| 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 - 12 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
13.05%±4.99% | 22.00%±6.59% | 34.51%±19.06% | 2.59%±10.64% | 10.58%±3.21% | 0.75%±0.16% | 2.7K |
| 🥈 | 3 1 - 8 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
12.22%±3.69% | 18.16%±6.65% | 17.17%±14.28% | 11.52%±6.99% | 13.50%±1.94% | 0.74%±0.16% | 7.8K |
| 🥉 | 2 1 - 8 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
12.20%±3.52% | 10.05%±6.58% | 18.12%±13.77% | 17.62%±6.05% | 14.47%±1.82% | 0.75%±0.16% | 9.9K |
| 4 | 4 1 - 19 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
8.55%±2.91% | 11.30%±4.96% | 14.37%±9.67% | 8.22%±4.64% | 8.10%±7.94% | 0.75%±0.16% | 15.6K |
| 5 | 17 1 - 23 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
7.95%±3.65% | 12.71%±6.22% | 28.01%±13.09% | 7.27%±10.36% | 5.78%±2.49% | 0.50%±0.38% | 2.9K |
| 6 | 5 1 - 20 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
7.64%±2.79% | 9.01%±5.11% | 14.60%±10.52% | 2.91%±5.33% | 10.92%±1.54% | 0.75%±0.16% | 12.8K |
| 7 | 11 1 - 29 |
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
6.57%±2.72% | 7.90%±5.12% | 10.08%±10.27% | 3.57%±5.13% | 10.62%±2.63% | 0.69%±0.19% | 9.8K |
| 8 | 9 3 - 24 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
6.17%±2.17% | 3.37%±3.98% | 10.86%±7.82% | 4.63%±3.77% | 11.22%±3.87% | 0.75%±0.16% | 21.9K |
| 9 | 20 1 - 32 |
Claude Opus 4.6
Anthropic · Proprietary
|
5.91%±2.80% | 3.70%±5.48% | 8.18%±9.93% | 7.98%±4.91% | 8.95%±2.86% | 0.75%±0.16% | 9.8K |
| 10 | 6 3 - 33 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
5.49%±2.97% | 6.21%±5.12% | 7.22%±9.24% | 8.41%±4.78% | 5.54%±8.13% | 0.07%±0.94% | 14.4K |
| 11 | 13 4 - 31 |
Grok 4.5
SpaceXAI · Proprietary
|
5.34%±2.05% | 5.39%±4.19% | 4.03%±7.65% | 5.93%±3.97% | 10.61%±1.80% | 0.75%±0.16% | 15.4K |
| 12 | 14 3 - 33 |
Claude Opus 4.7
Anthropic · Proprietary
|
5.32%±2.77% | 4.00%±5.45% | 6.84%±9.90% | 6.91%±5.25% | 8.11%±3.05% | 0.75%±0.16% | 10.0K |
| 13 | 16 4 - 33 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
4.96%±2.06% | 10.42%±3.99% | 7.86%±7.62% | 1.85%±4.00% | 4.83%±2.47% | 0.18%±0.41% | 9.0K |
| 14 | 7 4 - 32 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
4.41%±1.23% | 14.52%±2.42% | 7.11%±4.38% | 5.72%±2.82% | 5.41%±1.23% | 0.75%±0.16% | 42.7K |
| 15 | 8 4 - 40 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
4.15%±3.47% | 0.16%±6.72% | 5.57%±11.65% | 8.00%±6.63% | 6.62%±6.36% | 0.73%±0.17% | 12.4K |
| 16 | 19 4 - 37 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
3.82%±2.34% | 9.57%±4.71% | 2.50%±8.43% | 0.90%±4.91% | 7.17%±1.94% | 0.75%±0.16% | 7.9K |
| 17 | 31 3 - 48 |
Kimi K2.7 Code
月之暗面 · Modified MIT
|
3.10%±4.96% | 6.58%±8.90% | 1.69%±19.32% | 7.67%±9.56% | 1.21%±5.44% | 0.75%±0.16% | 4.5K |
| 18 | 10 4 - 42 |
Hy4 preview
腾讯 · Apache 2.0
|
2.93%±2.86% | 8.45%±5.72% | 3.00%±10.72% | 3.37%±6.27% | 6.01%±1.64% | 0.56%±0.23% | 5.3K |
| 19 | 21 6 - 38 |
GPT 5.5
OpenAI · Proprietary
|
2.80%±1.70% | 1.75%±3.51% | 0.49%±6.03% | 0.87%±3.23% | 11.88%±2.03% | 0.75%±0.16% | 28.0K |
| 20 | 23 6 - 40 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
