| 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 - 3 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
16.48%±2.70% | 16.45%±4.87% | 39.23%±10.71% | 14.28%±5.22% | 12.09%±1.22% | 0.33%±0.03% | 5.0K |
| 🥈 | 2 1 - 5 |
Claude Opus 5.5 (High)
Anthropic · Proprietary
|
14.56%±3.27% | 12.90%±7.19% | 27.63%±12.41% | 19.32%±6.47% | 12.71%±1.40% | 0.25%±0.10% | 2.2K |
| 🥉 | 3 1 - 7 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
13.73%±3.45% | 17.13%±5.59% | 43.05%±13.34% | 1.92%±7.34% | 6.20%±1.48% | 0.33%±0.03% | 4.1K |
| 4 | 5 2 - 8 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
10.61%±1.90% | 8.72%±4.33% | 20.30%±6.78% | 12.23%±3.54% | 11.56%±0.92% | 0.27%±0.04% | 8.9K |
| 5 | 7 3 - 10 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
9.16%±1.70% | 4.82%±4.11% | 17.44%±5.70% | 13.99%±2.99% | 9.21%±1.34% | 0.33%±0.03% | 12.5K |
| 6 | 4 3 - 11 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
8.73%±1.95% | 9.27%±4.68% | 12.10%±6.71% | 9.78%±3.66% | 12.18%±0.97% | 0.31%±0.04% | 6.9K |
| 7 | 6 2 - 17 |
GPT 6 Sol (Max)
OpenAI · Proprietary
|
8.50%±3.27% | 9.17%±7.22% | 11.02%±11.69% | 14.74%±6.39% | 7.22%±2.37% | 0.33%±0.03% | 2.2K |
| 8 | 8 4 - 12 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
8.08%±1.74% | 4.28%±3.91% | 17.44%±6.08% | 12.48%±2.95% | 6.09%±2.25% | 0.13%±0.19% | 12.6K |
| 9 | 9 5 - 18 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
6.76%±1.78% | 2.28%±4.16% | 21.66%±6.10% | 7.35%±3.10% | 2.18%±1.41% | 0.33%±0.03% | 10.8K |
| 10 | 10 5 - 22 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
5.61%±2.22% | 6.52%±5.21% | 7.38%±7.57% | 8.28%±4.53% | 5.73%±1.34% | 0.13%±0.12% | 9.9K |
| 11 | 18 7 - 18 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.47%±0.92% | 7.64%±2.18% | 12.56%±3.13% | 6.14%±1.66% | 0.68%±0.84% | 0.33%±0.03% | 28.0K |
| 12 | 14 8 - 20 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
4.95%±0.73% | 9.49%±1.73% | 9.52%±2.39% | 1.16%±1.44% | 4.25%±0.58% | 0.33%±0.03% | 45.6K |
| 13 | 11 6 - 25 |
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
4.85%±2.31% | 6.35%±4.94% | 8.88%±7.79% | 3.16%±5.06% | 5.52%±1.42% | 0.33%±0.03% | 4.2K |
| 14 | 12 8 - 21 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
4.83%±1.33% | 0.60%±3.37% | 8.23%±4.26% | 8.25%±2.31% | 7.94%±1.39% | 0.33%±0.03% | 17.0K |
| 15 | 13 8 - 21 |
Hy4 preview
腾讯 · Apache 2.0
|
4.63%±1.22% | 8.22%±2.76% | 8.37%±4.19% | 1.16%±2.47% | 7.52%±0.69% | 0.20%±0.07% | 18.5K |
| 16 | 16 8 - 21 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
4.60%±0.81% | 7.79%±1.89% | 5.48%±2.65% | 3.55%±1.63% | 5.88%±0.73% | 0.32%±0.03% | 23.7K |
| 17 | 17 9 - 21 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
4.30%±0.77% | 9.63%±1.82% | 5.00%±2.49% | 1.92%±1.79% | 8.61%±0.41% | 0.18%±0.05% | 33.5K |
| 18 | 19 8 - 23 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
4.20%±1.13% | 6.43%±2.68% | 7.49%±3.72% | 1.68%±2.28% | 5.09%±0.88% | 0.31%±0.04% | 16.9K |
| 19 | 20 11 - 25 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.39%±0.85% | 7.39%±2.18% | 6.74%±2.80% | 3.48%±1.59% | 1.00%±0.70% | 0.33%±0.03% | 30.1K |
| 20 | 24 11 - 26 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
3.02%±1.31% | 1.41%±3.45% | 1.39%±4.05% | 6.54%±2.54% | 5.44%±1.29% | 0.33%±0.03% | 9.5K |
| 21 | 15 12 - 26 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
2.65%±1.17% | 6.33%±2.78% | 3.89%±3.74% | 3.72%±2.45% | 0.84%±0.71% | 0.13%±0.09% | 10.8K |
| 22 | 22 16 - 27 |
GPT 5.5
OpenAI · Proprietary
|
2.24%±1.17% | 2.30%±2.97% | 4.68%±3.63% | 4.43%±2.01% | 4.06%±1.46% | 0.33%±0.03% | 22.6K |
| 23 | 21 18 - 27 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
