| 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 - 4 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
14.73%±2.35% | 20.77%±3.57% | 41.68%±9.55% | 0.03%±4.64% | 10.84%±1.01% | 0.37%±0.06% | 7.4K |
| 🥈 | 3 1 - 7 |
Claude Opus 5 (High)
Anthropic · Proprietary
|
11.27%±1.99% | 11.85%±4.08% | 21.15%±7.40% | 10.91%±3.95% | 12.11%±0.83% | 0.33%±0.06% | 13.9K |
| 🥉 | 4 1 - 8 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
10.39%±2.25% | 10.17%±4.56% | 19.19%±8.12% | 9.42%±4.34% | 12.79%±0.84% | 0.36%±0.06% | 10.8K |
| 4 | 2 1 - 9 |
GPT 6 Astra (Max)
OpenAI · Proprietary
|
10.27%±3.08% | 16.31%±4.95% | 33.52%±11.56% | 4.33%±6.24% | 5.46%±1.41% | 0.39%±0.05% | 5.7K |
| 5 | 5 2 - 8 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
9.58%±1.68% | 6.07%±3.69% | 19.85%±6.07% | 12.52%±3.01% | 9.05%±1.62% | 0.39%±0.05% | 20.8K |
| 6 | 7 2 - 11 |
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
|
8.35%±1.68% | 5.89%±3.55% | 20.60%±6.18% | 10.29%±3.18% | 4.60%±1.02% | 0.39%±0.05% | 17.4K |
| 7 | 6 2 - 11 |
Claude Opus 4.8 (High)
Anthropic · Proprietary
|
8.18%±1.69% | 1.88%±3.59% | 19.74%±6.02% | 12.37%±3.07% | 6.75%±1.76% | 0.15%±0.32% | 22.0K |
| 8 | 9 3 - 18 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
6.66%±2.22% | 4.21%±4.58% | 13.10%±7.87% | 7.87%±4.85% | 7.89%±1.26% | 0.26%±0.09% | 17.2K |
| 9 | 8 5 - 14 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
6.66%±0.83% | 13.26%±1.68% | 13.96%±2.87% | 1.27%±1.61% | 4.42%±0.61% | 0.39%±0.05% | 59.8K |
| 10 | 12 8 - 16 |
GLM 5.2 (Max)
智谱 ZAI · MIT
|
5.54%±0.86% | 9.08%±1.80% | 13.27%±3.08% | 3.78%±1.54% | 1.21%±0.73% | 0.39%±0.05% | 43.5K |
| 11 | 11 6 - 18 |
GPT 5.5 (xHigh)
OpenAI · Proprietary
|
5.52%±1.25% | 0.91%±2.90% | 8.71%±4.33% | 7.94%±2.36% | 9.68%±1.31% | 0.38%±0.05% | 30.5K |
| 12 | 10 6 - 19 |
Hy4 preview
腾讯 · Apache 2.0
|
5.49%±1.59% | 10.35%±2.99% | 12.35%±5.94% | 2.98%±3.28% | 7.50%±0.79% | 0.24%±0.09% | 11.3K |
| 13 | 14 8 - 18 |
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
|
5.07%±1.08% | 11.05%±2.16% | 8.53%±3.95% | 0.23%±2.25% | 5.16%±0.84% | 0.39%±0.05% | 23.6K |
| 14 | 17 9 - 23 |
Grok 4.5
SpaceXAI · Proprietary
|
4.34%±1.36% | 6.53%±2.96% | 3.98%±4.70% | 5.58%±2.68% | 5.24%±1.64% | 0.39%±0.05% | 21.9K |
| 15 | 13 9 - 26 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
3.67%±2.08% | 4.89%±4.67% | 4.49%±6.83% | 3.50%±4.94% | 5.11%±1.65% | 0.39%±0.05% | 5.4K |
| 16 | 16 8 - 27 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
3.62%±2.24% | 4.31%±6.03% | 10.05%±7.15% | 1.90%±4.30% | 1.52%±1.44% | 0.31%±0.12% | 3.8K |
| 17 | 19 10 - 24 |
GPT 5.5
OpenAI · Proprietary
|
3.54%±1.08% | 1.04%±2.49% | 5.68%±3.63% | 5.25%±1.95% | 5.36%±1.51% | 0.39%±0.05% | 40.4K |
| 18 | 15 10 - 25 |
Qwen3.8 Max
阿里巴巴 · Proprietary
|
3.40%±1.18% | 7.58%±2.66% | 4.13%±4.08% | 2.61%±2.37% | 3.78%±1.06% | 1.09%±0.30% | 14.0K |
| 19 | 21 14 - 26 |
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
|
2.84%±0.87% | 8.51%±1.92% | 4.35%±2.93% | 0.66%±1.79% | 1.64%±0.67% | 0.36%±0.06% | 36.4K |
| 20 | 20 14 - 26 |
GLM 5.3 (Max)
智谱 ZAI · MIT
|
2.72%±0.76% | 10.62%±1.69% | 5.46%±2.56% | 0.03%±1.44% | 2.90%±0.78% | 0.39%±0.05% | 41.0K |
| 21 | 18 13 - 27 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
2.62%±1.33% | 1.33%±3.13% | 2.94%±4.40% | 3.57%±2.60% | 4.87%±1.13% | 0.39%±0.05% | 13.3K |
| 22 | 23 14 - 28 |
GPT 5.4 (High)
OpenAI · Proprietary
|
