| 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 - 5 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
12.73%±1.63% | 15.97%±3.34% | 19.13%±5.89% | 13.36%±3.16% | 14.22%±0.84% | 0.99%±0.17% | 20.1K |
| 🥈 | 2 1 - 5 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
12.41%±1.91% | 17.21%±3.64% | 19.00%±6.92% | 9.93%±3.94% | 14.88%±0.91% | 1.05%±0.17% | 15.8K |
| 🥉 | 3 1 - 7 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
11.62%±1.63% | 11.16%±3.25% | 19.15%±5.78% | 13.87%±3.13% | 12.82%±2.67% | 1.07%±0.17% | 33.0K |
| 4 | 4 1 - 8 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
10.31%±1.45% | 10.02%±2.99% | 22.22%±5.29% | 9.16%±2.93% | 9.06%±1.14% | 1.08%±0.17% | 27.0K |
| 5 | 5 1 - 9 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
9.99%±1.53% | 7.49%±2.83% | 22.41%±5.17% | 11.10%±2.87% | 9.15%±2.43% | 0.21%±1.33% | 35.6K |
| 6 | 6 3 - 8 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
9.53%±0.61% | 18.24%±1.20% | 17.56%±2.15% | 2.31%±1.24% | 8.47%±0.52% | 1.08%±0.17% | 89.8K |
| 7 | 7 4 - 13 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
8.56%±0.97% | 4.00%±2.06% | 13.71%±3.37% | 9.30%±1.87% | 14.70%±1.18% | 1.07%±0.17% | 48.5K |
| 8 | 8 3 - 17 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
8.05%±2.27% | 1.31%±4.71% | 14.45%±7.69% | 12.52%±4.86% | 11.00%±1.79% | 0.95%±0.18% | 26.1K |
| 9 | 9 6 - 17 |
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
7.27%±1.26% | 4.56%±2.65% | 10.81%±4.20% | 7.59%±2.44% | 12.44%±1.92% | 0.98%±0.18% | 36.6K |
| 10 | 10 7 - 17 |
Claude Opus 4.7
Anthropic · Proprietary
|
7.18%±1.28% | 4.96%±2.70% | 11.33%±4.22% | 8.75%±2.44% | 9.84%±2.08% | 1.03%±0.17% | 37.1K |
| 11 | 11 7 - 17 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
6.97%±1.11% | 13.49%±2.26% | 6.38%±3.79% | 3.16%±2.46% | 10.74%±0.76% | 1.08%±0.17% | 18.8K |
| 12 | 12 7 - 17 |
GPT 5.5 (High)
OpenAI · Proprietary
|
6.76%±0.89% | 2.60%±1.88% | 11.11%±3.08% | 6.65%±1.68% | 12.36%±1.27% | 1.08%±0.17% | 73.8K |
| 13 | 13 7 - 19 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
6.46%±1.23% | 12.52%±2.65% | 6.81%±4.36% | 4.66%±2.51% | 8.22%±1.03% | 0.08%±0.30% | 14.7K |
| 14 | 14 8 - 19 |
Grok 4.5
SpaceXAI · Proprietary
|
6.38%±1.18% | 4.72%±2.60% | 6.65%±4.18% | 8.49%±2.22% | 10.98%±1.30% | 1.08%±0.17% | 32.1K |
| 15 | 15 8 - 20 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.86%±0.83% | 7.25%±1.80% | 8.97%±2.83% | 6.12%±1.56% | 5.89%±1.01% | 1.08%±0.17% | 58.7K |
| 16 | 16 8 - 21 |
Claude Opus 4.6
Anthropic · Proprietary
|
5.78%±1.22% | 3.67%±2.66% | 7.81%±4.00% | 5.96%±2.35% | 10.36%±1.81% | 1.08%±0.17% | 36.4K |
| 17 | 17 8 - 20 |
GPT 5.5
OpenAI · Proprietary
|
5.68%±0.82% | 3.23%±1.75% | 7.69%±2.81% | 4.68%±1.55% | 11.73%±0.93% | 1.08%±0.17% | 75.7K |
| 18 | 18 13 - 24 |
GPT 5.4 (High)
OpenAI · Proprietary
|