2.59%±1.96% | 12.99%±3.66% | 6.98%±7.08% | 4.09%±4.27% | 3.70%±2.36% | 0.75%±0.16% | 8.0K |
| 21 | 12 8 - 39 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
2.43%±1.45% | 3.67%±2.88% | 5.09%±4.93% | 0.03%±2.70% | 2.61%±2.43% | 0.75%±0.16% | 29.4K |
| 22 | 15 8 - 42 |
GPT 5.5 (High)
OpenAI · Proprietary
|
2.06%±1.89% | 2.09%±4.00% | 1.60%±6.93% | 0.96%±3.66% | 10.99%±1.94% | 0.75%±0.16% | 25.7K |
| 23 | 32 7 - 43 |
DeepSeek V4 Pro
DeepSeek · MIT
|
2.00%±2.19% | 0.74%±4.63% | 1.03%±7.83% | 1.13%±4.13% | 6.55%±1.92% | 0.54%±0.25% | 13.5K |
| 24 | 35 8 - 42 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
1.98%±1.94% | 12.35%±3.36% | 5.28%±6.85% | 8.59%±4.25% | 0.10%±2.91% | 0.75%±0.16% | 10.5K |
| 25 | 29 4 - 48 |
Claude Opus 4.8
Anthropic · Proprietary
|
1.91%±3.85% | 4.31%±5.75% | 11.20%±11.14% | 4.74%±5.34% | 11.09%±3.25% | 21.80%±12.21% | 13.7K |
| 26 | 33 6 - 46 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
1.82%±2.64% | 5.08%±5.59% | 3.51%±8.62% | 3.46%±4.80% | 6.47%±4.80% | 0.75%±0.16% | 10.8K |
| 27 | 18 9 - 42 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
1.68%±1.69% | 5.68%±3.47% | 1.47%±6.08% | 5.34%±3.70% | 5.83%±1.36% | 0.75%±0.16% | 13.5K |
| 28 | 25 8 - 46 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
1.60%±2.38% | 2.42%±4.88% | 0.51%±8.24% | 2.28%±4.60% | 7.91%±4.05% | 0.75%±0.16% | 7.8K |
| 29 | 34 8 - 46 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.54%±2.34% | 9.62%±4.56% | 0.02%±7.79% | 4.69%±5.11% | 2.00%±3.48% | 0.75%±0.16% | 8.7K |
| 30 | 28 9 - 46 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
1.25%±2.15% | 1.08%±4.35% | 0.37%±7.64% | 0.13%±4.25% | 7.09%±2.38% | 0.75%±0.16% | 8.4K |
| 31 | 42 12 - 46 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
0.79%±2.28% | 1.34%±4.69% | 3.49%±8.13% | 0.68%±4.42% | 2.13%±2.70% | 0.59%±0.36% | 7.7K |
| 32 | 47 10 - 48 |
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
0.68%±2.58% | 3.52%±5.79% | 2.63%±9.07% | 4.19%±4.94% | 4.69%±2.72% | 0.64%±0.22% | 5.9K |
| 33 | 37 15 - 46 |
Muse Spark 1.1
Meta · Proprietary
|
0.50%±1.25% | 11.86%±2.48% | 6.08%±4.14% | 5.78%±2.72% | 1.76%±2.58% | 0.74%±0.16% | 39.3K |
| 34 | 22 15 - 46 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
0.17%±1.34% | 6.84%±2.67% | 0.29%±4.41% | 4.55%±2.68% | 2.49%±2.48% | 0.75%±0.16% | 22.5K |
| 35 | 26 15 - 47 |
GPT 5.4 (High)
OpenAI · Proprietary
|
0.01%±1.71% | 1.83%±3.74% | 7.71%±5.89% | 1.25%±3.45% | 7.46%±2.34% | 0.75%±0.16% | 27.1K |
| 36 | 39 15 - 48 |
GLM 5.1
智谱 ZAI · MIT
|
0.13%±2.06% | 0.93%±3.56% | 6.81%±6.81% | 0.39%±3.41% | 6.09%±4.95% | 0.86%±0.71% | 26.5K |
| 37 | 24 16 - 47 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
0.16%±1.52% | 1.51%±3.09% | 1.20%±5.21% | 5.30%±3.47% | 1.04%±1.23% | 0.75%±0.16% | 23.7K |
| 38 | 36 5 - 55 |
Kimi K2.6
月之暗面 · Modified MIT
|
1.07%±6.37% | 10.04%±10.10% | 5.78%±17.76% | 6.69%±10.27% | 8.51%±21.94% | 0.75%±0.16% | 4.7K |
| 39 | 27 17 - 49 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
1.08%±2.11% | 8.36%±4.38% | 3.17%±7.22% | 5.81%±5.25% | 4.58%±1.75% | 0.20%±0.33% | 7.8K |
| 40 | 41 20 - 49 |
Gemini 3.5 Flash (High)
Google · Proprietary
|
