| 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
|
12.32%±3.22% | 19.73%±4.79% | 23.93%±12.89% | 5.03%±6.36% | 12.63%±1.65% | 0.26%±0.03% | 6.3K |
| 🥈 | 2 1 - 10 |
Claude Opus 5.5 (High)
Anthropic · Proprietary
|
11.04%±4.76% | 16.49%±7.62% | 16.44%±19.31% | 12.59%±9.89% | 9.41%±2.94% | 0.26%±0.03% | 1.8K |
| 🥉 | 4 1 - 7 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.59%±2.90% | 13.16%±5.12% | 18.96%±11.56% | 7.92%±5.89% | 12.67%±1.97% | 0.25%±0.04% | 9.2K |
| 4 | 3 1 - 14 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
8.62%±3.98% | 16.12%±6.14% | 24.27%±15.74% | 3.20%±8.29% | 5.66%±6.03% | 0.26%±0.03% | 4.4K |
| 5 | 7 1 - 10 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
8.41%±2.23% | 5.76%±4.21% | 17.60%±8.51% | 9.73%±3.87% | 8.69%±3.46% | 0.26%±0.03% | 17.3K |
| 6 | 5 1 - 11 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
8.36%±2.51% | 6.40%±5.00% | 12.75%±9.83% | 10.57%±4.64% | 11.80%±2.16% | 0.26%±0.03% | 11.5K |
| 7 | 6 1 - 26 |
GPT 6 Sol (Max)
OpenAI · Proprietary
|
6.10%±4.49% | 14.54%±7.40% | 3.31%±17.49% | 6.55%±9.88% | 12.45%±2.45% | 0.26%±0.03% | 1.8K |
| 8 | 15 3 - 16 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
5.85%±1.81% | 14.25%±3.02% | 10.58%±6.96% | 2.32%±3.98% | 1.95%±1.52% | 0.16%±0.14% | 10.9K |
| 9 | 9 3 - 25 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
5.28%±2.29% | 4.30%±4.23% | 13.28%±8.43% | 2.40%±4.51% | 6.18%±2.40% | 0.26%±0.03% | 14.6K |
| 10 | 8 3 - 25 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
5.10%±2.38% | 4.00%±4.42% | 8.31%±8.59% | 5.46%±4.10% | 7.89%±3.55% | 0.17%±0.52% | 15.3K |
| 11 | 13 6 - 26 |
Hy4 preview
腾讯 · Apache 2.0
|
3.45%±1.77% | 5.87%±3.23% | 5.43%±6.69% | 0.55%±3.50% | 5.30%±1.06% | 0.08%±0.12% | 17.8K |
| 12 | 12 6 - 26 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
3.24%±1.69% | 2.27%±3.49% | 3.04%±6.21% | 3.90%±3.40% | 11.25%±2.15% | 0.26%±0.03% | 23.1K |
| 13 | 10 5 - 29 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
3.20%±2.81% | 3.53%±5.63% | 7.29%±9.96% | 6.45%±5.48% | 5.64%±3.49% | 0.15%±0.16% | 13.5K |
| 14 | 21 7 - 26 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.13%±1.26% | 6.44%±2.46% | 4.70%±4.57% | 3.61%±2.63% | 1.78%±1.60% | 0.85%±0.29% | 19.6K |
| 15 | 31 7 - 26 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
2.81%±1.30% | 3.80%±2.74% | 3.33%±4.76% | 5.14%±2.67% | 1.49%±1.30% | 0.26%±0.03% | 22.1K |
| 16 | 20 8 - 28 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
2.49%±1.24% | 4.59%±2.57% | 5.55%±4.61% | 1.07%±2.27% | 1.00%±1.16% | 0.26%±0.03% | 33.7K |
| 17 | 17 8 - 28 |
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
|
2.46%±1.18% | 14.60%±1.98% | 0.87%±4.31% | 7.09%±2.83% | 3.75%±0.99% | 0.14%±0.07% | 29.5K |
| 18 | 14 8 - 26 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
2.45%±0.99% | 8.59%±1.95% | 2.87%±3.56% | 3.88%±2.20% | 4.42%±1.14% | 0.26%±0.03% | 55.0K |
| 19 | 11 6 - 33 |
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
2.43%±3.37% | 17.74%±5.18% | 1.24%±12.06% | 11.92%±8.43% | 7.31%±2.31% | 0.26%±0.03% | 3.6K |
| 20 | 23 8 - 29 |
Grok 4.5
SpaceXAI · Proprietary
|
2.11%±1.78% | 1.42%±3.60% | 1.30%±6.24% | 3.33%±3.62% | 6.83%±2.53% | 0.26%±0.03% | 17.8K |
| 21 | 16 8 - 28 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
2.01%±1.13% | 8.94%±2.06% | 0.53%±3.92% | 2.28%±2.59% | 3.66%±1.57% | 0.26%±0.03% | 24.1K |
| 22 | 18 8 - 29 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
1.82%±1.33% | 0.85%±2.63% | 6.77%±4.77% | 0.10%±2.53% | 3.04%±1.69% | 0.26%±0.03% | 35.1K |
| 23 | 19 8 - 30 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
