| 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 Opus 5 (High)
Anthropic · Proprietary
|
12.86%±3.75% | 11.23%±6.73% | 21.54%±14.38% | 16.89%±6.22% | 13.81%±1.89% | 0.82%±0.18% | 9.5K |
| 🥈 | 2 1 - 12 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
11.59%±3.85% | 18.01%±6.89% | 18.53%±14.75% | 7.34%±7.48% | 13.28%±2.05% | 0.80%±0.18% | 7.4K |
| 🥉 | 15 1 - 23 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
8.31%±3.63% | 13.43%±6.23% | 28.04%±13.17% | 6.64%±10.03% | 6.15%±2.42% | 0.57%±0.40% | 2.9K |
| 4 | 4 1 - 20 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
8.09%±2.83% | 10.34%±5.16% | 15.84%±10.73% | 2.64%±5.42% | 10.83%±1.60% | 0.82%±0.18% | 12.4K |
| 5 | 3 1 - 21 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
7.99%±3.07% | 10.55%±5.19% | 14.31%±10.00% | 6.74%±4.86% | 7.54%±8.53% | 0.82%±0.18% | 15.1K |
| 6 | 9 1 - 26 |
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
6.90%±2.61% | 8.61%±4.88% | 10.30%±9.85% | 4.05%±5.03% | 10.76%±2.46% | 0.75%±0.21% | 9.8K |
| 7 | 19 2 - 28 |
Claude Opus 4.6
Anthropic · Proprietary
|
6.24%±2.67% | 4.58%±5.22% | 8.21%±9.47% | 8.34%±4.80% | 9.27%±2.64% | 0.82%±0.18% | 9.8K |
| 8 | 7 2 - 26 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
6.16%±2.19% | 3.71%±3.85% | 12.01%±7.69% | 3.56%±3.71% | 10.72%±4.42% | 0.82%±0.18% | 21.5K |
| 9 | 5 2 - 32 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
5.97%±3.04% | 6.30%±5.15% | 9.77%±9.60% | 6.87%±4.96% | 6.96%±7.59% | 0.05%±1.21% | 13.9K |
| 10 | 11 2 - 32 |
Claude Opus 4.7
Anthropic · Proprietary
|
5.71%±2.65% | 4.92%±5.18% | 7.02%±9.49% | 7.46%±5.10% | 8.32%±2.99% | 0.82%±0.18% | 10.0K |
| 11 | 12 3 - 29 |
Grok 4.5
SpaceXAI · Proprietary
|
5.37%±2.02% | 4.83%±4.19% | 3.79%±7.63% | 6.21%±3.88% | 11.22%±1.61% | 0.82%±0.18% | 15.0K |
| 12 | 6 3 - 28 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
4.62%±1.21% | 13.54%±2.40% | 8.50%±4.25% | 5.18%±2.75% | 5.43%±1.24% | 0.82%±0.18% | 41.7K |
| 13 | 8 2 - 40 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
4.43%±3.81% | 2.78%±7.18% | 10.25%±12.80% | 8.50%±6.97% | 5.39%±7.28% | 0.80%±0.18% | 12.0K |
| 14 | 18 3 - 32 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
4.38%±2.09% | 9.82%±4.14% | 5.04%±7.58% | 2.94%±4.08% | 4.30%±2.87% | 0.18%±0.49% | 8.2K |
| 15 | 17 3 - 37 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
3.50%±2.45% | 11.21%±5.04% | 0.05%±8.87% | 2.75%±5.36% | 8.29%±2.21% | 0.82%±0.18% | 6.9K |
| 16 | 31 3 - 37 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
3.48%±2.24% | 10.90%±4.27% | 3.95%±8.06% | 2.46%±4.97% | 4.21%±2.58% | 0.82%±0.18% | 7.7K |
| 17 | 10 4 - 33 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
3.48%±1.50% | 4.32%±2.92% | 7.44%±5.19% | 1.82%±2.79% | 3.01%±2.56% | 0.82%±0.18% | 28.1K |
| 18 | 20 5 - 36 |
GPT 5.5
OpenAI · Proprietary
|
3.18%±1.69% | 2.57%±3.40% | 2.01%±6.09% | 1.15%±3.23% | 11.66%±2.02% | 0.82%±0.18% | 27.6K |
| 19 | 29 2 - 47 |
Kimi K2.7 Code
月之暗面 · Modified MIT
|
3.17%±4.68% | 7.23%±8.40% | 1.02%±18.13% | 7.64%±9.29% | 0.84%±5.07% | 0.82%±0.18% | 4.5K |
| 20 | 13 3 - 44 |
