| 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
|
14.21%±2.35% | 19.80%±5.43% | 19.97%±8.57% | 16.35%±4.28% | 14.44%±1.15% | 0.48%±0.15% | 6.9K |
| 🥈 | 2 1 - 7 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
13.12%±2.74% | 17.10%±6.23% | 18.53%±9.75% | 14.02%±5.04% | 15.40%±1.06% | 0.56%±0.14% | 5.3K |
| 🥉 | 3 1 - 8 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
11.99%±2.12% | 6.68%±5.59% | 22.54%±7.35% | 17.85%±3.60% | 12.30%±1.77% | 0.60%±0.14% | 10.5K |
| 4 | 4 1 - 13 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
10.96%±2.17% | 6.96%±5.35% | 27.16%±7.74% | 12.56%±3.69% | 7.53%±1.42% | 0.60%±0.14% | 8.8K |
| 5 | 5 1 - 13 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
10.91%±2.14% | 5.81%±5.02% | 23.05%±7.24% | 16.14%±3.75% | 9.07%±2.42% | 0.46%±0.17% | 11.4K |
| 6 | 6 2 - 9 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
10.17%±0.90% | 17.85%±2.09% | 18.82%±2.96% | 5.74%±1.58% | 7.85%±0.69% | 0.60%±0.14% | 31.7K |
| 7 | 8 1 - 21 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
9.53%±3.07% | 10.98%±6.86% | 13.72%±10.49% | 11.48%±6.58% | 11.06%±1.55% | 0.43%±0.16% | 8.6K |
| 8 | 16 3 - 17 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
8.90%±1.47% | 17.36%±3.37% | 12.26%±4.82% | 5.41%±3.00% | 8.88%±1.21% | 0.60%±0.14% | 9.0K |
| 9 | 14 5 - 22 |
GPT 5.5 (High)
OpenAI · Proprietary
|
7.73%±1.43% | 4.67%±3.48% | 13.16%±4.68% | 9.96%±2.36% | 10.24%±2.32% | 0.60%±0.14% | 19.2K |
| 10 | 10 7 - 21 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
7.60%±1.03% | 12.32%±2.57% | 13.38%±3.46% | 7.18%±1.78% | 4.52%±0.99% | 0.60%±0.14% | 21.2K |
| 11 | 7 5 - 24 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
7.53%±1.51% | 1.70%±3.93% | 12.35%±4.81% | 10.36%±2.52% | 12.65%±1.90% | 0.60%±0.14% | 15.5K |
| 12 | 9 5 - 26 |
Claude Opus 4.7 (High)
Anthropic · Proprietary
|
7.08%±1.99% | 1.55%±5.24% | 11.78%±6.18% | 9.65%±3.56% | 11.89%±2.34% | 0.56%±0.14% | 7.8K |
| 13 | 13 4 - 29 |
Hy4 preview
腾讯 · Apache 2.0
|
6.86%±2.57% | 17.63%±6.16% | 7.02%±8.57% | 2.86%±5.59% | 11.98%±1.18% | 0.52%±0.16% | 2.9K |
| 14 | 17 7 - 26 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
6.86%±1.76% | 11.78%±4.48% | 5.89%±5.54% | 6.74%±3.36% | 9.26%±1.37% | 0.60%±0.14% | 5.7K |
| 15 | 12 7 - 26 |
Grok 4.5
SpaceXAI · Proprietary
|
6.61%±1.60% | 10.17%±4.03% | 4.07%±5.31% | 8.64%±3.03% | 9.58%±1.54% | 0.60%±0.14% | 11.3K |
| 16 | 11 7 - 29 |
Claude Opus 4.7
Anthropic · Proprietary
|
6.47%±2.00% | 2.82%±5.28% | 11.99%±6.28% | 7.87%±3.66% | 9.16%±2.26% | 0.50%±0.16% | 8.1K |
| 17 | 27 5 - 31 |
Claude Opus 4.8
Anthropic · Proprietary
|
5.83%±2.99% | 7.47%±5.28% | 10.61%±6.75% | 11.31%±4.16% | 9.45%±2.42% | 9.69%±10.30% | 10.8K |
| 18 | 20 8 - 29 |
GPT 5.5
OpenAI · Proprietary
|
5.54%±1.20% | 3.24%±3.19% | 6.64%±3.77% | 8.73%±2.08% | 8.50%±1.48% | 0.60%±0.14% | 20.9K |
| 19 | 23 8 - 29 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
5.47%±1.61% | 4.35%±4.64% | 1.90%±4.86% | 12.78%±2.98% | 7.72%±1.52% | 0.60%±0.14% | 5.5K |
| 20 | 18 8 - 29 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
