| 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
|
15.40%±2.29% | 20.96%±3.13% | 43.67%±9.17% | 1.62%±4.88% | 10.40%±1.15% | 0.38%±0.07% | 6.9K |
| 🥈 | 3 1 - 7 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
11.62%±2.00% | 12.64%±4.11% | 21.02%±7.50% | 11.99%±3.94% | 12.10%±0.85% | 0.34%±0.06% | 13.6K |
| 🥉 | 2 1 - 8 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
11.29%±2.70% | 19.08%±3.71% | 38.14%±9.99% | 5.82%±6.83% | 4.66%±1.57% | 0.40%±0.05% | 5.2K |
| 4 | 4 2 - 8 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.41%±2.28% | 10.76%±4.62% | 18.81%±8.26% | 9.24%±4.45% | 12.86%±0.86% | 0.37%±0.06% | 10.6K |
| 5 | 5 2 - 8 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
9.51%±1.70% | 5.39%±3.77% | 20.04%±6.14% | 12.52%±3.03% | 9.22%±1.66% | 0.40%±0.05% | 20.7K |
| 6 | 6 2 - 10 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
8.63%±1.71% | 6.02%±3.64% | 21.59%±6.30% | 10.60%±3.23% | 4.56%±1.03% | 0.40%±0.05% | 17.1K |
| 7 | 7 2 - 11 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
8.30%±1.72% | 2.38%±3.64% | 20.42%±6.16% | 12.07%±3.09% | 6.51%±1.82% | 0.14%±0.35% | 21.7K |
| 8 | 9 3 - 15 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
7.00%±2.30% | 3.83%±4.74% | 14.70%±8.15% | 8.26%±4.96% | 7.95%±1.30% | 0.26%±0.09% | 17.0K |
| 9 | 8 6 - 13 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
6.84%±0.83% | 13.27%±1.70% | 14.88%±2.91% | 1.20%±1.58% | 4.44%±0.59% | 0.40%±0.05% | 59.1K |
| 10 | 12 8 - 15 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.64%±0.87% | 9.11%±1.84% | 13.62%±3.13% | 3.52%±1.55% | 1.58%±0.74% | 0.40%±0.05% | 42.5K |
| 11 | 11 7 - 17 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
5.60%±1.27% | 1.15%±2.93% | 8.89%±4.35% | 7.96%±2.35% | 9.62%±1.44% | 0.40%±0.05% | 30.2K |
| 12 | 13 8 - 17 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
5.43%±1.08% | 11.38%±2.21% | 8.85%±3.93% | 1.03%±2.23% | 5.47%±0.82% | 0.40%±0.05% | 22.6K |
| 13 | 10 6 - 19 |
Hy4 preview
腾讯 · Apache 2.0
|
5.38%±1.71% | 10.04%±3.22% | 11.25%±6.43% | 2.37%±3.54% | 7.73%±0.84% | 0.27%±0.09% | 9.8K |
| 14 | 15 9 - 22 |
Grok 4.5
SpaceXAI · Proprietary
|
4.43%±1.38% | 6.54%±3.00% | 4.23%±4.77% | 5.54%±2.69% | 5.44%±1.65% | 0.40%±0.05% | 21.6K |
| 15 | 14 9 - 26 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
3.76%±2.23% | 4.66%±5.96% | 10.09%±7.13% | 1.90%±4.27% | 1.80%±1.43% | 0.32%±0.12% | 3.8K |
| 16 | 18 11 - 25 |
GPT 5.5
OpenAI · Proprietary
|
3.61%±1.07% | 1.55%±2.49% | 4.86%±3.59% | 5.79%±1.93% | 5.48%±1.53% | 0.40%±0.05% | 40.1K |
| 17 | 16 11 - 25 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.47%±1.20% | 8.21%±2.72% | 3.72%±4.11% | 2.58%±2.41% | 3.91%±1.09% | 1.08%±0.31% | 13.4K |
| 18 | 20 13 - 25 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
2.93%±0.89% | 8.41%±2.00% | 4.93%±3.01% | 0.61%±1.77% | 1.56%±0.70% | 0.37%±0.06% | 34.9K |
| 19 | 17 13 - 27 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
2.74%±1.36% | 1.93%±3.23% | 2.79%±4.51% | 3.78%±2.67% | 4.81%±1.19% | 0.40%±0.05% | 12.6K |
| 20 | 19 14 - 25 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
2.58%±0.78% | 10.13%±1.75% | 5.45%±2.59% | 0.14%±1.49% | 2.96%±0.77% | 0.40%±0.05% | 38.1K |
| 21 | 22 14 - 27 |
GPT 5.4 (High)
OpenAI · Proprietary
|
2.28%±1.10% | 0.64%±2.65% | 2.35%±3.71% | 4.44%±2.08% | 4.84%±1.00% | 0.40%±0.05% | 38.8K |
| 22 | 21 15 - 27 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
1.93%±1.05% | 10.98%±2.36% | 2.84%±3.42% | 0.14%±2.11% | 4.70%±0.96% | 0.40%±0.05% | 15.0K |
