| 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
|
15.91%±2.68% | 15.55%±5.04% | 39.36%±10.66% | 12.31%±5.31% | 12.00%±1.24% | 0.34%±0.03% | 5.0K |
| 🥈 | 2 1 - 4 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
14.30%±3.45% | 17.87%±5.54% | 44.06%±13.43% | 2.88%±7.21% | 6.34%±1.49% | 0.34%±0.03% | 4.1K |
| 🥉 | 3 2 - 7 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
11.18%±1.92% | 9.73%±4.31% | 21.39%±6.94% | 12.92%±3.55% | 11.61%±0.93% | 0.27%±0.04% | 8.8K |
| 4 | 6 2 - 14 |
GPT 6 Sol (Max)
OpenAI · Proprietary
|
9.17%±3.55% | 9.84%±8.16% | 9.96%±12.47% | 17.41%±8.10% | 8.29%±1.90% | 0.34%±0.03% | 1.6K |
| 5 | 5 3 - 9 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
9.11%±1.70% | 4.76%±4.12% | 17.64%±5.73% | 13.67%±3.01% | 9.13%±1.37% | 0.34%±0.03% | 12.4K |
| 6 | 7 3 - 9 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
8.27%±1.75% | 4.62%±3.89% | 18.22%±6.15% | 12.34%±2.96% | 6.05%±2.27% | 0.13%±0.19% | 12.6K |
| 7 | 4 3 - 10 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
8.17%±1.91% | 8.97%±4.77% | 9.58%±6.47% | 9.84%±3.66% | 12.14%±0.99% | 0.32%±0.04% | 6.8K |
| 8 | 8 4 - 17 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
6.73%±1.79% | 2.15%±4.17% | 21.20%±6.12% | 7.51%±3.12% | 2.46%±1.39% | 0.34%±0.03% | 10.7K |
| 9 | 9 4 - 20 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
5.68%±2.25% | 6.20%±5.27% | 7.62%±7.64% | 8.57%±4.57% | 5.89%±1.33% | 0.14%±0.12% | 9.9K |
| 10 | 15 6 - 17 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.51%±0.93% | 7.52%±2.20% | 12.96%±3.17% | 5.98%±1.66% | 0.73%±0.85% | 0.34%±0.03% | 27.7K |
| 11 | 10 7 - 18 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
5.23%±0.74% | 9.84%±1.74% | 9.91%±2.43% | 1.57%±1.45% | 4.48%±0.55% | 0.34%±0.03% | 44.8K |
| 12 | 12 7 - 21 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
4.69%±1.30% | 0.59%±3.36% | 7.66%±4.17% | 8.00%±2.31% | 8.04%±1.41% | 0.33%±0.03% | 16.9K |
| 13 | 11 7 - 21 |
Hy4 preview
腾讯 · Apache 2.0
|
4.65%±1.26% | 7.61%±2.88% | 8.31%±4.27% | 0.56%±2.55% | 7.68%±0.70% | 0.22%±0.07% | 17.6K |
| 14 | 16 8 - 20 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
4.60%±0.82% | 8.14%±1.93% | 4.67%±2.67% | 3.81%±1.69% | 6.03%±0.75% | 0.33%±0.03% | 22.4K |
| 15 | 14 8 - 20 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
4.40%±0.80% | 10.41%±1.87% | 4.99%±2.58% | 2.11%±1.88% | 8.53%±0.43% | 0.18%±0.05% | 31.2K |
| 16 | 18 8 - 23 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
4.31%±1.12% | 6.63%±2.67% | 7.60%±3.71% | 1.82%±2.27% | 5.19%±0.87% | 0.32%±0.04% | 16.9K |
| 17 | 17 7 - 26 |
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
3.41%±2.56% | 3.81%±5.70% | 6.22%±8.76% | 0.81%±5.36% | 5.87%±1.52% | 0.34%±0.03% | 3.1K |
| 18 | 23 10 - 25 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
3.25%±1.32% | 1.35%±3.47% | 1.58%±4.09% | 7.35%±2.55% | 5.62%±1.27% | 0.34%±0.03% | 9.3K |
| 19 | 19 11 - 24 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.25%±0.85% | 7.06%±2.21% | 6.55%±2.77% | 3.32%±1.60% | 1.02%±0.70% | 0.34%±0.03% | 29.9K |
| 20 | 13 11 - 25 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
2.85%±1.24% | 6.43%±2.90% | 4.52%±4.00% | 3.55%±2.61% | 0.37%±0.72% | 0.13%±0.10% | 10.0K |
| 21 | 20 17 - 25 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
2.28%±0.91% | 5.13%±2.25% | 1.95%±2.89% | 1.99%±1.79% | 3.16%±0.85% | 0.83%±0.32% | 17.5K |
| 22 | 21 16 - 26 |
GPT 5.5
OpenAI · Proprietary
|
2.15%±1.15% | 2.31%±2.97% | 4.06%±3.57% | 4.60%±2.00% | 4.08%±1.45% | 0.34%±0.03% | 22.5K |
| 23 | 22 14 - 26 |
Grok 4.5
