| 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 - 2 |
Claude Opus 5.5 (Max)
Anthropic · Proprietary
|
22.87%±3.48% | 22.47%±5.32% | 49.69%±13.17% | 22.76%±3.32% | 15.08%±0.67% | 0.46%±0.21% | 3.7K |
| 🥈 | 2 1 - 8 |
Claude Sonnet 5.5 (Max)
Anthropic · Proprietary
|
15.76%±4.30% | 23.83%±7.02% | 24.47%±16.48% | 16.23%±5.04% | 11.77%±1.30% | 0.52%±0.23% | 2.5K |
| 🥉 | 3 2 - 8 |
GPT-6 Astra (Max)
OpenAI · Proprietary
|
14.84%±3.09% | 13.64%±6.13% | 31.37%±10.82% | 17.78%±3.61% | 6.64%±1.70% | 0.68%±0.09% | 4.6K |
| 4 | 5 2 - 8 |
GPT-6.1 Sol (Max)
OpenAI · Proprietary
|
14.46%±2.31% | 15.59%±4.32% | 29.91%±8.10% | 18.15%±2.68% | 1.39%±1.55% | 0.71%±0.06% | 5.4K |
| 5 | 4 2 - 9 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
13.89%±2.92% | 13.88%±6.08% | 23.46%±10.16% | 19.56%±3.24% | 9.86%±1.19% | 0.66%±0.12% | 5.0K |
| 6 | 7 2 - 11 |
Muse Wonder Full (Max)
Meta · Proprietary
|
11.36%±1.90% | 14.34%±3.85% | 17.55%±6.35% | 14.93%±2.63% | 7.86%±0.94% | 0.35%±0.24% | 5.3K |
| 7 | 8 2 - 12 |
GPT-6 Sol (Max)
OpenAI · Proprietary
|
10.58%±2.36% | 12.32%±5.16% | 13.80%±7.70% | 15.70%±2.93% | 10.29%±0.81% | 0.65%±0.07% | 3.5K |
| 8 | 6 5 - 11 |
Gemini 4 Argon (High)
Google · Proprietary
|
10.18%±1.24% | 12.34%±2.64% | 21.07%±3.90% | 15.69%±1.64% | 7.23%±1.43% | 0.32%±0.23% | 15.8K |
| 9 | 11 2 - 18 |
Kimi K3.1 Pro (Max)
月之暗面 · Proprietary
|
9.29%±4.52% | 3.80%±9.37% | 19.05%±14.39% | 14.88%±5.68% | 6.78%±1.87% | 0.71%±0.06% | 1.4K |
| 10 | 10 6 - 14 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
8.56%±1.98% | 2.22%±4.65% | 14.47%±5.59% | 15.59%±2.61% | 11.17%±1.73% | 0.66%±0.11% | 12.5K |
| 11 | 9 6 - 15 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
8.04%±2.20% | 11.58%±4.96% | 8.80%±6.35% | 10.13%±3.38% | 10.05%±1.08% | 0.67%±0.09% | 7.2K |
| 12 | 12 8 - 18 |
GPT-5.6 Sol (xHigh)
OpenAI · Proprietary
|
6.74%±1.83% | 3.90%±4.53% | 8.69%±5.08% | 11.36%±2.87% | 11.46%±1.24% | 0.64%±0.09% | 11.0K |
| 13 | 13 9 - 16 |
DeepSeek-V4.1-Flash-20261017 (Max)
DeepSeek · MIT
|
6.48%±1.16% | 9.40%±2.72% | 8.75%±3.45% | 8.23%±1.76% | 4.92%±0.54% | 0.33%±0.11% | 13.0K |
| 14 | 14 9 - 24 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
5.36%±2.42% | 3.81%±5.69% | 5.38%±6.82% | 7.35%±3.73% | 14.66%±1.10% | 0.24%±0.23% | 10.0K |
| 15 | 27 10 - 24 |
Claude Haiku 5.5 (High)
Anthropic · Proprietary
|
4.48%±1.43% | 4.21%±3.67% | 1.86%±4.17% | 11.20%±1.86% | 6.94%±0.71% | 0.56%±0.41% | 10.7K |