2.01%±0.89% | 4.68%±2.21% | 1.59%±2.85% | 1.54%±1.76% | 3.10%±0.85% | 0.87%±0.30% | 18.1K |
| 24 | 23 17 - 30 |
Grok 4.5
SpaceXAI · Proprietary
|
1.73%±1.36% | 1.00%±3.63% | 1.21%±4.25% | 5.10%±2.66% | 5.43%±1.18% | 0.33%±0.03% | 14.1K |
| 25 | 25 18 - 31 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
1.42%±1.48% | 4.40%±4.05% | 3.19%±4.59% | 6.55%±2.64% | 1.44%±1.34% | 0.33%±0.03% | 7.4K |
| 26 | 29 20 - 30 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
1.13%±0.94% | 7.79%±2.27% | 0.25%±3.11% | 1.25%±2.01% | 0.12%±0.56% | 1.00%±0.13% | 28.4K |
| 27 | 26 22 - 31 |
GPT 5.4 (High)
OpenAI · Proprietary
|
0.01%±1.16% | 3.31%±3.19% | 0.71%±3.47% | 2.78%±2.18% | 0.96%±1.64% | 0.33%±0.03% | 21.9K |
| 28 | 27 24 - 31 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
0.02%±0.65% | 6.50%±1.74% | 1.47%±1.92% | 0.07%±1.28% | 5.40%±0.66% | 0.33%±0.03% | 29.4K |
| 29 | 32 24 - 31 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
0.32%±0.82% | 4.48%±2.13% | 0.88%±2.55% | 0.27%±1.64% | 4.84%±0.74% | 0.11%±0.10% | 20.9K |
| 30 | 28 24 - 31 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
0.40%±0.94% | 3.88%±2.54% | 2.97%±2.81% | 2.52%±1.81% | 2.02%±1.01% | 0.33%±0.03% | 14.7K |
| 31 | 30 26 - 33 |
DeepSeek V4 Pro
DeepSeek · MIT
|
1.33%±1.33% | 3.58%±3.55% | 2.33%±4.27% | 2.33%±2.22% | 2.02%±1.23% | 0.42%±0.19% | 11.8K |
| 32 | 31 31 - 35 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
3.28%±0.87% | 3.23%±2.57% | 6.32%±2.40% | 1.85%±1.65% | 4.88%±0.90% | 0.12%±0.32% | 19.0K |
| 33 | 33 31 - 35 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
3.51%±0.92% | 7.63%±2.71% | 10.17%±2.49% | 7.55%±1.83% | 7.51%±1.10% | 0.30%±0.06% | 18.5K |
| 34 | 35 32 - 38 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
5.07%±1.13% | 8.59%±3.44% | 10.98%±2.82% | 3.81%±1.93% | 1.82%±2.06% | 0.14%±0.21% | 13.6K |
| 35 | 34 34 - 37 |
Muse Spark 1.1
Meta · Proprietary
|
5.42%±0.60% | 6.26%±1.74% | 11.40%±1.50% | 6.94%±1.17% | 2.79%±1.00% | 0.31%±0.03% | 50.1K |
| 36 | 36 32 - 39 |
Hy3
腾讯 · Apache 2.0
|
5.60%±1.73% | 5.91%±4.37% | 6.60%±4.73% | 3.30%±3.45% | 9.11%±3.87% | 3.12%±1.12% | 9.6K |
| 37 | 38 34 - 40 |
Minimax M3
MiniMax · MiniMax Community License
|
7.07%±1.19% | 13.81%±3.68% | 12.83%±3.03% | 9.15%±2.25% | 0.68%±1.21% | 0.21%±0.27% | 13.6K |
| 38 | 37 35 - 41 |
Mimo V2.5 Pro
小米 · MIT
|
7.27%±1.12% | 11.27%±3.42% | 11.88%±2.80% | 6.05%±2.07% | 6.18%±1.88% | 0.98%±0.32% | 14.8K |
| 39 | 41 36 - 44 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
8.11%±1.78% | 11.47%±5.14% | 13.44%±4.10% | 8.27%±3.02% | 6.68%±3.76% | 0.69%±0.33% | 7.3K |
| 40 | 40 39 - 44 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
9.65%±1.23% | 12.53%±3.41% | 4.72%±2.92% | 6.57%±1.92% | 23.40%±2.53% | 1.04%±1.53% | 23.2K |
| 41 | 39 38 - 44 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
9.67%±1.38% | 13.20%±4.05% | 10.52%±3.40% | 6.50%±2.50% | 18.42%±2.43% | 0.29%±0.05% | 7.8K |
| 42 | 42 37 - 44 |
Inkling Small
Thinky · Apache 2.0
|
9.94%±1.88% | 22.15%±6.87% | 22.22%±4.09% | 14.02%±4.07% | 9.25%±1.68% | 0.56%±0.47% | 4.0K |
| 43 | 43 39 - 44 |
Inkling
Thinky · Apache 2.0
|
10.58%±1.37% | 21.94%±4.71% | 21.36%±2.88% | 15.97%±2.92% | 6.30%±1.40% | 0.08%±0.12% | 13.2K |
| 44 | 44 39 - 44 |
Mistral Medium 3.5
Mistral · Modified MIT
|
11.91%±2.06% | 13.70%±6.14% | 16.57%±5.07% | 12.32%±4.36% | 14.61%±3.30% | 2.37%±0.99% | 3.5K |
| 45 | 45 45 - 45 |
Solar Pro 4
Upstage · Proprietary
|
16.59%±2.48% | 19.74%±8.07% | 22.42%±4.77% | 12.08%±4.75% | 26.64%±5.62% | 2.08%±0.96% | 3.3K |
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
SpaceXAI
腾讯
Meta
DeepSeek
Google
阿里巴巴
MiniMax
小米
Mistral