2.14%±1.08% | 0.55%±2.62% | 1.58%±3.65% | 4.82%±2.10% | 4.47%±1.01% | 0.39%±0.05% | 39.2K |
| 23 | 24 14 - 28 |
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
|
2.04%±1.39% | 2.10%±3.43% | 1.29%±4.63% | 7.79%±2.70% | 2.84%±1.59% | 0.39%±0.05% | 11.1K |
| 24 | 22 15 - 28 |
GLM 5.3 Flash
智谱 ZAI · MIT
|
1.80%±0.99% | 10.55%±2.22% | 2.90%±3.19% | 0.26%±2.02% | 5.12%±0.95% | 0.39%±0.05% | 17.1K |
| 25 | 25 16 - 29 |
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
|
1.06%±1.23% | 1.07%±2.87% | 1.12%±3.98% | 2.08%±2.54% | 2.86%±1.36% | 0.39%±0.05% | 13.2K |
| 26 | 26 17 - 29 |
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
|
0.83%±1.16% | 10.52%±2.44% | 1.74%±3.98% | 3.47%±2.68% | 0.33%±0.66% | 0.83%±0.16% | 18.6K |
| 27 | 27 22 - 29 |
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
|
0.27%±1.01% | 6.29%±2.36% | 1.75%±3.42% | 1.56%±2.04% | 5.01%±0.92% | 0.11%±0.14% | 17.8K |
| 28 | 28 20 - 29 |
DeepSeek V4 Pro
DeepSeek · MIT
|
0.23%±1.34% | 0.52%±3.37% | 1.85%±4.66% | 0.84%±2.40% | 3.67%±0.97% | 0.38%±0.20% | 19.5K |
| 29 | 29 25 - 32 |
Claude Sonnet 4.6
Anthropic · Proprietary
|
1.53%±1.50% | 6.06%±3.94% | 5.08%±4.55% | 2.38%±2.95% | 5.60%±1.87% | 0.28%±0.18% | 16.1K |
| 30 | 30 29 - 36 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
3.15%±1.48% | 2.22%±3.72% | 9.99%±4.80% | 9.10%±3.23% | 5.16%±1.67% | 0.39%±0.05% | 15.1K |
| 31 | 32 29 - 36 |
Qwen3.7 Max
阿里巴巴 · Proprietary
|
3.31%±1.15% | 3.90%±2.89% | 8.08%±3.27% | 3.49%±2.00% | 0.88%±2.26% | 0.21%±0.25% | 22.5K |
| 32 | 33 29 - 38 |
Hy3
腾讯 · Apache 2.0
|
4.36%±1.60% | 4.00%±3.63% | 6.30%±4.80% | 2.44%±3.30% | 5.36%±3.02% | 3.70%±2.04% | 15.4K |
| 33 | 31 30 - 37 |
Muse Spark 1.1
Meta · Proprietary
|
4.53%±0.74% | 1.03%±1.89% | 12.22%±2.05% | 7.35%±1.47% | 2.43%±1.39% | 0.38%±0.05% | 57.7K |
| 34 | 34 30 - 38 |
Minimax M3
MiniMax · MiniMax Community License
|
5.49%±1.12% | 10.11%±3.14% | 11.69%±3.28% | 7.34%±2.25% | 1.64%±1.08% | 0.06%±0.14% | 22.3K |
| 35 | 37 30 - 38 |
Mimo V2.5 Pro
小米 · MIT
|
5.50%±1.10% | 6.35%±2.97% | 11.78%±3.08% | 3.27%±2.12% | 5.39%±1.98% | 0.70%±0.33% | 22.6K |
| 36 | 35 30 - 39 |
Qwen3.7 Plus
阿里巴巴 · Proprietary
|
5.85%±1.49% | 8.74%±4.03% | 12.43%±4.08% | 4.76%±3.01% | 2.37%±2.51% | 0.97%±0.47% | 12.4K |
| 37 | 36 32 - 39 |
Gemini 3.6 Flash (High)
Google · Proprietary
|
6.40%±1.30% | 7.15%±3.46% | 9.25%±3.72% | 4.48%±2.55% | 11.48%±1.90% | 0.36%±0.07% | 11.6K |
| 38 | 38 33 - 39 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
6.62%±1.15% | 7.51%±2.91% | 2.96%±3.37% | 3.45%±1.98% | 19.07%±1.99% | 0.09%±0.47% | 42.8K |
| 39 | 39 36 - 41 |
Inkling Small
Thinky · Apache 2.0
|
8.72%±1.82% | 20.05%±5.57% | 20.71%±4.84% | 10.31%±4.28% | 8.17%±1.34% | 0.67%±0.58% | 6.9K |
| 40 | 40 39 - 41 |
Inkling
Thinky · Apache 2.0
|
9.36%±1.26% | 17.90%±3.96% | 22.70%±3.15% | 11.52%±2.89% | 5.21%±1.32% | 0.11%±0.17% | 23.2K |
| 41 | 41 39 - 42 |
Mistral Medium 3.5
Mistral · Modified MIT
|
10.94%±1.79% | 18.88%±4.71% | 14.30%±4.89% | 8.52%±3.97% | 11.30%±2.55% | 1.72%±0.78% | 5.6K |
| 42 | 42 41 - 43 |
Minimax M2.7
MiniMax · Modified MIT
|
12.86%±1.40% | 12.44%±3.75% | 22.29%±3.39% | 7.35%±3.19% | 22.43%±2.94% | 0.23%±0.17% | 22.2K |
| 43 | 43 42 - 43 |
Gemini 3.5 Flash Lite
Google · Proprietary
|
14.93%±1.62% | 15.41%±4.59% | 21.48%±3.57% | 12.69%±3.43% | 23.39%±3.54% | 1.68%±0.92% | 13.2K |
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
智谱 ZAI
腾讯
DeepSeek
SpaceXAI
Meta
Google
阿里巴巴
MiniMax
小米
Mistral