| 16 | 20 14 - 22 |
GPT-6 Luna (Max)
OpenAI · Proprietary
|
3.88%±0.59% | 1.49%±1.49% | 2.08%±1.67% | 8.09%±0.86% | 10.40%±0.34% | 0.58%±0.08% | 66.8K |
| 17 | 18 12 - 27 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
3.77%±1.16% | 5.54%±2.79% | 2.56%±3.24% | 6.68%±1.73% | 3.05%±0.98% | 0.65%±0.07% | 26.4K |
| 18 | 19 11 - 34 |
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
3.48%±2.09% | 6.38%±4.97% | 3.43%±5.53% | 0.43%±3.74% | 9.51%±0.84% | 0.68%±0.07% | 6.2K |
| 19 | 15 12 - 34 |
Muse Wonder (Max)
Meta · Proprietary
|
3.05%±2.08% | 6.16%±5.05% | 0.83%±5.62% | 4.08%±3.60% | 5.43%±1.27% | 0.04%±0.66% | 4.1K |
| 20 | 24 14 - 33 |
GLM-5.2 (Max)
智谱 ZAI · MIT
|
2.85%±1.16% | 4.94%±2.80% | 6.22%±3.20% | 3.22%±2.03% | 4.50%±1.15% | 0.71%±0.06% | 28.0K |
| 21 | 21 15 - 28 |
DeepSeek-V4.1-Flash-20260910 (Max)
DeepSeek · MIT
|
2.74%±0.48% | 6.57%±1.18% | 3.02%±1.33% | 2.29%±0.77% | 0.17%±0.34% | 0.52%±0.07% | 90.4K |
| 22 | 16 14 - 34 |
MiMo-V2.6-Pro
小米 · MIT
|
2.36%±1.09% | 4.34%±2.77% | 2.35%±3.00% | 2.62%±1.76% | 2.83%±0.76% | 0.07%±0.31% | 16.2K |
| 23 | 23 15 - 34 |
Hy4 preview
腾讯 · Apache 2.0
|
2.31%±0.88% | 5.92%±2.20% | 2.21%±2.46% | 2.61%±1.37% | 0.85%±0.64% | 0.09%±0.25% | 29.9K |
| 24 | 22 14 - 34 |
MiMo-V2.6-Flash
小米 · MIT
|
1.96%±1.82% | 4.45%±4.41% | 3.32%±5.29% | 6.01%±2.71% | 2.33%±1.39% | 3.77%±0.60% | 7.9K |
| 25 | 26 17 - 34 |
GLM-5.3 (Max)
智谱 ZAI · MIT
|
1.51%±1.17% | 3.67%±2.84% | 4.35%±3.02% | 0.82%±1.99% | 5.46%±1.35% | 0.66%±0.09% | 29.8K |
| 26 | 29 17 - 34 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
1.39%±1.49% | 0.42%±3.89% | 1.16%±3.75% | 1.31%±2.46% | 10.11%±1.26% | 0.61%±0.10% | 10.1K |
| 27 | 32 18 - 34 |
GPT-6 Luna (Medium)
OpenAI · Proprietary
|
1.19%±1.27% | 4.13%±3.36% | 0.60%±3.47% | 4.62%±1.85% | 7.29%±0.86% | 0.62%±0.11% | 10.2K |
| 28 | 25 19 - 34 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
1.10%±1.00% | 4.27%±2.53% | 0.08%±2.59% | 1.44%±1.77% | 3.04%±1.19% | 0.71%±0.06% | 45.2K |
| 29 | 17 17 - 34 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
1.07%±1.58% | 1.81%±3.79% | 2.74%±4.03% | 1.78%±2.56% | 10.17%±0.62% | 0.58%±0.09% | 12.4K |
| 30 | 28 19 - 34 |
Qwen3.8-Max
阿里巴巴 · Proprietary
|
1.00%±0.84% | 3.05%±2.08% | 1.12%±2.24% | 1.17%±1.35% | 0.32%±0.86% | 0.66%±0.23% | 26.2K |
| 31 | 30 19 - 38 |
GPT-5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.08%±2.03% | 8.73%±4.77% | 4.05%±5.40% | 4.19%±3.11% | 0.70%±1.98% | 0.50%±0.18% | 7.9K |
