| 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 - 4 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
15.52%±3.05% | 22.10%±4.97% | 39.09%±11.91% | 4.11%±6.80% | 11.92%±1.26% | 0.37%±0.04% | 4.2K |
| 🥈 | 2 1 - 7 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
13.14%±4.01% | 21.25%±6.87% | 35.98%±14.72% | 1.42%±9.74% | 6.68%±1.44% | 0.37%±0.04% | 3.5K |
| 🥉 | 4 1 - 7 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
11.81%±2.31% | 12.94%±5.17% | 20.13%±8.18% | 14.19%±4.26% | 11.49%±1.29% | 0.31%±0.05% | 7.9K |
| 4 | 3 1 - 8 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.55%±2.52% | 11.95%±5.79% | 17.19%±8.76% | 9.89%±4.73% | 13.35%±0.91% | 0.35%±0.05% | 6.1K |
| 5 | 5 2 - 8 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
9.75%±1.91% | 6.87%±4.92% | 17.56%±6.60% | 14.38%±3.37% | 9.58%±1.45% | 0.37%±0.04% | 11.4K |
| 6 | 7 2 - 12 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
8.60%±2.05% | 3.71%±4.82% | 24.68%±7.11% | 10.29%±3.55% | 3.93%±1.28% | 0.37%±0.04% | 9.7K |
| 7 | 6 2 - 13 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
8.36%±1.96% | 1.66%±4.76% | 17.97%±6.58% | 14.38%±3.46% | 7.68%±1.75% | 0.10%±0.34% | 12.2K |
| 8 | 8 6 - 15 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
6.90%±0.94% | 13.49%±2.25% | 13.46%±3.13% | 2.78%±1.75% | 4.39%±0.68% | 0.37%±0.04% | 35.4K |
| 9 | 9 4 - 22 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
6.52%±2.52% | 7.97%±5.74% | 10.11%±8.57% | 6.81%±5.36% | 7.53%±1.29% | 0.20%±0.12% | 9.5K |
| 10 | 11 6 - 17 |
Hy4 preview
腾讯 · Apache 2.0
|
6.05%±1.53% | 13.09%±3.33% | 11.12%±5.52% | 2.30%±3.06% | 8.04%±0.80% | 0.28%±0.07% | 10.1K |
| 11 | 13 6 - 17 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.81%±0.99% | 11.29%±2.34% | 12.76%±3.37% | 4.51%±1.70% | 0.11%±1.00% | 0.37%±0.04% | 24.5K |
| 12 | 15 8 - 22 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
5.07%±1.19% | 10.53%±2.79% | 8.89%±3.99% | 0.39%±2.32% | 5.19%±0.88% | 0.36%±0.05% | 16.0K |
| 13 | 10 7 - 22 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
4.95%±1.48% | 0.68%±3.99% | 7.80%±4.70% | 8.71%±2.68% | 8.53%±1.48% | 0.37%±0.04% | 16.4K |
| 14 | 14 8 - 22 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
4.59%±1.41% | 8.67%±3.50% | 6.75%±4.43% | 1.03%±2.94% | 6.12%±1.18% | 0.37%±0.04% | 8.6K |
| 15 | 12 6 - 26 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
4.34%±2.44% | 11.35%±6.17% | 1.89%±7.51% | 0.13%±6.23% | 8.17%±1.21% | 0.19%±0.15% | 3.2K |
| 16 | 17 9 - 23 |
Grok 4.5
SpaceXAI · Proprietary
|
3.99%±1.56% | 5.35%±3.99% | 1.29%±5.03% | 7.85%±2.98% | 5.09%±1.48% | 0.37%±0.04% | 12.5K |
| 17 | 20 9 - 25 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
3.48%±1.53% | 2.26%±4.26% | 2.82%±4.64% | 6.26%±2.83% | 5.70%±1.40% | 0.37%±0.04% | 7.8K |
| 18 | 18 11 - 23 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.39%±0.86% | 11.14%±2.21% | 7.29%±2.80% | 0.59%±1.52% | 2.44%±0.80% | 0.37%±0.04% | 26.1K |
| 19 | 21 11 - 25 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
3.18%±1.01% | 9.73%±2.52% | 4.67%±3.35% | 0.08%±1.91% | 1.26%±0.81% | 0.35%±0.05% | 20.7K |
| 20 | 16 11 - 25 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.18%±1.26% | 8.68%±3.14% | 2.77%±4.05% | 2.29%±2.45% | 3.16%±1.18% | 0.97%±0.53% | 9.7K |
| 21 | 19 11 - 27 |
GPT 5.5
OpenAI · Proprietary
|
2.90%±1.28% | 1.55%±3.47% | 4.51%±3.93% | 6.29%±2.24% | 4.88%±1.45% | 0.37%±0.04% | 21.9K |
| 22 | 22 11 - 28 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
