| 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 - 7 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
11.62%±2.99% | 21.78%±4.67% | 21.06%±11.99% | 3.21%±6.31% | 11.78%±1.65% | 0.28%±0.04% | 5.6K |
| 🥈 | 4 1 - 7 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
11.30%±2.98% | 16.08%±5.25% | 19.06%±11.76% | 8.89%±5.92% | 12.19%±2.06% | 0.26%±0.05% | 8.5K |
| 🥉 | 2 1 - 9 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
9.81%±3.67% | 21.04%±5.64% | 26.23%±14.95% | 6.85%±8.11% | 8.36%±3.32% | 0.28%±0.04% | 4.0K |
| 4 | 3 1 - 9 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
9.23%±2.74% | 8.19%±5.26% | 16.85%±10.69% | 9.50%±4.79% | 11.36%±2.32% | 0.28%±0.04% | 10.7K |
| 5 | 5 1 - 9 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
8.32%±2.27% | 9.35%±4.28% | 15.57%±8.43% | 7.00%±3.96% | 9.42%±4.26% | 0.28%±0.04% | 16.5K |
| 6 | 13 1 - 13 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
8.27%±3.71% | 13.14%±5.78% | 26.34%±13.87% | 3.93%±9.60% | 6.23%±2.11% | 0.41%±1.07% | 3.6K |
| 7 | 6 1 - 14 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
6.42%±2.32% | 7.84%±4.26% | 9.70%±8.47% | 6.18%±4.06% | 8.63%±3.52% | 0.23%±0.62% | 15.1K |
| 8 | 7 3 - 19 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
5.78%±2.31% | 5.37%±4.36% | 14.35%±8.72% | 1.35%±4.49% | 7.55%±1.78% | 0.28%±0.04% | 13.8K |
| 9 | 8 6 - 20 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
4.56%±1.16% | 11.80%±2.23% | 7.64%±4.27% | 2.18%±2.52% | 5.28%±1.20% | 0.28%±0.04% | 47.1K |
| 10 | 10 6 - 23 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
4.27%±1.70% | 0.92%±3.33% | 6.13%±6.24% | 3.32%±3.31% | 10.68%±2.52% | 0.28%±0.04% | 22.7K |
| 11 | 17 6 - 23 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
4.23%±1.59% | 6.43%±3.15% | 6.85%±5.83% | 4.69%±3.20% | 4.01%±1.88% | 0.83%±0.36% | 13.2K |
| 12 | 9 3 - 28 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
3.81%±2.76% | 0.60%±5.70% | 6.17%±9.97% | 6.69%±5.66% | 6.60%±3.59% | 0.18%±0.15% | 13.1K |
| 13 | 12 6 - 32 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
2.84%±2.76% | 13.43%±4.50% | 2.22%±10.09% | 4.09%±6.69% | 2.42%±2.28% | 0.23%±0.09% | 6.9K |
| 14 | 19 7 - 28 |
Grok 4.5
SpaceXAI · Proprietary
|
2.73%±1.78% | 1.51%±3.77% | 0.76%±6.35% | 3.22%±3.69% | 9.40%±1.88% | 0.28%±0.04% | 16.6K |
| 15 | 28 8 - 28 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
2.65%±1.24% | 5.71%±2.65% | 2.01%±4.39% | 3.35%±2.59% | 1.90%±1.27% | 0.28%±0.04% | 20.6K |
| 16 | 16 8 - 28 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
2.58%±1.49% | 3.72%±2.95% | 4.41%±5.52% | 1.14%±3.03% | 5.66%±1.23% | 0.28%±0.04% | 18.6K |
| 17 | 20 8 - 32 |
GPT 5.5
OpenAI · Proprietary
|
2.16%±1.52% | 1.07%±3.04% | 2.04%±5.42% | 0.83%±2.85% | 10.40%±1.91% | 0.28%±0.04% | 28.9K |
| 18 | 15 8 - 32 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
2.08%±1.67% | 11.21%±2.97% | 0.76%±5.76% | 3.75%±4.05% | 3.41%±1.96% | 0.28%±0.04% | 11.9K |
| 19 | 14 9 - 32 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
2.07%±1.33% | 1.23%±2.65% | 5.16%±4.60% | 1.16%±2.50% | 2.55%±2.05% | 0.28%±0.04% | 32.5K |
| 20 | 18 10 - 32 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
1.96%±1.20% | 6.85%±2.39% | 4.71%±4.26% | 1.31%±2.24% | 0.76%±1.59% | 0.28%±0.04% | 30.6K |
| 21 | 21 8 - 32 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
1.65%±1.97% | 0.59%±4.27% | 0.31%±6.84% | 0.65%±4.10% | 7.59%±1.58% | 0.28%±0.04% | 9.8K |
| 22 | 11 10 - 32 |
Hy4 preview
腾讯 · Apache 2.0
|
1.50%±1.89% | 5.44%±3.79% | 0.74%±7.01% | 4.32%±4.15% | 5.57%±1.27% | 0.07%±0.13% | 12.8K |
| 23 | 31 10 - 34 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
0.80%±2.35% | 4.26%±4.86% | 5.42%±8.04% | 1.90%±4.60% | 4.47%±3.14% | 0.28%±0.04% | 10.9K |
