok 4.3 (High)
SpaceXAI · Proprietary
|
8.03%±0.81% | 8.93%±1.76% | 14.24%±1.97% | 6.98%±1.29% | 11.11%±2.55% | 1.09%±0.19% | 53.0K |
| 39 | 39 37 - 40 |
Gemini 3 Flash
Google · Proprietary
|
8.77%±0.76% | 8.27%±1.62% | 11.76%±1.88% | 5.36%±1.23% | 18.69%±2.16% | 0.23%±0.88% | 73.5K |
| 40 | 40 37 - 42 |
gemini-3.5-flash-lite
Google · Proprietary
|
10.20%±2.61% | 17.21%±6.83% | 17.63%±6.72% | 5.82%±5.80% | 10.80%±5.04% | 0.45%±0.75% | 2.5K |
| 43 | 43 42 - 44 |
Grok 4.3
SpaceXAI · Proprietary
|
14.45%±1.05% | 11.31%±1.66% | 16.43%±1.83% | 7.58%±1.24% | 38.09%±4.33% | 1.19%±0.19% | 72.9K |
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
SpaceXAI
Meta
Google
阿里巴巴