| 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 - 6 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
12.28%±3.23% | 19.69%±4.82% | 23.70%±12.98% | 5.54%±6.42% | 12.19%±1.69% | 0.27%±0.03% | 6.2K |
| 🥈 | 4 1 - 7 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.94%±2.93% | 13.82%±5.10% | 19.39%±11.63% | 8.50%±5.94% | 12.73%±1.96% | 0.26%±0.04% | 9.1K |
| 🥉 | 5 1 - 10 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
8.93%±2.26% | 6.65%±4.20% | 18.93%±8.69% | 9.90%±3.88% | 8.92%±3.42% | 0.27%±0.03% | 17.2K |
| 4 | 2 1 - 12 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
8.86%±3.80% | 17.25%±6.03% | 22.35%±15.34% | 3.39%±8.30% | 7.83%±3.93% | 0.27%±0.03% | 4.4K |
| 5 | 3 1 - 11 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
8.43%±2.52% | 6.48%±5.03% | 13.07%±9.87% | 10.58%±4.69% | 11.77%±2.17% | 0.27%±0.03% | 11.4K |
| 6 | 6 1 - 26 |
GPT 6 Sol (Max)
OpenAI · Proprietary
|
6.28%±5.04% | 14.21%±7.89% | 5.27%±19.98% | 11.36%±11.60% | 10.81%±3.36% | 0.27%±0.03% | 1.4K |
| 7 | 13 3 - 15 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
5.80%±1.91% | 14.12%±3.15% | 11.32%±7.37% | 1.01%±4.20% | 2.41%±1.57% | 0.15%±0.15% | 10.2K |
| 8 | 7 2 - 19 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
5.67%±2.37% | 5.05%±4.36% | 9.38%±8.69% | 5.73%±4.09% | 8.35%±3.46% | 0.18%±0.53% | 15.2K |
| 9 | 8 3 - 24 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
5.02%±2.28% | 4.42%±4.25% | 12.06%±8.34% | 2.28%±4.55% | 6.08%±2.43% | 0.27%±0.03% | 14.5K |
| 10 | 11 5 - 25 |
Hy4 preview
腾讯 · Apache 2.0
|
3.64%±1.82% | 6.46%±3.32% | 5.35%±6.90% | 0.84%±3.62% | 5.44%±1.09% | 0.12%±0.09% | 17.0K |
| 11 | 17 3 - 32 |
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
3.44%±4.12% | 19.96%±5.94% | 0.14%±14.63% | 9.40%±10.95% | 6.53%±3.06% | 0.27%±0.03% | 2.6K |
| 12 | 20 6 - 25 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.36%±1.28% | 6.69%±2.49% | 4.75%±4.67% | 4.17%±2.65% | 2.04%±1.61% | 0.84%±0.30% | 19.1K |
| 13 | 12 6 - 25 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
3.31%±1.68% | 1.42%±3.45% | 3.01%±6.20% | 3.59%±3.42% | 11.08%±2.18% | 0.27%±0.03% | 23.0K |
| 14 | 9 4 - 29 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
3.11%±2.80% | 3.33%±5.64% | 7.34%±9.97% | 5.51%±5.49% | 5.89%±3.43% | 0.16%±0.16% | 13.5K |
| 15 | 30 6 - 25 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
2.85%±1.30% | 4.24%±2.72% | 2.82%±4.72% | 5.13%±2.66% | 1.79%±1.22% | 0.27%±0.03% | 21.9K |
| 16 | 10 7 - 25 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
2.77%±1.01% | 9.01%±1.96% | 3.71%±3.65% | 3.80%±2.21% | 4.66%±1.13% | 0.27%±0.03% | 54.2K |
| 17 | 19 7 - 27 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
2.38%±1.25% | 4.20%±2.59% | 5.63%±4.61% | 0.73%±2.27% | 1.07%±1.17% | 0.27%±0.03% | 33.4K |
| 18 | 14 7 - 27 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
2.37%±1.22% | 14.32%±2.05% | 0.88%±4.43% | 7.31%±3.01% | 3.83%±1.02% | 0.14%±0.08% | 27.6K |
| 19 | 16 8 - 28 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
2.04%±1.17% | 8.96%±2.11% | 0.91%±4.01% | 1.90%±2.67% | 3.80%±1.63% | 0.27%±0.03% | 22.9K |
| 20 | 22 7 - 30 |
Grok 4.5
SpaceXAI · Proprietary
|
1.98%±1.77% | 1.69%±3.61% | 2.18%±6.17% | 3.15%±3.62% | 6.99%±2.56% | 0.27%±0.03% | 17.7K |
| 21 | 15 8 - 28 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
1.87%±1.33% | 0.70%±2.64% | 6.66%±4.76% | 0.03%±2.52% | 3.09%±1.70% | 0.27%±0.03% | 34.9K |
| 22 | 18 8 - 29 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
1.78%±1.51% | 0.31%±2.97% | 4.85%±5.57% | 1.80%±3.07% | 5.29%±1.28% | 0.27%±0.03% | 18.8K |