| 24 | 25 12 - 32 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
0.62%±1.31% | 8.50%±2.56% | 2.07%±4.67% | 3.06%±2.84% | 4.67%±1.60% | 0.28%±0.04% | 17.6K |
| 25 | 30 12 - 35 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.16%±1.82% | 1.78%±3.88% | 1.16%±6.45% | 1.27%±3.58% | 4.92%±1.85% | 0.10%±0.16% | 14.7K |
| 26 | 23 12 - 37 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.16%±2.10% | 4.09%±4.23% | 1.18%±7.38% | 2.87%±4.20% | 6.28%±3.29% | 0.28%±0.04% | 8.7K |
| 27 | 24 12 - 33 |
GPT 5.4 (High)
OpenAI · Proprietary
|
0.15%±1.56% | 2.65%±3.17% | 4.52%±5.53% | 1.07%±3.10% | 6.55%±1.96% | 0.28%±0.04% | 27.9K |
| 28 | 33 16 - 33 |
Muse Spark 1.1
Meta · Proprietary
|
0.18%±1.08% | 6.89%±2.17% | 6.81%±3.52% | 1.90%±2.33% | 0.68%±2.18% | 0.27%±0.04% | 46.4K |
| 29 | 32 12 - 38 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
0.25%±1.96% | 2.01%±3.99% | 4.33%±6.43% | 1.24%±4.13% | 2.02%±3.39% | 0.28%±0.04% | 13.1K |
| 30 | 22 16 - 37 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
0.51%±1.41% | 1.46%±2.85% | 1.02%±4.94% | 3.02%±3.09% | 0.64%±1.21% | 0.28%±0.04% | 26.2K |
| 31 | 27 16 - 38 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
0.65%±1.58% | 5.71%±3.38% | 5.23%±5.29% | 1.87%±3.26% | 5.54%±2.27% | 0.28%±0.04% | 11.9K |
| 32 | 39 16 - 38 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
1.12%±1.96% | 2.15%±4.05% | 0.22%±6.72% | 1.96%±3.88% | 5.39%±2.75% | 0.20%±0.15% | 8.7K |
| 33 | 34 24 - 39 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
2.51%±1.79% | 6.88%±3.58% | 3.30%±5.45% | 0.99%±3.08% | 1.02%±4.59% | 0.35%±0.46% | 16.2K |
| 34 | 29 27 - 39 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
3.04%±1.39% | 1.81%±2.95% | 7.82%±4.59% | 0.60%±3.08% | 8.63%±1.85% | 0.03%±0.13% | 15.1K |
| 35 | 26 28 - 39 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
3.13%±1.31% | 5.24%±2.72% | 5.50%±4.43% | 8.13%±3.16% | 6.53%±1.14% | 0.73%±0.20% | 21.4K |
| 36 | 36 26 - 42 |
Mimo V2.5 Pro
小米 · MIT
|
3.42%±1.97% | 7.84%±3.77% | 3.33%±6.08% | 1.29%±3.38% | 4.26%±4.99% | 0.39%±0.40% | 16.4K |
| 37 | 38 30 - 42 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
3.72%±1.61% | 3.46%±2.87% | 5.40%±4.79% | 0.31%±2.49% | 20.50%±4.63% | 0.28%±0.04% | 31.8K |
| 38 | 40 28 - 42 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
4.06%±2.17% | 4.41%±4.83% | 11.48%±7.05% | 3.13%±4.48% | 0.19%±4.13% | 1.07%±0.78% | 9.0K |
| 39 | 35 33 - 43 |
Hy3
腾讯 · Apache 2.0
|
5.53%±2.00% | 15.24%±4.48% | 7.14%±6.53% | 0.53%±4.03% | 1.88%±3.03% | 2.89%±1.22% | 11.1K |
| 40 | 37 36 - 43 |
Minimax M3
MiniMax · MiniMax Community License
|
6.53%±1.52% | 15.59%±3.78% | 14.08%±4.73% | 3.31%±3.05% | 0.56%±2.35% | 0.24%±0.46% | 16.6K |
| 41 | 41 36 - 45 |
Inkling Small
Thinky · Apache 2.0
|
7.41%±2.73% | 18.79%±6.71% | 14.66%±8.93% | 4.27%±6.15% | 1.10%±3.24% | 0.45%±0.66% | 4.8K |
| 42 | 45 36 - 45 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
7.67%±2.68% | 15.03%±4.85% | 2.42%±7.54% | 3.43%±4.60% | 16.68%±7.51% | 0.77%±0.75% | 9.6K |
| 43 | 42 39 - 44 |
Inkling
Thinky · Apache 2.0
|
8.13%±1.88% | 18.10%±4.46% | 18.62%±5.51% | 2.04%±3.91% | 1.66%±3.81% | 0.21%±0.33% | 16.4K |
| 44 | 43 41 - 46 |
Mistral Medium 3.5
Mistral · Modified MIT
|
11.64%±2.92% | 13.96%±6.10% | 21.27%±6.98% | 5.22%±5.68% | 25.22%±8.59% | 2.99%±2.29% | 4.2K |
| 45 | 44 42 - 46 |
Minimax M2.7
MiniMax · Modified MIT
|
12.26%±2.17% | 20.78%±4.18% | 16.25%±5.39% | 2.19%±3.80% | 22.15%±6.89% | 0.08%±0.16% | 15.6K |
| 46 | 46 44 - 46 |
Solar Pro 4
Upstage · Proprietary
|
15.26%±4.17% | 22.37%±8.14% | 20.49%±10.39% | 2.33%±6.88% | 30.07%±13.35% | 1.05%±1.23% | 3.8K |
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
Google
月之暗面
阿里巴巴
DeepSeek
SpaceXAI
Meta
智谱 ZAI
腾讯
小米
MiniMax
Mistral