| 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
|
17.22%±2.83% | 21.10%±4.46% | 50.15%±11.03% | 4.39%±5.84% | 10.09%±1.97% | 0.38%±0.04% | 3.8K |
| 🥈 | 2 1 - 6 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
14.13%±3.13% | 22.57%±4.94% | 46.29%±11.77% | 3.59%±7.25% | 5.03%±1.71% | 0.38%±0.04% | 3.0K |
| 🥉 | 3 1 - 7 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
12.94%±2.34% | 16.86%±5.15% | 20.13%±8.45% | 15.53%±4.23% | 11.87%±0.97% | 0.30%±0.05% | 7.5K |
| 4 | 4 2 - 10 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.91%±2.74% | 12.27%±6.15% | 18.94%±9.53% | 9.77%±5.16% | 13.20%±0.99% | 0.35%±0.05% | 5.8K |
| 5 | 5 2 - 10 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
9.91%±1.96% | 6.95%±5.06% | 17.50%±6.77% | 14.37%±3.42% | 10.37%±1.42% | 0.38%±0.04% | 11.1K |
| 6 | 6 2 - 12 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
8.97%±2.05% | 5.03%±4.95% | 24.03%±7.22% | 11.21%±3.64% | 4.18%±1.29% | 0.38%±0.04% | 9.4K |
| 7 | 7 3 - 12 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
8.81%±2.02% | 2.98%±4.82% | 19.70%±6.90% | 14.05%±3.51% | 7.26%±1.89% | 0.06%±0.40% | 12.0K |
| 8 | 8 4 - 13 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
7.32%±0.95% | 14.17%±2.26% | 14.80%±3.16% | 2.74%±1.76% | 4.52%±0.69% | 0.38%±0.04% | 33.5K |
| 9 | 9 4 - 18 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
7.01%±2.72% | 7.77%±6.15% | 11.82%±9.30% | 7.35%±5.84% | 7.91%±1.33% | 0.19%±0.13% | 9.1K |
| 10 | 10 4 - 16 |
Hy4 preview
腾讯 · Apache 2.0
|
6.51%±1.88% | 13.05%±4.13% | 11.48%±6.83% | 1.26%±3.73% | 8.97%±0.94% | 0.29%±0.09% | 5.6K |
| 11 | 13 6 - 16 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
6.14%±1.27% | 13.38%±2.97% | 9.77%±4.36% | 1.66%±2.52% | 5.49%±1.01% | 0.38%±0.04% | 12.8K |
| 12 | 12 6 - 16 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
6.08%±1.00% | 11.11%±2.42% | 13.68%±3.37% | 4.79%±1.72% | 0.43%±1.11% | 0.38%±0.04% | 23.3K |
| 13 | 11 8 - 22 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
5.05%±1.50% | 1.00%±4.04% | 8.56%±4.74% | 8.30%±2.61% | 9.04%±1.59% | 0.38%±0.04% | 16.1K |
| 14 | 17 9 - 25 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
4.42%±1.58% | 4.97%±4.18% | 4.59%±4.88% | 6.32%±2.93% | 5.85%±1.40% | 0.38%±0.04% | 7.1K |
| 15 | 15 9 - 25 |
Grok 4.5
SpaceXAI · Proprietary
|
4.21%±1.59% | 7.10%±4.01% | 1.62%±5.15% | 6.31%±3.04% | 5.62%±1.55% | 0.38%±0.04% | 11.9K |
| 16 | 16 9 - 26 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.75%±1.37% | 10.10%±3.52% | 1.32%±4.35% | 3.85%±2.71% | 4.07%±1.25% | 0.58%±0.27% | 7.6K |
| 17 | 20 12 - 26 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
3.36%±1.02% | 9.89%±2.59% | 4.88%±3.26% | 0.24%±1.93% | 1.42%±0.85% | 0.35%±0.05% | 19.6K |
| 18 | 19 13 - 26 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.20%±0.92% | 10.99%±2.30% | 6.82%±2.89% | 0.96%±1.63% | 3.16%±0.88% | 0.38%±0.04% | 22.1K |
| 19 | 23 12 - 26 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
2.96%±1.66% | 1.74%±4.68% | 2.43%±5.12% | 10.27%±3.01% | 3.47%±1.61% | 0.38%±0.04% | 6.1K |
| 20 | 18 13 - 26 |
GPT 5.5
OpenAI · Proprietary
|
2.94%±1.25% | 1.08%±3.43% | 3.80%±3.83% | 6.73%±2.13% | 4.85%±1.47% | 0.38%±0.04% | 21.6K |
| 21 | 25 13 - 27 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
2.38%±1.52% | 11.77%±3.69% | 1.04%±5.09% | 0.57%±3.11% | 1.50%±0.77% | 0.92%±0.19% | 9.3K |
| 22 | 21 14 - 27 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