SpaceXAI · Proprietary
|
2.06%±1.36% | 0.43%±3.64% | 0.81%±4.28% | 5.58%±2.66% | 5.63%±1.17% | 0.34%±0.03% | 14.0K |
| 24 | 24 16 - 29 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
1.77%±1.50% | 3.50%±4.04% | 3.61%±4.67% | 6.91%±2.67% | 1.46%±1.35% | 0.34%±0.03% | 7.4K |
| 25 | 27 18 - 29 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
1.36%±0.96% | 7.80%±2.30% | 1.30%±3.20% | 1.26%±2.02% | 0.05%±0.56% | 0.99%±0.13% | 27.8K |
| 26 | 25 21 - 30 |
GPT 5.4 (High)
OpenAI · Proprietary
|
0.13%±1.17% | 3.34%±3.20% | 0.44%±3.49% | 3.06%±2.19% | 1.01%±1.64% | 0.34%±0.03% | 21.8K |
| 27 | 26 24 - 30 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
0.01%±0.67% | 6.60%±1.80% | 1.61%±1.97% | 0.03%±1.32% | 5.33%±0.67% | 0.34%±0.03% | 28.0K |
| 28 | 31 24 - 30 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
0.28%±0.82% | 4.61%±2.13% | 0.97%±2.55% | 0.10%±1.66% | 4.85%±0.75% | 0.11%±0.11% | 20.5K |
| 29 | 28 24 - 30 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
0.36%±0.95% | 3.74%±2.56% | 3.08%±2.81% | 2.57%±1.84% | 2.10%±1.03% | 0.34%±0.03% | 14.3K |
| 30 | 29 26 - 31 |
DeepSeek V4 Pro
DeepSeek · MIT
|
1.26%±1.32% | 3.48%±3.54% | 2.30%±4.26% | 2.24%±2.22% | 2.14%±1.21% | 0.42%±0.20% | 11.8K |
| 31 | 30 30 - 34 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
3.15%±0.88% | 3.23%±2.57% | 5.98%±2.41% | 1.70%±1.66% | 4.71%±0.89% | 0.12%±0.33% | 18.9K |
| 32 | 32 31 - 34 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
3.55%±0.92% | 7.09%±2.73% | 10.76%±2.48% | 8.19%±1.88% | 7.99%±0.99% | 0.31%±0.06% | 18.0K |
| 33 | 34 31 - 37 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
4.99%±1.13% | 8.37%±3.43% | 10.97%±2.81% | 3.78%±1.94% | 1.77%±2.06% | 0.09%±0.19% | 13.5K |
| 34 | 33 33 - 37 |
Muse Spark 1.1
Meta · Proprietary
|
5.29%±0.62% | 6.18%±1.77% | 11.08%±1.53% | 6.69%±1.19% | 2.81%±1.03% | 0.32%±0.04% | 49.0K |
| 35 | 35 31 - 38 |
Hy3
腾讯 · Apache 2.0
|
5.49%±1.73% | 5.71%±4.37% | 6.28%±4.76% | 3.36%±3.44% | 8.93%±3.85% | 3.15%±1.11% | 9.6K |
| 36 | 37 33 - 38 |
Minimax M3
MiniMax · MiniMax Community License
|
6.86%±1.21% | 13.40%±3.68% | 12.26%±3.09% | 9.33%±2.26% | 0.87%±1.20% | 0.19%±0.27% | 13.6K |
| 37 | 36 33 - 39 |
Mimo V2.5 Pro
小米 · MIT
|
7.01%±1.13% | 10.62%±3.40% | 11.52%±2.84% | 5.87%±2.08% | 6.10%±1.90% | 0.97%±0.32% | 14.7K |
| 38 | 39 35 - 43 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
8.17%±1.76% | 11.65%±5.15% | 13.56%±4.03% | 8.48%±2.99% | 6.47%±3.71% | 0.69%±0.33% | 7.2K |
| 39 | 38 38 - 43 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
9.37%±1.22% | 12.03%±3.37% | 4.51%±2.93% | 6.37%±1.91% | 22.88%±2.47% | 1.03%±1.53% | 23.2K |
| 40 | 40 38 - 43 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
9.82%±1.38% | 13.60%±4.07% | 10.72%±3.39% | 6.95%±2.51% | 18.12%±2.43% | 0.30%±0.05% | 7.7K |
| 41 | 41 37 - 43 |
Inkling Small
Thinky · Apache 2.0
|
10.01%±1.90% | 22.35%±6.87% | 21.73%±4.21% | 14.59%±4.07% | 9.19%±1.69% | 0.57%±0.48% | 4.0K |
| 42 | 42 38 - 43 |
Inkling
Thinky · Apache 2.0
|
10.41%±1.36% | 21.26%±4.65% | 21.31%±2.89% | 15.93%±2.90% | 6.37%±1.38% | 0.08%±0.12% | 13.2K |
| 43 | 43 38 - 43 |
Mistral Medium 3.5
Mistral · Modified MIT
|
11.86%±2.08% | 14.04%±6.17% | 16.14%±5.15% | 12.32%±4.37% | 14.37%±3.30% | 2.42%±1.01% | 3.4K |
| 44 | 44 44 - 44 |
Solar Pro 4
Upstage · Proprietary
|
16.87%±2.41% | 19.67%±8.07% | 23.96%±4.17% | 12.15%±4.71% | 26.43%±5.68% | 2.11%±0.98% | 3.2K |
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
智谱 ZAI
月之暗面
腾讯
Meta
DeepSeek
SpaceXAI
Google
阿里巴巴
MiniMax
小米
Mistral