5.30%±1.51% | 9.32%±4.05% | 4.79%±4.68% | 5.11%±2.86% | 7.44%±1.22% | 0.17%±0.32% | 6.2K |
| 21 | 22 11 - 29 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
5.10%±1.04% | 14.11%±2.74% | 7.04%±3.19% | 3.42%±1.90% | 0.34%±1.12% | 0.60%±0.14% | 15.8K |
| 22 | 21 10 - 31 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
4.72%±1.58% | 16.08%±4.15% | 4.43%±4.73% | 3.65%±3.26% | 1.14%±1.45% | 0.60%±0.14% | 4.4K |
| 23 | 26 8 - 31 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
4.38%±2.36% | 11.94%±5.78% | 2.33%±7.68% | 2.73%±4.95% | 5.66%±1.06% | 0.76%±0.33% | 3.8K |
| 24 | 25 12 - 30 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
4.35%±1.02% | 11.72%±2.75% | 3.85%±3.13% | 1.83%±1.97% | 3.78%±0.91% | 0.59%±0.14% | 16.8K |
| 25 | 19 12 - 31 |
Claude Opus 4.6
Anthropic · Proprietary
|
3.90%±1.85% | 2.57%±4.93% | 3.13%±5.66% | 3.59%±3.38% | 9.61%±2.26% | 0.60%±0.14% | 7.9K |
| 26 | 24 15 - 31 |
GPT 5.4 (High)
OpenAI · Proprietary
|
3.68%±1.24% | 1.80%±3.47% | 2.67%±3.82% | 6.24%±2.26% | 7.11%±1.21% | 0.60%±0.14% | 20.3K |
| 27 | 15 11 - 32 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
3.55%±2.72% | 5.99%±8.25% | 4.89%±7.40% | 1.57%±5.32% | 4.78%±1.67% | 0.50%±0.19% | 2.0K |
| 28 | 28 15 - 31 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
3.12%±1.68% | 1.85%±4.58% | 2.41%±5.07% | 3.68%±3.21% | 7.03%±1.87% | 0.60%±0.14% | 5.7K |
| 29 | 30 21 - 33 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
2.08%±1.49% | 7.20%±4.07% | 3.01%±4.58% | 0.79%±2.80% | 0.64%±1.34% | 0.04%±0.24% | 6.4K |
| 30 | 35 15 - 43 |
Kimi K2.6
月之暗面 · Modified MIT
|
0.74%±4.03% | 1.09%±9.68% | 8.44%±12.63% | 7.27%±7.84% | 11.54%±7.02% | 0.60%±0.14% | 3.5K |
| 31 | 29 22 - 43 |
Kimi K2.7 Code
月之暗面 · Modified MIT
|
0.18%±3.37% | 3.01%±9.20% | 5.55%±9.67% | 3.35%±7.91% | 2.33%±4.06% | 0.60%±0.14% | 3.5K |
| 32 | 33 30 - 40 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
0.62%±1.15% | 6.79%±3.46% | 4.55%±3.12% | 5.22%±2.24% | 0.62%±1.45% | 0.49%±0.16% | 8.5K |
| 33 | 38 28 - 42 |
Hy3
腾讯 · Apache 2.0
|
0.72%±2.05% | 3.03%±4.79% | 1.25%±6.16% | 1.93%±3.77% | 3.96%±4.60% | 2.01%±0.98% | 7.7K |
| 34 | 34 30 - 41 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.88%±1.38% | 2.14%±4.18% | 4.20%±3.94% | 2.21%±2.40% | 4.83%±1.24% | 0.69%±0.36% | 10.1K |
| 35 | 32 29 - 41 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
0.90%±1.70% | 5.79%±5.13% | 5.61%±4.56% | 3.62%±3.30% | 10.09%±2.32% | 0.40%±0.34% | 8.6K |
| 36 | 31 30 - 41 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.20%±1.51% | 0.58%±4.77% | 10.09%±3.62% | 6.15%±2.96% | 10.24%±2.16% | 0.60%±0.14% | 6.5K |
| 37 | 37 30 - 41 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
1.23%±1.17% | 1.41%±3.46% | 8.63%±3.12% | 2.75%±2.13% | 3.88%±1.99% | 0.07%±0.35% | 11.7K |
| 38 | 36 30 - 43 |
Muse Spark 1.1
Meta · Proprietary
|
2.35%±0.90% | 0.06%±2.58% | 8.21%±2.21% | 6.28%±1.64% | 2.23%±1.51% | 0.59%±0.14% | 29.5K |
| 39 | 39 30 - 44 |
GLM 5.1
智谱 ZAI · MIT
|
2.41%±1.28% | 1.53%±3.41% | 4.18%±3.01% | 1.63%±2.42% | 5.76%±3.04% | 2.00%±0.63% | 19.8K |
| 40 | 45 30 - 47 |