| 23 | 21 8 - 30 |
GPT 5.5
OpenAI · Proprietary
|
1.66%±1.57% | 4.46%±3.20% | 2.94%±5.65% | 0.54%±2.95% | 10.07%±1.92% | 0.27%±0.03% | 29.2K |
| 24 | 23 8 - 32 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
0.85%±1.92% | 3.12%±4.01% | 2.61%±6.74% | 1.30%±3.79% | 5.81%±2.39% | 0.27%±0.03% | 11.0K |
| 25 | 24 9 - 33 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.06%±2.11% | 6.83%±4.25% | 2.91%±7.54% | 2.29%±4.18% | 6.25%±2.80% | 0.27%±0.03% | 9.4K |
| 26 | 26 17 - 32 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
0.02%±1.05% | 7.60%±2.01% | 0.85%±3.69% | 2.54%±2.20% | 6.08%±1.60% | 0.27%±0.03% | 28.0K |
| 27 | 25 15 - 33 |
GPT 5.4 (High)
OpenAI · Proprietary
|
0.39%±1.59% | 5.30%±3.31% | 4.63%±5.77% | 0.80%±3.18% | 6.91%±1.91% | 0.27%±0.03% | 28.2K |
| 28 | 29 14 - 35 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.48%±1.89% | 4.68%±3.93% | 0.17%±6.73% | 1.96%±3.71% | 4.32%±1.95% | 0.10%±0.15% | 14.8K |
| 29 | 28 21 - 35 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
1.14%±1.35% | 5.20%±2.75% | 4.67%±4.45% | 1.13%±2.73% | 2.80%±2.31% | 0.27%±0.03% | 16.0K |
| 30 | 33 23 - 33 |
Muse Spark 1.1
Meta · Proprietary
|
1.18%±0.93% | 4.31%±1.80% | 7.22%±2.90% | 2.80%±1.95% | 0.44%±2.10% | 0.26%±0.04% | 56.4K |
| 31 | 40 19 - 38 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
1.50%±1.90% | 1.80%±3.89% | 0.56%±6.70% | 0.69%±3.86% | 6.02%±2.58% | 0.19%±0.16% | 9.4K |
| 32 | 32 23 - 38 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.79%±1.43% | 0.84%±2.99% | 8.95%±4.57% | 0.64%±3.06% | 1.19%±2.49% | 0.27%±0.03% | 18.5K |
| 33 | 34 26 - 39 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.31%±1.81% | 9.73%±3.71% | 4.37%±5.50% | 1.05%±3.15% | 1.07%±4.25% | 0.32%±0.41% | 16.8K |
| 34 | 27 29 - 39 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
3.43%±1.19% | 3.87%±2.53% | 6.29%±4.13% | 7.42%±2.78% | 6.63%±1.00% | 0.65%±0.17% | 28.6K |
| 35 | 31 31 - 39 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
4.12%±1.15% | 0.16%±2.45% | 8.93%±3.83% | 1.42%±2.58% | 9.83%±1.52% | 0.28%±0.26% | 21.1K |
| 36 | 36 29 - 40 |
Mimo V2.5 Pro
小米 · MIT
|
4.33%±1.97% | 9.59%±3.80% | 5.20%±5.87% | 0.21%±3.39% | 6.08%±5.47% | 0.56%±0.47% | 17.6K |
| 37 | 38 33 - 41 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
5.13%±1.64% | 6.46%±3.02% | 3.21%±4.85% | 0.99%±2.63% | 21.65%±4.56% | 0.27%±0.03% | 32.0K |
| 38 | 35 31 - 41 |
Hy3
腾讯 · Apache 2.0
|
5.15%±2.00% | 14.30%±4.40% | 7.24%±6.47% | 0.73%±4.04% | 2.16%±3.02% | 2.78%±1.18% | 11.7K |
| 39 | 39 31 - 42 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
5.37%±2.24% | 7.94%±5.01% | 11.45%±7.03% | 4.03%±4.62% | 2.35%±4.53% | 1.08%±0.76% | 9.1K |
| 40 | 37 36 - 42 |
Minimax M3
MiniMax · MiniMax Community License
|
7.78%±1.57% | 18.08%±3.92% | 15.56%±4.69% | 4.86%±3.20% | 0.15%±2.65% | 0.27%±0.46% | 17.2K |
| 41 | 41 37 - 44 |
Inkling Small
Thinky · Apache 2.0
|
8.98%±2.66% | 22.61%±6.84% | 16.84%±8.25% | 5.29%±6.12% | 0.24%±3.37% | 0.39%±0.59% | 4.9K |
| 42 | 42 39 - 43 |
Inkling
Thinky · Apache 2.0
|
9.38%±1.99% | 22.46%±4.66% | 18.56%±5.59% | 3.15%±4.14% | 2.50%±4.19% | 0.21%±0.33% | 16.6K |
| 43 | 43 41 - 44 |
Mistral Medium 3.5
Mistral · Modified MIT
|
12.61%±2.80% | 16.75%±6.15% | 22.32%±6.58% | 3.97%±5.81% | 25.42%±8.19% | 2.55%±1.98% | 4.4K |
| 44 | 44 42 - 44 |
Solar Pro 4
Upstage · Proprietary
|
15.93%±4.37% | 25.97%±8.19% | 17.33%±11.26% | 3.81%±6.71% | 31.57%±14.15% | 0.99%±1.16% | 3.9K |
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
Google
腾讯
SpaceXAI
阿里巴巴
月之暗面
智谱 ZAI
DeepSeek
Meta
小米
MiniMax
Mistral