| 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
|
15.07%±2.46% | 22.65%±3.40% | 38.98%±10.11% | 1.74%±5.74% | 11.58%±0.95% | 0.38%±0.06% | 7.6K |
| 🥈 | 4 2 - 7 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
10.63%±1.96% | 9.98%±4.03% | 20.44%±7.20% | 10.85%±3.85% | 11.51%±1.13% | 0.34%±0.05% | 14.3K |
| 🥉 | 3 1 - 7 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.58%±2.16% | 10.07%±4.40% | 20.13%±7.89% | 9.08%±4.16% | 13.24%±0.81% | 0.37%±0.05% | 11.1K |
| 4 | 2 1 - 10 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
10.06%±3.38% | 18.37%±4.99% | 27.78%±12.15% | 2.70%±8.48% | 6.47%±1.33% | 0.39%±0.05% | 5.9K |
| 5 | 5 2 - 8 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
9.32%±1.62% | 6.26%±3.61% | 18.33%±5.85% | 12.90%±2.99% | 8.71%±1.54% | 0.39%±0.05% | 21.2K |
| 6 | 7 2 - 10 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
8.30%±1.68% | 5.22%±3.50% | 21.08%±6.13% | 10.32%±3.17% | 4.46%±1.03% | 0.39%±0.05% | 17.7K |
| 7 | 6 2 - 11 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
8.15%±1.68% | 1.48%±3.58% | 19.52%±5.94% | 12.62%±3.03% | 6.98%±1.74% | 0.17%±0.30% | 22.1K |
| 8 | 8 5 - 14 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
6.52%±0.81% | 13.00%±1.64% | 13.34%±2.84% | 1.59%±1.59% | 4.30%±0.59% | 0.39%±0.05% | 62.1K |
| 9 | 9 4 - 18 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
6.09%±2.13% | 3.29%±4.43% | 11.72%±7.45% | 7.41%±4.60% | 7.74%±1.20% | 0.27%±0.09% | 17.5K |
| 10 | 10 5 - 17 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
5.49%±1.25% | 1.07%±2.90% | 8.00%±4.31% | 8.49%±2.40% | 9.48%±1.28% | 0.39%±0.05% | 30.7K |
| 11 | 13 8 - 17 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.32%±0.85% | 9.48%±1.79% | 12.03%±3.06% | 3.47%±1.53% | 1.24%±0.71% | 0.39%±0.05% | 44.6K |
| 12 | 11 8 - 19 |
Hy4 preview
腾讯 · Apache 2.0
|
5.06%±1.36% | 11.06%±2.59% | 10.27%±5.07% | 3.43%±2.82% | 7.16%±0.69% | 0.23%±0.09% | 17.2K |
| 13 | 15 8 - 18 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
4.78%±0.99% | 9.59%±2.02% | 8.42%±3.58% | 0.44%±2.04% | 5.08%±0.74% | 0.38%±0.05% | 27.8K |
| 14 | 12 7 - 23 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
4.45%±2.13% | 9.92%±4.75% | 5.92%±7.16% | 1.22%±5.28% | 7.35%±1.17% | 0.28%±0.10% | 5.3K |
| 15 | 17 9 - 23 |
Grok 4.5
SpaceXAI · Proprietary
|
4.15%±1.33% | 5.00%±2.96% | 3.33%±4.57% | 7.11%±2.61% | 4.93%±1.63% | 0.39%±0.05% | 22.6K |
| 16 | 14 9 - 23 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
3.74%±1.20% | 8.48%±2.62% | 4.18%±4.00% | 0.50%±2.58% | 5.13%±1.04% | 0.39%±0.05% | 14.7K |
| 17 | 19 9 - 23 |
GPT 5.5
OpenAI · Proprietary
|
3.61%±1.10% | 0.70%±2.52% | 5.84%±3.67% | 5.65%±1.99% | 5.47%±1.54% | 0.39%±0.05% | 40.6K |
| 18 | 16 11 - 24 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.13%±1.10% | 7.25%±2.40% | 5.05%±3.76% | 1.40%±2.16% | 3.45%±0.98% | 1.49%±0.48% | 17.0K |
| 19 | 18 13 - 23 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
3.01%±0.74% | 10.59%±1.65% | 6.17%±2.53% | 0.08%±1.38% | 2.17%±0.69% | 0.39%±0.05% | 44.7K |
| 20 | 21 14 - 25 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
2.80%±0.87% | 8.27%±1.93% | 4.55%±3.01% | 0.66%±1.76% | 1.46%±0.68% | 0.37%±0.05% | 36.6K |
| 21 | 22 14 - 28 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
2.12%±1.39% | 2.89%±3.40% | 2.34%±4.65% | 8.14%±2.71% | 2.60%±1.54% | 0.39%±0.05% | 11.5K |
| 22 | 24 14 - 28 |
GPT 5.4 (High)
OpenAI · Proprietary
|
1.76%±1.09% | 1.16%±2.67% | 1.53%±3.67% | 3.77%±2.14% | 4.25%±1.03% | 0.39%±0.05% | 39.3K |