Hy4 preview
腾讯 · Apache 2.0
|
3.06%±3.50% | 10.34%±6.83% | 5.27%±12.58% | 5.46%±8.29% | 4.72%±2.78% | 0.41%±0.41% | 3.3K |
| 21 | 14 6 - 40 |
GPT 5.5 (High)
OpenAI · Proprietary
|
2.57%±1.82% | 0.86%±3.80% | 1.91%±6.63% | 0.25%±3.55% | 11.21%±1.87% | 0.82%±0.18% | 25.7K |
| 22 | 34 6 - 40 |
DeepSeek V4 Pro
DeepSeek · MIT
|
2.52%±2.10% | 0.66%±4.40% | 4.14%±7.58% | 3.07%±3.90% | 5.49%±2.03% | 0.57%±0.29% | 13.2K |
| 23 | 33 6 - 40 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
2.44%±1.91% | 12.99%±3.31% | 5.30%±6.82% | 7.68%±4.15% | 0.77%±2.79% | 0.82%±0.18% | 10.5K |
| 24 | 32 5 - 41 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
2.37%±2.45% | 3.75%±5.52% | 2.00%±8.38% | 4.34%±4.89% | 8.45%±2.55% | 0.82%±0.18% | 10.5K |
| 25 | 27 3 - 46 |
Claude Opus 4.8
Anthropic · Proprietary
|
2.31%±3.66% | 5.18%±5.46% | 11.13%±10.60% | 5.56%±5.19% | 11.36%±2.92% | 21.69%±11.55% | 13.7K |
| 26 | 21 8 - 45 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
1.34%±2.30% | 11.66%±4.52% | 1.38%±8.20% | 4.16%±5.39% | 2.98%±2.58% | 0.82%±0.18% | 5.1K |
| 27 | 16 11 - 45 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
1.30%±1.92% | 7.07%±3.85% | 2.29%±6.65% | 5.71%±4.42% | 6.60%±1.57% | 0.82%±0.18% | 10.6K |
| 28 | 46 8 - 47 |
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
1.07%±2.51% | 2.99%±5.64% | 3.00%±8.79% | 5.13%±4.90% | 5.47%±2.52% | 0.72%±0.22% | 5.9K |
| 29 | 42 10 - 46 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
1.06%±2.35% | 1.35%±4.74% | 5.19%±8.52% | 0.07%±4.48% | 2.11%±2.90% | 0.82%±0.18% | 7.3K |
| 30 | 28 11 - 46 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
0.98%±2.24% | 0.92%±4.60% | 2.25%±7.83% | 0.23%±4.60% | 7.02%±2.56% | 0.82%±0.18% | 7.4K |
| 31 | 23 11 - 47 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.76%±2.36% | 3.89%±4.93% | 4.04%±7.88% | 3.89%±4.61% | 7.03%±4.71% | 0.82%±0.18% | 7.4K |
| 32 | 39 14 - 47 |
GLM 5.1
智谱 ZAI · MIT
|
0.31%±1.92% | 0.32%±3.38% | 6.67%±6.40% | 0.95%±3.29% | 5.02%±4.33% | 0.72%±0.70% | 26.5K |
| 33 | 36 15 - 45 |
Muse Spark 1.1
Meta · Proprietary
|
0.31%±1.26% | 11.23%±2.48% | 5.54%±4.11% | 6.42%±2.78% | 1.45%±2.65% | 0.81%±0.18% | 37.9K |
| 34 | 24 15 - 46 |
GPT 5.4 (High)
OpenAI · Proprietary
|
0.27%±1.68% | 0.15%±3.61% | 7.55%±5.75% | 1.17%±3.38% | 7.04%±2.55% | 0.82%±0.18% | 26.6K |
| 35 | 22 15 - 47 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
0.10%±1.54% | 6.65%±2.96% | 0.35%±4.93% | 4.83%±3.03% | 1.76%±2.91% | 0.82%±0.18% | 18.4K |
| 36 | 35 3 - 53 |
Kimi K2.6
月之暗面 · Modified MIT
|
0.43%±5.90% | 8.28%±9.53% | 5.66%±16.93% | 7.18%±9.99% | 7.51%±19.61% | 0.82%±0.18% | 4.7K |
| 37 | 25 18 - 47 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
0.61%±1.55% | 0.33%±3.17% | 0.54%±5.30% | 5.07%±3.52% | 1.01%±1.27% | 0.82%±0.18% | 22.1K |
| 38 | 41 18 - 47 |
Gemini 3.5 Flash (High)
Google · Proprietary
|
0.79%±1.68% | 0.89%±3.06% | 1.85%±5.36% | 4.65%±2.99% | 2.44%±4.17% | 0.38%±0.23% | 36.4K |
| 39 | 26 16 - 50 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
1.42%±2.70% | 8.06%±5.77% | 7.52%±9.13% | 3.72%±7.02% | 3.77%±2.17% | 0.14%±0.44% | 4.5K |