4.58%±0.83% | 4.55%±1.82% | 3.25%±2.78% | 4.96%±1.67% | 9.07%±1.01% | 1.08%±0.17% | 74.9K |
| 19 | 19 13 - 28 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
3.83%±1.54% | 1.06%±3.48% | 5.94%±5.10% | 3.86%±3.29% | 9.33%±1.43% | 1.08%±0.17% | 11.9K |
| 20 | 20 17 - 27 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.77%±1.08% | 12.78%±2.20% | 4.83%±3.64% | 1.24%±2.46% | 1.42%±1.07% | 1.08%±0.17% | 22.6K |
| 21 | 21 18 - 27 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
3.46%±0.78% | 7.90%±1.84% | 2.02%±2.55% | 1.80%±1.58% | 4.53%±0.64% | 1.08%±0.17% | 45.9K |
| 22 | 22 18 - 28 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
3.30%±1.17% | 3.25%±2.97% | 0.74%±3.76% | 9.77%±2.44% | 9.63%±1.27% | 1.08%±0.17% | 15.3K |
| 23 | 23 15 - 32 |
Claude Opus 4.8
Anthropic · Proprietary
|
2.72%±2.36% | 7.47%±2.87% | 11.79%±4.78% | 10.52%±2.76% | 11.10%±1.80% | 27.28%±9.45% | 33.7K |
| 24 | 24 19 - 28 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.21%±1.25% | 1.09%±2.79% | 0.94%±3.69% | 0.34%±2.46% | 10.55%±2.35% | 0.98%±0.21% | 37.0K |
| 25 | 25 18 - 32 |
Kimi K2.7 Code
月之暗面 · Modified MIT
|
2.03%±2.18% | 3.56%±4.66% | 1.26%±7.24% | 6.07%±5.09% | 1.82%±2.63% | 1.08%±0.17% | 11.1K |
| 26 | 26 19 - 34 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
1.67%±1.96% | 8.47%±4.38% | 1.01%±6.39% | 0.47%±4.71% | 0.76%±1.65% | 0.12%±0.43% | 6.7K |
| 27 | 27 19 - 31 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.60%±1.10% | 7.06%±2.70% | 6.19%±3.35% | 4.34%±2.36% | 10.42%±1.29% | 1.07%±0.17% | 18.4K |
| 28 | 28 21 - 30 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
1.57%±0.88% | 9.97%±2.07% | 2.04%±2.78% | 3.59%±1.91% | 2.47%±0.98% | 1.01%±0.17% | 24.1K |
| 29 | 29 19 - 34 |
Kimi K2.6
月之暗面 · Modified MIT
|
1.09%±2.37% | 1.84%±4.90% | 4.21%±7.60% | 9.28%±5.26% | 7.30%±4.82% | 1.08%±0.17% | 11.3K |
| 30 | 30 25 - 33 |
Muse Spark 1.1
Meta · Proprietary
|
0.10%±0.61% | 6.18%±1.45% | 7.15%±1.77% | 6.24%±1.31% | 5.67%±1.05% | 1.05%±0.17% | 80.5K |
| 31 | 31 24 - 34 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.18%±0.91% | 2.58%±2.31% | 2.23%±2.90% | 1.06%±1.79% | 4.71%±0.95% | 0.26%±0.25% | 30.5K |
| 32 | 32 24 - 36 |
Hy3
腾讯 · Apache 2.0
|
0.42%±1.30% | 1.68%±2.82% | 0.79%±4.24% | 0.78%±2.64% | 1.02%±2.13% | 1.44%±0.61% | 21.3K |
| 33 | 33 26 - 34 |
GLM 5.1
智谱 ZAI · MIT
|
0.42%±0.81% | 0.88%±1.79% | 0.11%±2.40% | 0.21%±1.58% | 2.27%±1.64% | 0.84%±0.48% | 71.9K |
| 34 | 34 28 - 37 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
1.08%±0.89% | 2.67%±2.24% | 5.47%±2.69% | 2.43%±1.62% | 4.60%±1.62% | 0.56%±0.24% | 33.3K |
| 35 | 35 29 - 41 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
2.07%±1.33% | 3.33%±3.38% | 9.66%±3.89% | 2.48%±2.86% | 5.01%±2.11% | 0.13%±0.35% | 17.4K |
| 36 | 36 32 - 40 |
Gemini 3.5 Flash (High)
Google · Proprietary
|