1.65%±1.51% | 0.06%±2.98% | 4.83%±5.58% | 1.93%±3.09% | 5.16%±1.30% | 0.26%±0.03% | 18.8K |
| 24 | 22 8 - 32 |
GPT 5.5
OpenAI · Proprietary
|
1.56%±1.57% | 5.11%±3.22% | 3.12%±5.64% | 0.32%±2.97% | 9.83%±2.01% | 0.26%±0.03% | 29.3K |
| 25 | 24 8 - 33 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
1.26%±1.90% | 3.55%±4.00% | 3.71%±6.74% | 0.61%±3.78% | 6.49%±1.94% | 0.26%±0.03% | 11.1K |
| 26 | 25 10 - 34 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.29%±2.13% | 6.44%±4.22% | 3.67%±7.67% | 2.38%±4.16% | 6.35%±2.76% | 0.26%±0.03% | 9.4K |
| 27 | 26 16 - 34 |
GPT 5.4 (High)
OpenAI · Proprietary
|
0.29%±1.61% | 5.04%±3.29% | 4.05%±5.85% | 1.00%±3.19% | 6.40%±2.13% | 0.26%±0.03% | 28.3K |
| 28 | 27 19 - 33 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
0.39%±1.01% | 7.37%±1.97% | 0.51%±3.54% | 2.66%±2.13% | 6.40%±1.59% | 0.26%±0.03% | 29.1K |
| 29 | 30 16 - 36 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.58%±1.90% | 4.95%±3.94% | 0.03%±6.75% | 2.18%±3.73% | 4.17%±1.98% | 0.10%±0.15% | 14.8K |
| 30 | 28 23 - 36 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
1.22%±1.35% | 4.81%±2.71% | 4.90%±4.39% | 1.13%±2.69% | 2.21%±2.57% | 0.26%±0.03% | 16.4K |
| 31 | 34 24 - 34 |
Muse Spark 1.1
Meta · Proprietary
|
1.29%±0.91% | 4.00%±1.78% | 7.36%±2.86% | 3.09%±1.93% | 0.26%±2.03% | 0.26%±0.04% | 57.3K |
| 32 | 33 23 - 36 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
1.29%±1.41% | 0.41%±2.95% | 7.90%±4.64% | 0.17%±2.97% | 1.42%±2.37% | 0.26%±0.03% | 18.9K |
| 33 | 39 22 - 40 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
1.72%±1.89% | 1.83%±3.87% | 0.94%±6.62% | 0.13%±3.83% | 6.14%±2.58% | 0.18%±0.16% | 9.4K |
| 34 | 35 27 - 40 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.25%±1.79% | 10.26%±3.72% | 3.91%±5.59% | 1.02%±3.17% | 0.62%±3.93% | 0.46%±0.49% | 16.8K |
| 35 | 29 30 - 40 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
3.53%±1.20% | 3.17%±2.55% | 6.63%±4.13% | 7.05%±2.81% | 6.48%±0.99% | 0.64%±0.17% | 29.2K |
| 36 | 37 30 - 40 |
Mimo V2.5 Pro
小米 · MIT
|
4.27%±1.95% | 9.86%±3.80% | 5.24%±5.89% | 0.04%±3.39% | 5.66%±5.29% | 0.56%±0.47% | 17.7K |
| 37 | 32 33 - 40 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
4.30%±1.15% | 0.82%±2.48% | 8.94%±3.83% | 1.68%±2.58% | 9.80%±1.51% | 0.27%±0.25% | 21.5K |
| 38 | 36 33 - 42 |
Hy3
腾讯 · Apache 2.0
|
5.09%±2.01% | 14.35%±4.40% | 7.13%±6.49% | 0.95%±4.06% | 2.16%±3.05% | 2.78%±1.18% | 11.7K |
| 39 | 40 33 - 42 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
5.19%±1.63% | 6.34%±3.02% | 2.79%±4.82% | 0.76%±2.63% | 21.92%±4.57% | 0.26%±0.03% | 32.0K |
| 40 | 41 33 - 43 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
5.79%±2.25% | 8.92%±5.07% | 11.45%±7.00% | 4.96%±4.66% | 2.55%±4.56% | 1.06%±0.74% | 9.1K |
| 41 | 38 38 - 43 |
Minimax M3
MiniMax · MiniMax Community License
|
7.79%±1.57% | 18.24%±3.93% | 15.69%±4.69% | 4.61%±3.21% | 0.15%±2.64% | 0.27%±0.46% | 17.2K |
| 42 | 42 38 - 45 |
Inkling Small
Thinky · Apache 2.0
|
9.33%±2.65% | 23.59%±6.87% | 17.24%±8.14% | 5.55%±6.12% | 0.12%±3.40% | 0.38%±0.58% | 5.0K |
| 43 | 43 40 - 44 |
Inkling
Thinky · Apache 2.0
|
9.44%±2.00% | 22.69%±4.67% | 18.67%±5.58% | 3.01%±4.16% | 2.61%±4.25% | 0.21%±0.32% | 16.6K |
| 44 | 44 42 - 45 |
Mistral Medium 3.5
Mistral · Modified MIT
|
12.57%±2.79% | 16.72%±6.13% | 22.23%±6.57% | 4.15%±5.79% | 25.55%±8.13% | 2.50%±1.94% | 4.4K |
| 45 | 45 43 - 45 |
Solar Pro 4
Upstage · Proprietary
|
16.21%±4.34% | 25.84%±8.17% | 18.14%±10.98% | 4.19%±6.68% | 31.90%±14.20% | 0.97%±1.15% | 3.9K |
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
腾讯
阿里巴巴
智谱 ZAI
DeepSeek
月之暗面
SpaceXAI
Meta
小米
MiniMax
Mistral