| 40 | 43 23 - 50 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
2.01%±1.69% | 0.15%±3.33% | 4.38%±5.26% | 1.20%±2.79% | 16.28%±4.18% | 0.82%±0.18% | 30.6K |
| 41 | 37 22 - 50 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
2.10%±2.07% | 5.01%±4.11% | 4.07%±6.16% | 0.78%±3.46% | 0.92%±5.71% | 0.28%±0.55% | 15.0K |
| 42 | 30 23 - 51 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
2.37%±2.15% | 3.27%±4.55% | 7.41%±7.20% | 2.72%±4.46% | 5.41%±2.15% | 0.44%±0.31% | 7.2K |
| 43 | 38 24 - 52 |
Hy3
腾讯 · Apache 2.0
|
2.77%±2.32% | 11.61%±5.12% | 2.32%±8.18% | 0.44%±4.33% | 1.91%±3.14% | 1.37%±1.13% | 9.7K |
| 44 | 47 18 - 53 |
Inkling Small
Thinky · Apache 2.0
|
2.78%±3.57% | 11.22%±8.03% | 9.23%±12.46% | 0.71%±8.12% | 5.62%±3.08% | 0.23%±0.62% | 4.0K |
| 45 | 40 23 - 52 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
2.88%±2.48% | 3.22%±5.48% | 11.45%±7.92% | 3.10%±5.11% | 3.78%±4.25% | 0.41%±0.97% | 8.2K |
| 46 | 45 27 - 53 |
Mimo V2.5 Pro
小米 · MIT
|
3.62%±2.38% | 6.45%±4.31% | 4.37%±6.94% | 2.69%±3.83% | 4.87%±6.91% | 0.26%±0.35% | 14.8K |
| 47 | 53 31 - 54 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
4.27%±2.84% | 12.30%±5.76% | 1.28%±8.89% | 1.44%±5.23% | 8.09%±5.48% | 1.11%±2.37% | 9.3K |
| 48 | 44 38 - 53 |
Minimax M3
MiniMax · MiniMax Community License
|
4.92%±1.72% | 10.20%±4.19% | 14.48%±5.29% | 1.51%±3.41% | 1.24%±2.75% | 0.32%±0.44% | 15.3K |
| 49 | 55 38 - 54 |
Grok Build 0.1
SpaceXAI · Proprietary
|
5.00%±1.92% | 3.97%±3.63% | 4.04%±5.99% | 3.47%±3.95% | 13.60%±5.01% | 0.09%±0.20% | 30.3K |
| 50 | 49 41 - 56 |
Inkling
Thinky · Apache 2.0
|
6.25%±2.02% | 12.39%±5.09% | 19.32%±6.21% | 3.01%±4.42% | 3.20%±3.34% | 0.28%±0.44% | 15.5K |
| 51 | 54 44 - 56 |
Gemini 3 Flash
Google · Proprietary
|
7.83%±2.09% | 0.57%±2.98% | 2.29%±5.07% | 6.51%±2.84% | 27.67%±6.27% | 2.13%±4.73% | 29.9K |
| 52 | 48 42 - 56 |
Mistral Medium 3.5
Mistral · Modified MIT
|
7.95%±3.43% | 11.75%±6.49% | 17.87%±8.04% | 6.20%±6.50% | 13.22%±11.12% | 3.09%±3.03% | 3.2K |
| 53 | 50 38 - 56 |
Solar Pro 4
Upstage · Proprietary
|
8.85%±5.76% | 11.60%±11.81% | 15.12%±17.50% | 1.60%±11.58% | 16.11%±11.48% | 3.03%±7.01% | 2.4K |
| 54 | 51 50 - 56 |
Minimax M2.7
MiniMax · Modified MIT
|
10.34%±2.44% | 17.32%±4.75% | 15.29%±6.22% | 0.81%±4.13% | 18.93%±7.85% | 0.65%±0.22% | 14.9K |
| 55 | 52 50 - 56 |
Grok 4.3 (High)
SpaceXAI · Proprietary
|
10.37%±2.44% | 11.61%±3.59% | 8.39%±5.37% | 9.29%±3.16% | 22.98%±9.29% | 0.41%±0.21% | 26.7K |
| 56 | 56 48 - 57 |
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
10.91%±4.19% | 14.99%±8.25% | 10.73%±13.11% | 6.96%±8.60% | 21.61%±9.93% | 0.24%±0.73% | 4.8K |
| 57 | 58 56 - 58 |
Gemma 4 31B
Google · Apache 2.0
|
19.33%±4.55% | 1.16%±3.57% | 0.76%±5.21% | 11.88%±4.13% | 48.52%±18.31% | 34.31%±11.80% | 21.9K |
| 58 | 57 57 - 58 |
Grok 4.3
SpaceXAI · Proprietary
|
21.01%±4.50% | 7.59%±3.21% | 12.97%±5.07% | 6.48%±2.73% | 78.66%±21.43% | 0.64%±0.20% | 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
月之暗面
阿里巴巴
Meta
智谱 ZAI
腾讯
DeepSeek
小米
MiniMax
Mistral
NVIDIA