2.22%±0.68% | 0.29%±1.55% | 0.91%±2.01% | 6.67%±1.32% | 3.36%±1.30% | 0.12%±0.20% | 94.4K |
| 37 | 37 32 - 40 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
2.41%±0.74% | 0.24%±1.63% | 2.85%±2.18% | 2.84%±1.35% | 13.14%±1.49% | 0.83%±0.27% | 81.9K |
| 38 | 38 33 - 42 |
Mimo V2.5 Pro
小米 · MIT
|
2.79%±0.91% | 3.50%±2.25% | 8.15%±2.71% | 2.67%±1.74% | 0.41%±1.49% | 0.02%±0.32% | 34.1K |
| 39 | 39 34 - 42 |
Minimax M3
MiniMax · MiniMax Community License
|
3.10%±0.87% | 6.61%±2.29% | 9.60%±2.60% | 5.61%±1.75% | 5.69%±0.84% | 0.63%±0.27% | 33.6K |
| 40 | 40 34 - 42 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
3.22%±1.22% | 3.04%±3.03% | 5.03%±3.76% | 4.34%±2.45% | 4.73%±1.66% | 1.04%±0.17% | 15.0K |
| 41 | 41 34 - 42 |
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
3.48%±1.40% | 8.78%±3.46% | 6.12%±4.01% | 1.22%±2.83% | 1.84%±2.39% | 0.53%±0.51% | 13.7K |
| 42 | 42 36 - 44 |
Mistral Medium 3.5
Mistral · Modified MIT
|
5.22%±1.85% | 11.91%±4.41% | 12.18%±5.09% | 2.73%±4.19% | 2.11%±2.92% | 2.64%±1.80% | 6.4K |
| 43 | 43 37 - 44 |
Inkling Small
Thinky · Apache 2.0
|
5.42%±1.85% | 17.40%±5.09% | 16.12%±5.27% | 5.25%±4.74% | 11.49%±1.64% | 0.19%±0.56% | 8.8K |
| 44 | 44 41 - 44 |
Inkling
Thinky · Apache 2.0
|
6.74%±0.99% | 12.48%±2.84% | 18.46%±2.78% | 10.59%±2.27% | 7.23%±1.07% | 0.59%±0.21% | 37.8K |
| 45 | 45 41 - 50 |
Solar Pro 4
Upstage · Proprietary
|
8.79%±2.64% | 6.24%±6.11% | 15.29%±7.42% | 8.52%±6.22% | 12.92%±4.38% | 0.95%±2.33% | 5.4K |
| 46 | 46 44 - 50 |
Grok Build 0.1
SpaceXAI · Proprietary
|
9.44%±1.00% | 5.97%±1.92% | 11.07%±2.33% | 5.36%±1.97% | 25.47%±3.14% | 0.68%±0.17% | 74.4K |
| 47 | 47 44 - 50 |
Grok 4.3 (High)
SpaceXAI · Proprietary
|
9.86%±0.92% | 11.21%±1.89% | 13.33%±2.02% | 10.58%±1.49% | 15.04%±3.13% | 0.87%±0.17% | 62.8K |
| 48 | 48 44 - 50 |
Minimax M2.7
MiniMax · Modified MIT
|
10.16%±1.17% | 12.91%±2.67% | 15.66%±3.05% | 4.86%±2.36% | 18.27%±3.01% | 0.92%±0.19% | 33.7K |
| 49 | 49 44 - 50 |
Gemini 3 Flash
Google · Proprietary
|
10.32%±0.88% | 7.84%±1.64% | 10.40%±1.88% | 9.13%±1.39% | 23.43%±2.57% | 0.79%±1.82% | 83.4K |
| 50 | 50 44 - 50 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
10.87%±1.33% | 12.72%±3.14% | 14.51%±3.17% | 10.13%±2.81% | 16.31%±3.13% | 0.69%±1.04% | 20.9K |
| 51 | 51 44 - 50 |
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
12.67%±2.43% | 15.58%±5.09% | 14.23%±6.30% | 7.56%±5.06% | 26.33%±6.80% | 0.35%±0.35% | 12.3K |
| 52 | 52 51 - 52 |
Grok 4.3
SpaceXAI · Proprietary
|
17.61%±1.36% | 11.76%±1.72% | 15.42%±1.86% | 10.01%±1.39% | 51.81%±6.03% | 0.96%±0.17% | 82.7K |
| 53 | 53 51 - 52 |
Gemma 4 31B
Google · Apache 2.0
|
20.61%±2.82% | 1.49%±1.89% | 3.63%±2.61% | 9.28%±1.97% | 58.11%±11.56% | 30.54%±7.13% | 56.7K |
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
月之暗面
DeepSeek
阿里巴巴
SpaceXAI
智谱 ZAI
Meta
Google
腾讯
小米
MiniMax
Mistral
NVIDIA