| 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 - 2 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
14.54%±2.11% | 19.34%±3.22% | 37.04%±8.59% | 3.67%±4.44% | 12.31%±0.87% | 0.37%±0.05% | 7.9K |
| 🥈 | 2 1 - 8 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
10.93%±2.68% | 16.07%±4.21% | 31.02%±10.37% | 0.29%±5.90% | 6.85%±1.24% | 0.38%±0.04% | 6.2K |
| 🥉 | 4 2 - 8 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.05%±1.83% | 10.43%±3.64% | 18.96%±6.80% | 7.71%±3.38% | 12.77%±0.81% | 0.35%±0.05% | 11.4K |
| 4 | 3 2 - 8 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
10.00%±1.67% | 8.85%±3.50% | 19.83%±6.09% | 9.48%±3.26% | 11.54%±0.87% | 0.32%±0.05% | 14.7K |
| 5 | 5 2 - 8 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
9.28%±1.46% | 6.29%±3.14% | 18.31%±5.20% | 12.43%±2.66% | 9.01%±1.38% | 0.38%±0.04% | 21.8K |
| 6 | 6 2 - 10 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
8.55%±1.50% | 4.16%±2.99% | 18.88%±5.41% | 12.85%±2.55% | 6.68%±1.76% | 0.18%±0.20% | 22.3K |
| 7 | 7 2 - 11 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
8.08%±1.52% | 4.54%±3.11% | 22.88%±5.58% | 8.35%±2.78% | 4.23%±1.00% | 0.38%±0.04% | 18.3K |
| 8 | 9 2 - 16 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
7.10%±2.02% | 4.92%±4.03% | 14.72%±7.28% | 8.73%±4.08% | 6.92%±1.18% | 0.22%±0.10% | 17.8K |
| 9 | 8 6 - 15 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
6.38%±0.74% | 10.80%±1.51% | 12.56%±2.58% | 2.98%±1.48% | 5.16%±0.55% | 0.38%±0.04% | 64.8K |
| 10 | 10 7 - 18 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
5.57%±1.10% | 0.89%±2.42% | 10.03%±3.81% | 7.35%±2.03% | 9.21%±1.37% | 0.38%±0.04% | 31.0K |
| 11 | 14 8 - 18 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.30%±0.80% | 6.71%±1.72% | 11.54%±2.85% | 5.49%±1.48% | 2.38%±0.68% | 0.38%±0.04% | 45.7K |
| 12 | 11 8 - 18 |
Hy4 preview
腾讯 · Apache 2.0
|
5.24%±1.23% | 9.44%±2.38% | 10.27%±4.55% | 1.56%±2.56% | 7.82%±0.64% | 0.22%±0.08% | 21.9K |
| 13 | 16 8 - 18 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
4.99%±0.93% | 7.83%±1.92% | 7.81%±3.34% | 2.81%±1.93% | 6.13%±0.69% | 0.37%±0.04% | 29.0K |
| 14 | 13 6 - 22 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
4.99%±2.17% | 6.32%±4.61% | 12.08%±8.03% | 2.61%±4.60% | 3.60%±1.29% | 0.32%±0.09% | 5.4K |
| 15 | 12 8 - 22 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
4.73%±1.54% | 9.92%±3.12% | 5.78%±5.21% | 0.38%±3.92% | 8.05%±0.80% | 0.29%±0.06% | 12.8K |
| 16 | 15 9 - 22 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
4.13%±0.99% | 7.78%±2.08% | 3.42%±3.39% | 3.20%±2.10% | 5.85%±0.87% | 0.38%±0.04% | 19.9K |
| 17 | 19 10 - 23 |
Grok 4.5
SpaceXAI · Proprietary
|
3.75%±1.18% | 3.56%±2.69% | 1.58%±4.02% | 7.47%±2.34% | 5.77%±1.38% | 0.38%±0.04% | 23.1K |
| 18 | 20 10 - 23 |
GPT 5.5
OpenAI · Proprietary
|
3.54%±0.98% | 0.17%±2.11% | 6.82%±3.25% | 5.15%±1.71% | 5.17%±1.60% | 0.38%±0.04% | 41.0K |
| 19 | 18 14 - 24 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.17%±0.70% | 8.34%±1.60% | 5.93%±2.44% | 2.14%±1.33% | 0.94%±0.64% | 0.38%±0.04% | 46.2K |
| 20 | 17 14 - 25 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.00%±0.98% | 5.07%±2.16% | 4.25%±3.34% | 2.91%±1.98% | 4.21%±0.87% | 1.45%±0.46% | 19.5K |
| 21 | 22 14 - 25 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
2.69%±0.83% | 5.83%±1.85% | 4.13%±2.86% | 1.03%±1.67% | 2.10%±0.68% | 0.36%±0.04% | 36.7K |
| 22 | 23 14 - 28 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
2.04%±1.31% | 2.99%±3.06% | 4.13%±4.39% | 6.88%±2.47% | 1.78%±1.63% | 0.38%±0.04% | 11.9K |
| 23 | 24 19 - 29 |
GPT 5.4 (High)
OpenAI · Proprietary
|
1.51%±0.96% | 2.09%±2.28% | 1.75%±3.19% | 3.61%±1.84% | 3.92%±1.17% | 0.38%±0.04% | 39.7K |