Mimo V2.5 Pro
小米 · MIT
|
2.85%±1.27% | 2.41%±3.68% | 7.36%±3.34% | 2.20%±2.22% | 1.81%±2.47% | 0.48%±0.39% | 11.8K |
| 41 | 40 31 - 49 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
3.60%±1.76% | 5.38%±5.55% | 11.93%±4.30% | 2.32%±3.55% | 2.09%±2.59% | 0.45%±0.43% | 6.3K |
| 42 | 44 35 - 49 |
Minimax M3
MiniMax · MiniMax Community License
|
4.04%±1.32% | 9.18%±4.13% | 8.92%±3.39% | 7.39%±2.51% | 5.15%±1.13% | 0.15%±0.24% | 11.6K |
| 43 | 43 40 - 50 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
5.39%±1.32% | 7.00%±3.72% | 0.14%±3.52% | 4.61%±2.07% | 15.29%±2.35% | 0.07%±0.65% | 22.0K |
| 44 | 41 41 - 50 |
Gemini 3.5 Flash (High)
Google · Proprietary
|
5.63%±1.15% | 7.33%±3.35% | 3.76%±2.87% | 9.83%±1.93% | 6.66%±2.37% | 0.57%±0.26% | 26.6K |
| 45 | 42 41 - 50 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
6.04%±1.56% | 4.72%±4.68% | 9.94%±3.85% | 7.25%±2.94% | 8.83%±2.52% | 0.52%±0.16% | 5.7K |
| 46 | 47 39 - 50 |
Inkling Small
Thinky · Apache 2.0
|
6.12%±2.46% | 19.97%±8.78% | 19.77%±5.41% | 4.78%±5.94% | 14.34%±1.94% | 0.41%±0.67% | 3.1K |
| 47 | 46 40 - 50 |
Gemini 3.5 Flash (Medium)
Google · Proprietary
|
6.17%±2.10% | 9.00%±5.90% | 6.01%±5.21% | 7.26%±3.82% | 7.84%±3.77% | 0.76%±2.18% | 4.4K |
| 48 | 48 40 - 50 |
Mistral Medium 3.5
Mistral · Modified MIT
|
6.22%±2.39% | 10.33%±6.88% | 10.87%±6.43% | 7.58%±5.26% | 0.79%±3.08% | 1.55%±1.12% | 2.4K |
| 49 | 49 43 - 50 |
Inkling
Thinky · Apache 2.0
|
7.43%±1.62% | 17.16%±5.33% | 16.43%±3.78% | 14.61%±3.30% | 10.78%±1.48% | 0.25%±0.23% | 12.2K |
| 50 | 50 36 - 54 |
Solar Pro 4
Upstage · Proprietary
|
7.72%±4.73% | 7.11%±11.63% | 8.81%±12.78% | 0.51%±9.47% | 22.14%±10.10% | 1.03%±1.98% | 2.0K |
| 51 | 51 50 - 55 |
Minimax M2.7
MiniMax · Modified MIT
|
11.17%±1.77% | 12.68%±5.13% | 15.89%±4.07% | 10.72%±3.60% | 17.00%±3.65% | 0.46%±0.22% | 11.3K |
| 52 | 52 50 - 56 |
Grok 4.3 (High)
SpaceXAI · Proprietary
|
13.65%±1.79% | 19.69%±3.95% | 14.84%±2.94% | 12.36%±2.13% | 21.91%±6.97% | 0.56%±0.14% | 19.7K |
| 53 | 53 50 - 56 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
13.87%±1.83% | 14.06%±5.88% | 17.77%±3.58% | 16.21%±3.69% | 20.15%±3.85% | 1.17%±0.91% | 7.1K |
| 54 | 55 51 - 56 |
Grok Build 0.1
SpaceXAI · Proprietary
|
14.40%±1.88% | 12.55%±4.06% | 12.71%±3.42% | 7.09%±3.16% | 40.13%±6.67% | 0.50%±0.14% | 22.1K |
| 55 | 54 52 - 56 |
Gemini 3 Flash
Google · Proprietary
|
14.73%±1.49% | 16.77%±3.60% | 13.28%±2.44% | 12.08%±2.06% | 31.59%±5.37% | 0.08%±0.71% | 22.2K |
| 56 | 56 50 - 57 |
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
16.04%±3.89% | 25.48%±10.83% | 14.41%±8.94% | 13.31%±7.49% | 27.27%±10.19% | 0.27%±0.28% | 3.4K |
| 57 | 57 56 - 58 |
Grok 4.3
SpaceXAI · Proprietary
|
19.95%±2.72% | 17.82%±3.62% | 16.79%±2.16% | 14.33%±2.16% | 51.40%±12.76% | 0.58%±0.14% | 22.5K |
| 58 | 58 57 - 58 |
Gemma 4 31B
Google · Apache 2.0
|
25.67%±3.79% | 10.74%±3.68% | 8.66%±2.69% | 10.98%±2.80% | 61.85%±13.85% | 36.14%±11.26% | 15.5K |
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
DeepSeek
智谱 ZAI
腾讯
SpaceXAI
阿里巴巴
Google
Meta
小米
MiniMax
Mistral
NVIDIA