1.27%±1.84% | 0.09%±3.28% | 1.72%±5.82% | 5.14%±3.13% | 3.33%±4.78% | 0.32%±0.22% | 36.4K |
| 41 | 38 20 - 51 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
2.01%±2.20% | 3.81%±4.15% | 4.42%±6.21% | 0.77%±3.51% | 1.28%±6.68% | 0.23%±0.48% | 15.3K |
| 42 | 43 25 - 51 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
2.13%±1.78% | 0.25%±3.53% | 3.38%±5.55% | 2.00%±2.93% | 16.52%±4.47% | 0.75%±0.16% | 31.0K |
| 43 | 45 24 - 53 |
Mimo V2.5 Pro
小米 · MIT
|
2.42%±2.31% | 4.27%±4.31% | 2.56%±7.19% | 1.91%±3.89% | 3.64%±6.05% | 0.28%±0.30% | 15.3K |
| 44 | 30 25 - 51 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
2.43%±1.88% | 3.14%±3.99% | 7.35%±6.30% | 1.58%±3.98% | 6.77%±1.94% | 0.42%±0.26% | 9.3K |
| 45 | 48 18 - 54 |
Inkling Small
Thinky · Apache 2.0
|
2.72%±3.44% | 14.88%±7.98% | 8.15%±12.08% | 4.15%±7.36% | 5.63%±2.88% | 0.33%±1.27% | 4.3K |
| 46 | 46 25 - 53 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
3.17%±2.49% | 3.35%±5.40% | 10.23%±7.95% | 4.54%±5.08% | 2.91%±4.67% | 0.65%±0.97% | 8.5K |
| 47 | 40 34 - 54 |
Hy3
腾讯 · Apache 2.0
|
4.11%±2.28% | 13.19%±5.17% | 5.55%±7.77% | 0.10%±4.35% | 0.13%±3.21% | 2.03%±1.19% | 10.2K |
| 48 | 53 32 - 55 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
4.46%±2.88% | 12.44%±5.89% | 1.01%±9.04% | 0.45%±5.23% | 8.43%±5.52% | 0.88%±1.99% | 9.5K |
| 49 | 44 40 - 54 |
Minimax M3
MiniMax · MiniMax Community License
|
5.11%±1.76% | 11.21%±4.31% | 13.66%±5.54% | 1.82%±3.44% | 0.84%±2.71% | 0.28%±0.43% | 15.7K |
| 50 | 56 40 - 55 |
Grok Build 0.1
SpaceXAI · Proprietary
|
5.61%±2.06% | 4.93%±3.89% | 4.16%±6.35% | 3.95%±4.14% | 15.06%±5.69% | 0.06%±0.18% | 30.3K |
| 51 | 50 43 - 56 |
Inkling
Thinky · Apache 2.0
|
6.48%±2.04% | 14.46%±5.28% | 20.22%±6.19% | 0.58%±4.50% | 2.60%±3.34% | 0.26%±0.42% | 15.9K |
| 52 | 49 43 - 57 |
Mistral Medium 3.5
Mistral · Modified MIT
|
7.61%±3.04% | 11.38%±6.22% | 18.70%±7.64% | 8.29%±6.09% | 13.45%±9.11% | 2.79%±2.53% | 3.6K |
| 53 | 55 45 - 57 |
Gemini 3 Flash
Google · Proprietary
|
8.39%±2.25% | 1.19%±3.18% | 2.25%±5.41% | 6.99%±2.94% | 28.99%±6.70% | 2.53%±5.41% | 29.9K |
| 54 | 51 38 - 57 |
Solar Pro 4
Upstage · Proprietary
|
9.15%±6.06% | 12.55%±12.40% | 14.72%±18.66% | 1.36%±12.09% | 17.01%±12.29% | 2.83%±6.53% | 2.4K |
| 55 | 52 51 - 57 |
Grok 4.3 (High)
SpaceXAI · Proprietary
|
10.83%±2.54% | 12.68%±3.80% | 8.07%±5.82% | 9.99%±3.29% | 23.76%±9.52% | 0.36%±0.19% | 26.7K |
| 56 | 57 48 - 58 |
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
11.31%±4.38% | 14.76%±8.43% | 10.61%±13.71% | 7.71%±8.74% | 23.19%±10.56% | 0.24%±0.68% | 4.8K |
| 57 | 54 52 - 57 |
Minimax M2.7
MiniMax · Modified MIT
|
11.61%±2.74% | 19.13%±4.89% | 17.10%±6.06% | 0.86%±4.21% | 21.56%±10.15% | 0.60%±0.20% | 15.3K |
| 58 | 59 57 - 59 |
Gemma 4 31B
Google · Apache 2.0
|
20.09%±4.68% | 2.16%±3.85% | 1.08%±5.26% | 12.21%±4.40% | 50.32%±18.77% | 34.70%±12.06% | 21.9K |
| 59 | 58 58 - 59 |
Grok 4.3
SpaceXAI · Proprietary
|
22.14%±4.99% | 8.31%±3.40% | 12.91%±5.43% | 6.82%±2.83% | 83.23%±23.88% | 0.58%±0.18% | 29.3K |
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
Google
OpenAI
SpaceXAI
阿里巴巴
月之暗面
腾讯
智谱 ZAI
DeepSeek
Meta
小米
MiniMax
Mistral
NVIDIA