| 23 | 23 14 - 27 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
1.88%±1.38% | 2.43%±3.51% | 0.18%±4.58% | 8.00%±2.71% | 3.26%±1.46% | 0.40%±0.05% | 10.8K |
| 24 | 24 15 - 28 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
1.37%±1.25% | 1.76%±2.95% | 0.82%±4.08% | 2.06%±2.57% | 3.46%±1.22% | 0.40%±0.05% | 12.5K |
| 25 | 25 15 - 28 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
1.34%±1.24% | 10.59%±2.61% | 0.59%±4.31% | 2.56%±2.83% | 0.10%±0.69% | 0.83%±0.17% | 16.1K |
| 26 | 26 19 - 28 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
0.50%±1.06% | 6.38%±2.47% | 2.60%±3.59% | 1.73%±2.13% | 4.64%±0.94% | 0.09%±0.14% | 16.4K |
| 27 | 27 20 - 28 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.13%±1.34% | 0.45%±3.39% | 2.10%±4.60% | 0.72%±2.37% | 3.42%±0.99% | 0.43%±0.21% | 19.2K |
| 28 | 28 24 - 31 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
1.31%±1.49% | 5.76%±3.91% | 4.74%±4.54% | 2.32%±2.92% | 5.96%±1.81% | 0.30%±0.18% | 16.1K |
| 29 | 29 28 - 35 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
3.24%±1.38% | 1.48%±3.66% | 10.48%±4.37% | 9.12%±2.97% | 4.50%±1.83% | 0.40%±0.05% | 14.5K |
| 30 | 31 28 - 35 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.29%±1.13% | 3.00%±2.89% | 8.92%±3.20% | 3.94%±1.99% | 0.41%±2.20% | 0.17%±0.25% | 22.2K |
| 31 | 32 28 - 37 |
Hy3
腾讯 · Apache 2.0
|
3.96%±1.63% | 3.03%±3.65% | 5.42%±4.93% | 2.31%±3.30% | 5.24%±3.05% | 3.79%±2.04% | 15.1K |
| 32 | 30 29 - 35 |
Muse Spark 1.1
Meta · Proprietary
|
4.20%±0.75% | 0.60%±1.90% | 11.80%±2.09% | 7.26%±1.48% | 1.76%±1.35% | 0.39%±0.05% | 56.6K |
| 33 | 33 29 - 38 |
Mimo V2.5 Pro
小米 · MIT
|
5.28%±1.11% | 6.46%±3.00% | 11.13%±3.13% | 3.23%±2.12% | 4.85%±1.98% | 0.72%±0.35% | 22.3K |
| 34 | 35 29 - 38 |
Minimax M3
MiniMax · MiniMax Community License
|
5.31%±1.14% | 9.66%±3.16% | 10.74%±3.36% | 7.91%±2.24% | 1.68%±1.10% | 0.07%±0.14% | 22.0K |
| 35 | 34 29 - 39 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
5.67%±1.49% | 8.45%±4.04% | 12.44%±4.07% | 4.71%±3.02% | 1.86%±2.50% | 0.91%±0.46% | 12.3K |
| 36 | 37 32 - 39 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
6.36%±1.16% | 6.97%±2.92% | 2.28%±3.38% | 3.61%±1.98% | 18.85%±1.98% | 0.09%±0.47% | 42.5K |
| 37 | 36 32 - 39 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
6.46%±1.30% | 6.19%±3.50% | 10.37%±3.66% | 5.04%±2.57% | 11.05%±1.89% | 0.37%±0.07% | 11.2K |
| 38 | 38 35 - 41 |
Inkling Small
Thinky · Apache 2.0
|
8.54%±1.90% | 19.95%±5.77% | 20.08%±5.04% | 10.55%±4.50% | 8.62%±1.34% | 0.74%±0.63% | 6.7K |
| 39 | 39 38 - 41 |
Inkling
Thinky · Apache 2.0
|
9.18%±1.29% | 17.84%±4.00% | 21.63%±3.28% | 12.10%±2.93% | 5.60%±1.31% | 0.09%±0.18% | 22.9K |
| 40 | 41 33 - 43 |
Solar Pro 4
Upstage · Proprietary
|
9.92%±4.26% | 10.98%±9.63% | 12.02%±12.20% | 0.24%±8.59% | 25.52%±9.54% | 0.82%±1.52% | 3.5K |
| 41 | 40 38 - 42 |
Mistral Medium 3.5
Mistral · Modified MIT
|
10.33%±1.84% | 19.56%±4.86% | 13.13%±5.12% | 7.46%±4.06% | 9.80%±2.41% | 1.71%±0.82% | 5.3K |
| 42 | 42 40 - 43 |
Minimax M2.7
MiniMax · Modified MIT
|
12.58%±1.39% | 12.11%±3.73% | 22.05%±3.38% | 7.20%±3.17% | 21.77%±2.89% | 0.24%±0.17% | 22.2K |
| 43 | 43 41 - 43 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
14.65%±1.61% | 15.25%±4.56% | 21.17%±3.57% | 12.66%±3.41% | 22.55%±3.43% | 1.62%±0.89% | 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
DeepSeek
腾讯
SpaceXAI
Google
阿里巴巴
Meta
小米
MiniMax
Mistral