1.84%±1.19% | 11.64%±3.10% | 0.83%±3.60% | 1.24%±2.30% | 4.90%±1.13% | 0.38%±0.04% | 8.7K |
| 23 | 22 14 - 27 |
GPT 5.4 (High)
OpenAI · Proprietary
|
1.71%±1.28% | 1.13%±3.58% | 1.10%±3.93% | 4.18%±2.32% | 4.02%±1.18% | 0.38%±0.04% | 20.9K |
| 24 | 24 14 - 27 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
1.61%±1.49% | 0.74%±4.01% | 0.84%±4.55% | 2.57%±2.81% | 3.50%±1.44% | 0.38%±0.04% | 7.1K |
| 25 | 14 13 - 30 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
1.32%±2.81% | 2.05%±9.07% | 3.41%±7.39% | 0.22%±5.20% | 1.07%±1.69% | 0.29%±0.14% | 2.0K |
| 26 | 26 16 - 27 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
1.28%±1.23% | 8.39%±3.23% | 2.92%±3.91% | 0.88%±2.34% | 3.95%±1.07% | 0.07%±0.13% | 9.7K |
| 27 | 27 21 - 30 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.51%±1.53% | 0.03%±4.31% | 3.84%±4.88% | 1.27%±2.64% | 3.18%±1.22% | 0.61%±0.27% | 10.6K |
| 28 | 29 26 - 33 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
2.31%±1.61% | 1.50%±4.73% | 8.32%±4.78% | 9.56%±3.25% | 7.43%±1.93% | 0.38%±0.04% | 8.2K |
| 29 | 28 26 - 35 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.79%±1.75% | 9.56%±5.26% | 6.33%±4.73% | 4.44%±3.23% | 6.16%±2.24% | 0.24%±0.22% | 8.9K |
| 30 | 32 26 - 35 |
Hy3
腾讯 · Apache 2.0
|
2.99%±1.98% | 0.60%±4.78% | 2.97%±5.87% | 2.99%±3.84% | 6.46%±4.20% | 3.13%±1.15% | 8.4K |
| 31 | 31 28 - 35 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.73%±1.31% | 2.38%±3.69% | 10.62%±3.14% | 4.46%±2.18% | 1.08%±2.90% | 0.13%±0.25% | 12.4K |
| 32 | 30 28 - 37 |
Muse Spark 1.1
Meta · Proprietary
|
4.83%±0.91% | 3.15%±2.62% | 10.44%±2.29% | 8.00%±1.66% | 2.90%±1.65% | 0.37%±0.04% | 31.7K |
| 33 | 33 28 - 38 |
Mimo V2.5 Pro
小米 · MIT
|
5.09%±1.28% | 6.50%±3.87% | 9.91%±3.28% | 3.53%±2.34% | 4.75%±2.34% | 0.77%±0.37% | 12.4K |
| 34 | 35 29 - 38 |
Minimax M3
MiniMax · MiniMax Community License
|
5.30%±1.36% | 10.02%±4.14% | 9.68%±3.63% | 8.76%±2.53% | 1.97%±1.17% | 0.02%±0.17% | 12.3K |
| 35 | 34 29 - 41 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
5.98%±1.80% | 10.06%±5.42% | 12.45%±4.31% | 3.71%±3.39% | 3.03%±3.26% | 0.65%±0.40% | 6.9K |
| 36 | 37 32 - 41 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
7.07%±1.39% | 9.21%±3.98% | 1.77%±3.76% | 5.46%±2.26% | 18.74%±2.29% | 0.19%±0.70% | 22.7K |
| 37 | 38 33 - 41 |
Inkling Small
Thinky · Apache 2.0
|
8.18%±2.22% | 20.45%±7.87% | 21.63%±4.87% | 9.65%±5.18% | 11.62%±1.58% | 0.79%±0.70% | 3.6K |
| 38 | 36 35 - 41 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
8.57%±1.53% | 10.78%±4.72% | 11.76%±3.70% | 7.64%±2.87% | 12.97%±2.48% | 0.31%±0.09% | 6.3K |
| 39 | 39 35 - 41 |
Inkling
Thinky · Apache 2.0
|
8.80%±1.56% | 18.85%±5.34% | 20.03%±3.41% | 13.13%±3.33% | 7.87%±1.41% | 0.13%±0.15% | 12.8K |
| 40 | 40 35 - 41 |
Mistral Medium 3.5
Mistral · Modified MIT
|
9.95%±2.23% | 17.52%±6.57% | 12.80%±5.85% | 10.38%±4.70% | 7.15%±2.86% | 1.92%±0.99% | 2.9K |
| 41 | 41 32 - 43 |
Solar Pro 4
Upstage · Proprietary
|
10.33%±5.22% | 10.54%±12.86% | 10.28%±13.72% | 1.16%±9.73% | 28.27%±12.29% | 1.39%±2.23% | 2.0K |
| 42 | 42 41 - 43 |
Minimax M2.7
MiniMax · Modified MIT
|
14.09%±1.83% | 17.33%±5.49% | 18.05%±4.15% | 13.07%±3.70% | 22.30%±3.79% | 0.28%±0.13% | 11.9K |
| 43 | 43 41 - 43 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
16.61%±1.90% | 18.06%±6.11% | 20.41%±3.62% | 16.89%±3.66% | 25.81%±4.08% | 1.89%±1.19% | 7.3K |
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
月之暗面
腾讯
DeepSeek
智谱 ZAI
SpaceXAI
阿里巴巴
Google
Meta
小米
MiniMax
Mistral