| 23 | 20 14 - 28 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
1.73%±1.32% | 1.53%±3.31% | 1.44%±4.30% | 3.01%±2.56% | 5.34%±1.10% | 0.39%±0.05% | 13.8K |
| 24 | 23 19 - 28 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
1.24%±0.84% | 10.44%±1.88% | 1.57%±2.69% | 1.16%±1.76% | 5.05%±0.79% | 0.39%±0.05% | 25.1K |
| 25 | 27 20 - 29 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.68%±1.30% | 1.39%±3.15% | 1.20%±4.52% | 0.42%±2.43% | 3.86%±0.97% | 0.22%±0.16% | 20.6K |
| 26 | 25 21 - 29 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
0.65%±1.13% | 0.04%±2.64% | 1.22%±3.65% | 1.71%±2.35% | 2.30%±1.23% | 0.39%±0.05% | 15.5K |
| 27 | 26 21 - 29 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
0.58%±1.02% | 10.72%±2.09% | 1.17%±3.48% | 4.52%±2.30% | 1.23%±0.60% | 0.90%±0.14% | 28.3K |
| 28 | 28 21 - 29 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
0.08%±0.93% | 6.17%±2.19% | 0.51%±3.10% | 1.86%±1.86% | 5.08%±0.86% | 0.11%±0.13% | 20.9K |
| 29 | 29 25 - 32 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
1.83%±1.53% | 6.41%±4.01% | 5.63%±4.57% | 2.63%±3.00% | 5.20%±1.98% | 0.29%±0.18% | 16.1K |
| 30 | 30 29 - 33 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
2.70%±1.28% | 2.17%±3.18% | 8.87%±3.96% | 8.28%±2.81% | 5.44%±1.41% | 0.39%±0.05% | 18.1K |
| 31 | 32 29 - 36 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.61%±1.17% | 5.30%±2.95% | 8.15%±3.28% | 3.44%±2.06% | 1.02%±2.31% | 0.14%±0.23% | 22.8K |
| 32 | 31 30 - 37 |
Muse Spark 1.1
Meta · Proprietary
|
4.50%±0.70% | 0.72%±1.76% | 12.26%±1.93% | 7.54%±1.41% | 2.38%±1.25% | 0.39%±0.05% | 62.6K |
| 33 | 33 29 - 38 |
Hy3
腾讯 · Apache 2.0
|
4.70%±1.61% | 5.38%±3.65% | 6.40%±4.83% | 3.00%±3.25% | 4.98%±2.91% | 3.74%±2.00% | 15.9K |
| 34 | 36 31 - 38 |
Mimo V2.5 Pro
小米 · MIT
|
5.61%±1.10% | 6.59%±3.00% | 11.25%±3.16% | 3.79%±2.11% | 5.74%±2.04% | 0.70%±0.32% | 23.2K |
| 35 | 37 31 - 38 |
Minimax M3
MiniMax · MiniMax Community License
|
5.75%±1.13% | 10.84%±3.18% | 11.87%±3.32% | 7.72%±2.30% | 1.60%±1.16% | 0.09%±0.13% | 22.6K |
| 36 | 35 31 - 39 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
6.03%±1.53% | 9.08%±4.05% | 12.13%±4.16% | 4.54%±3.02% | 3.39%±2.71% | 1.03%±0.51% | 12.5K |
| 37 | 34 32 - 39 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
6.42%±1.28% | 7.44%±3.41% | 9.60%±3.63% | 3.19%±2.55% | 12.24%±1.99% | 0.36%±0.07% | 12.0K |
| 38 | 38 33 - 39 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
6.66%±1.17% | 7.64%±2.95% | 2.57%±3.44% | 3.56%±2.01% | 19.45%±1.99% | 0.09%±0.49% | 42.9K |
| 39 | 39 36 - 41 |
Inkling Small
Thinky · Apache 2.0
|
9.20%±1.78% | 20.86%±5.54% | 21.49%±4.66% | 11.01%±4.14% | 7.99%±1.35% | 0.63%±0.56% | 7.0K |
| 40 | 40 39 - 41 |
Inkling
Thinky · Apache 2.0
|
9.95%±1.26% | 19.65%±4.03% | 24.03%±3.00% | 10.90%±2.89% | 4.67%±1.45% | 0.13%±0.16% | 23.3K |
| 41 | 41 39 - 42 |
Mistral Medium 3.5
Mistral · Modified MIT
|
10.96%±1.75% | 18.74%±4.67% | 14.52%±4.84% | 7.55%±3.88% | 12.22%±2.56% | 1.78%±0.80% | 5.7K |
| 42 | 42 41 - 43 |
Minimax M2.7
MiniMax · Modified MIT
|
13.29%±1.42% | 12.93%±3.80% | 22.60%±3.39% | 7.58%±3.24% | 23.56%±3.04% | 0.23%±0.16% | 22.2K |
| 43 | 43 42 - 43 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
15.40%±1.66% | 15.72%±4.66% | 21.77%±3.63% | 12.85%±3.46% | 24.91%±3.76% | 1.73%±0.96% | 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
SpaceXAI
Meta
阿里巴巴
小米
MiniMax
Google
Mistral