2.54%±1.65% | 3.10%±4.61% | 2.90%±5.09% | 9.76%±3.02% | 2.78%±1.52% | 0.37%±0.04% | 6.5K |
| 23 | 26 15 - 28 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
1.54%±1.25% | 11.83%±3.00% | 0.72%±4.06% | 2.62%±2.60% | 0.21%±0.67% | 1.03%±0.16% | 16.5K |
| 24 | 24 17 - 28 |
GPT 5.4 (High)
OpenAI · Proprietary
|
1.07%±1.29% | 1.87%±3.65% | 0.19%±3.92% | 3.31%±2.40% | 3.32%±1.24% | 0.37%±0.04% | 21.2K |
| 25 | 23 20 - 28 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
0.98%±0.95% | 11.75%±2.45% | 0.74%±2.76% | 0.99%±1.91% | 5.50%±0.92% | 0.37%±0.04% | 14.9K |
| 26 | 25 17 - 28 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
0.97%±1.35% | 0.25%±3.55% | 0.08%±4.07% | 1.86%±2.58% | 2.77%±1.26% | 0.37%±0.04% | 9.0K |
| 27 | 28 22 - 29 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
0.52%±1.08% | 7.67%±2.89% | 0.75%±3.36% | 1.29%±2.03% | 4.41%±0.96% | 0.13%±0.13% | 12.5K |
| 28 | 27 21 - 29 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.26%±1.45% | 1.84%±4.00% | 3.69%±4.65% | 0.25%±2.66% | 3.76%±1.18% | 0.34%±0.21% | 11.5K |
| 29 | 30 27 - 32 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.98%±1.54% | 2.35%±4.20% | 6.55%±4.41% | 9.07%±3.12% | 7.70%±1.58% | 0.37%±0.04% | 10.5K |
| 30 | 29 29 - 36 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
3.32%±1.79% | 9.85%±5.41% | 7.40%±4.75% | 4.92%±3.31% | 5.33%±2.34% | 0.24%±0.21% | 8.9K |
| 31 | 33 29 - 36 |
Hy3
腾讯 · Apache 2.0
|
3.46%±1.96% | 1.63%±4.83% | 3.50%±5.81% | 2.78%±3.73% | 6.15%±4.06% | 3.24%±1.12% | 8.8K |
| 32 | 32 29 - 36 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.95%±1.26% | 4.63%±3.80% | 10.47%±3.18% | 3.99%±2.23% | 0.54%±2.20% | 0.10%±0.23% | 12.7K |
| 33 | 31 30 - 36 |
Muse Spark 1.1
Meta · Proprietary
|
5.22%±0.85% | 3.15%±2.43% | 11.51%±2.11% | 8.55%±1.59% | 3.27%±1.46% | 0.37%±0.04% | 35.3K |
| 34 | 37 30 - 38 |
Minimax M3
MiniMax · MiniMax Community License
|
5.38%±1.37% | 10.61%±4.15% | 10.34%±3.67% | 8.03%±2.61% | 2.07%±1.16% | 0.00%±0.16% | 12.7K |
| 35 | 36 30 - 39 |
Mimo V2.5 Pro
小米 · MIT
|
5.75%±1.29% | 7.70%±3.94% | 10.16%±3.34% | 4.54%±2.33% | 5.53%±2.40% | 0.82%±0.36% | 13.0K |
| 36 | 35 30 - 41 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
6.65%±1.87% | 11.67%±5.51% | 12.22%±4.51% | 4.00%±3.40% | 4.79%±3.58% | 0.58%±0.37% | 7.0K |
| 37 | 38 34 - 41 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
7.58%±1.40% | 10.48%±4.07% | 2.89%±3.76% | 4.61%±2.29% | 19.71%±2.34% | 0.20%±0.72% | 22.9K |
| 38 | 34 35 - 41 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
8.37%±1.52% | 11.60%±4.62% | 10.62%±3.74% | 5.46%±2.84% | 14.47%±2.56% | 0.32%±0.08% | 6.8K |
| 39 | 39 34 - 41 |
Inkling Small
Thinky · Apache 2.0
|
8.55%±2.11% | 21.32%±7.54% | 21.64%±4.72% | 9.71%±4.71% | 10.54%±1.65% | 0.64%±0.60% | 3.8K |
| 40 | 40 36 - 41 |
Inkling
Thinky · Apache 2.0
|
9.43%±1.53% | 20.87%±5.40% | 22.09%±3.18% | 11.90%±3.30% | 7.53%±1.39% | 0.16%±0.13% | 13.0K |
| 41 | 41 36 - 41 |
Mistral Medium 3.5
Mistral · Modified MIT
|
10.48%±2.12% | 16.00%±6.26% | 14.47%±5.46% | 9.82%±4.49% | 9.99%±3.05% | 2.11%±1.03% | 3.1K |
| 42 | 42 42 - 43 |
Minimax M2.7
MiniMax · Modified MIT
|
14.86%±1.86% | 18.09%±5.60% | 18.85%±4.15% | 13.51%±3.77% | 24.14%±3.98% | 0.27%±0.13% | 11.9K |
| 43 | 43 42 - 43 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
17.42%±1.97% | 18.55%±6.31% | 21.28%±3.68% | 16.97%±3.71% | 28.28%±4.46% | 2.03%±1.32% | 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
智谱 ZAI
DeepSeek
Meta
SpaceXAI
阿里巴巴
MiniMax
小米
Google
Mistral