| 24 | 21 17 - 29 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
1.48%±1.21% | 4.75%±3.05% | 0.01%±3.88% | 5.74%±2.40% | 6.04%±1.03% | 0.38%±0.04% | 14.4K |
| 25 | 25 20 - 29 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
1.32%±0.77% | 7.12%±1.74% | 2.07%±2.51% | 1.30%±1.58% | 4.30%±0.75% | 0.38%±0.04% | 27.7K |
| 26 | 26 22 - 29 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
0.80%±0.93% | 9.17%±1.88% | 0.54%±3.20% | 3.10%±2.07% | 0.62%±0.55% | 0.90%±0.12% | 34.4K |
| 27 | 27 22 - 29 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
0.16%±0.99% | 2.90%±2.36% | 2.77%±3.14% | 3.07%±2.07% | 3.02%±1.13% | 0.38%±0.04% | 17.9K |
| 28 | 29 22 - 29 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
0.01%±0.84% | 4.41%±1.97% | 0.05%±2.77% | 0.09%±1.79% | 4.26%±0.78% | 0.15%±0.14% | 23.5K |
| 29 | 30 23 - 31 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.39%±1.10% | 0.71%±2.60% | 1.68%±3.76% | 2.31%±2.03% | 3.03%±0.96% | 0.28%±0.15% | 20.9K |
| 30 | 28 29 - 32 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
1.80%±0.74% | 0.59%±1.88% | 5.18%±2.24% | 1.40%±1.52% | 3.00%±0.80% | 0.01%±0.34% | 30.2K |
| 31 | 31 29 - 33 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.30%±1.31% | 6.15%±3.40% | 5.74%±3.90% | 4.45%±2.43% | 4.47%±1.85% | 0.34%±0.06% | 16.1K |
| 32 | 32 30 - 35 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
2.79%±1.06% | 4.85%±2.71% | 10.83%±3.16% | 5.51%±2.42% | 6.88%±1.18% | 0.38%±0.04% | 21.6K |
| 33 | 34 31 - 35 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.72%±0.99% | 6.13%±2.51% | 8.25%±2.80% | 3.05%±1.73% | 0.98%±1.85% | 0.18%±0.22% | 23.1K |
| 34 | 33 32 - 35 |
Muse Spark 1.1
Meta · Proprietary
|
4.31%±0.62% | 3.08%±1.58% | 12.19%±1.72% | 5.45%±1.27% | 1.19%±1.11% | 0.38%±0.04% | 67.0K |
| 35 | 35 32 - 40 |
Hy3
腾讯 · Apache 2.0
|
5.08%±1.43% | 6.91%±3.26% | 6.41%±4.20% | 2.79%±2.95% | 5.61%±2.82% | 3.70%±1.55% | 16.2K |
| 36 | 36 35 - 40 |
Mimo V2.5 Pro
小米 · MIT
|
5.94%±0.98% | 7.77%±2.60% | 11.62%±2.74% | 4.20%±1.89% | 5.29%±1.82% | 0.82%±0.31% | 23.8K |
| 37 | 37 35 - 40 |
Minimax M3
MiniMax · MiniMax Community License
|
5.95%±0.99% | 11.51%±2.74% | 12.03%±2.85% | 7.81%±1.98% | 1.56%±0.96% | 0.03%±0.14% | 23.1K |
| 38 | 40 35 - 40 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
6.63%±1.42% | 8.17%±3.66% | 12.16%±3.76% | 6.69%±2.68% | 5.00%±2.95% | 1.16%±0.50% | 12.6K |
| 39 | 39 35 - 40 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
6.87%±1.18% | 7.66%±3.06% | 9.44%±3.31% | 4.24%±2.28% | 13.36%±1.93% | 0.35%±0.06% | 12.4K |
| 40 | 38 35 - 40 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
6.96%±0.96% | 7.22%±2.27% | 2.01%±2.78% | 4.71%±1.61% | 20.73%±1.87% | 0.12%±0.51% | 43.1K |
| 41 | 41 41 - 43 |
Inkling Small
Thinky · Apache 2.0
|
10.26%±1.57% | 20.41%±4.91% | 22.62%±3.86% | 14.94%±3.65% | 7.28%±1.34% | 0.62%±0.47% | 7.1K |
| 42 | 42 41 - 43 |
Inkling
Thinky · Apache 2.0
|
10.31%±1.09% | 19.61%±3.38% | 23.08%±2.60% | 13.07%±2.46% | 4.11%±1.46% | 0.10%±0.12% | 23.4K |
| 43 | 43 41 - 45 |
Mistral Medium 3.5
Mistral · Modified MIT
|
11.46%±1.73% | 16.64%±4.59% | 15.43%±4.75% | 9.22%±3.83% | 14.05%±2.76% | 1.96%±0.82% | 5.9K |
| 44 | 44 43 - 45 |
Minimax M2.7
MiniMax · Modified MIT
|
13.68%±1.23% | 14.30%±3.14% | 21.60%±2.90% | 7.98%±2.76% | 24.71%±2.94% | 0.22%±0.15% | 22.3K |
| 45 | 46 43 - 46 |
Solar Pro 4
Upstage · Proprietary
|
15.16%±2.06% | 17.08%±5.73% | 22.92%±4.87% | 11.35%±4.47% | 22.58%±4.61% | 1.85%±0.87% | 5.5K |
| 46 | 45 45 - 46 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
17.10%±1.51% | 16.65%±3.68% | 19.93%±3.18% | 15.40%±2.71% | 31.54%±4.41% | 1.97%±0.99% | 13.2K |
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
智谱 ZAI
腾讯
DeepSeek
Google
Meta
SpaceXAI
阿里巴巴
小米
MiniMax
Mistral