| 32 | 31 19 - 41 |
DeepSeek-V4-Pro (High, 20260813)
DeepSeek · MIT
|
0.17%±2.37% | 1.58%±6.39% | 1.17%±6.17% | 1.17%±4.01% | 5.17%±1.59% | 0.57%±0.15% | 2.5K |
| 33 | 36 19 - 42 |
MiniMax-M3.1-Flash
MiniMax · MiniMax Community License
|
0.49%±2.48% | 7.33%±6.65% | 6.80%±6.71% | 1.94%±4.24% | 2.17%±1.58% | 0.31%±0.23% | 3.5K |
| 34 | 35 20 - 41 |
Step 5 Preview
阶跃星辰 · Proprietary
|
0.57%±2.10% | 1.43%±5.32% | 1.29%±5.51% | 1.92%±3.28% | 10.43%±1.94% | 0.61%±0.15% | 5.3K |
| 35 | 34 31 - 42 |
GLM-5.3-Flash
智谱 ZAI · MIT
|
1.97%±0.91% | 3.05%±2.33% | 2.92%±2.19% | 4.23%±1.66% | 10.91%±1.05% | 0.69%±0.07% | 33.1K |
| 36 | 38 31 - 42 |
Qwen3.8-Flash-Next
阿里巴巴 · Qwen-community-1.0
|
2.14%±0.99% | 3.54%±2.57% | 3.05%±2.57% | 0.51%±1.67% | 17.28%±0.93% | 0.98%±0.18% | 34.0K |
| 37 | 41 32 - 42 |
GPT-6 Luna (Low)
OpenAI · Proprietary
|
3.37%±1.41% | 12.66%±4.09% | 6.47%±3.43% | 2.52%±2.10% | 1.67%±1.31% | 0.63%±0.13% | 7.0K |
| 38 | 39 32 - 42 |
Qwen3.8-27B
阿里巴巴 · Apache 2.0
|
3.49%±1.11% | 1.16%±2.93% | 5.50%±2.58% | 4.57%±1.97% | 9.18%±1.59% | 0.12%±0.15% | 21.8K |
| 39 | 33 32 - 43 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
3.64%±1.35% | 7.68%±3.53% | 3.47%±3.02% | 8.78%±2.52% | 6.12%±1.58% | 0.49%±0.14% | 18.9K |
| 40 | 42 31 - 48 |
Mistral Large 4
Mistral · Proprietary
|
4.79%±3.30% | 1.32%±7.29% | 3.23%±6.82% | 0.61%±7.15% | 0.41%±2.05% | 17.42%±2.29% | 5.0K |
| 41 | 37 31 - 48 |
Beam 1.0 501B A23B
Reflection · Apache 2.0
|
4.92%±3.19% | 9.16%±8.62% | 7.60%±7.89% | 5.56%±4.96% | 5.67%±5.28% | 2.63%±1.77% | 4.1K |
| 42 | 44 34 - 46 |
Hy3
腾讯 · Apache 2.0
|
5.01%±2.20% | 8.46%±5.11% | 4.64%±4.74% | 0.62%±3.19% | 6.16%±5.11% | 5.75%±4.31% | 9.9K |
| 43 | 40 39 - 49 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
6.93%±1.95% | 12.20%±4.52% | 6.22%±3.68% | 12.98%±4.65% | 1.67%±4.49% | 0.60%±1.07% | 22.1K |
| 44 | 43 40 - 49 |
Qwen3.7-Max
阿里巴巴 · Proprietary
|
7.26%±1.54% | 9.23%±4.11% | 10.25%±2.99% | 15.00%±3.31% | 4.02%±3.57% | 0.21%±0.42% | 13.7K |
| 45 | 46 40 - 49 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
8.09%±1.14% | 12.01%±3.34% | 10.92%±2.31% | 12.39%±2.09% | 2.83%±1.54% | 0.31%±0.31% | 18.8K |
| 46 | 45 41 - 49 |
Muse Spark 1.1
Meta · Proprietary
|
8.53%±0.96% | 10.00%±2.46% | 10.95%±1.90% | 16.51%±1.93% | 2.41%±1.87% | 0.28%±0.12% | 49.9K |
| 47 | 48 41 - 49 |
MiMo-V2.5-Pro
小米 · MIT
|
8.79%±1.38% | 9.02%±3.64% | 11.82%±2.70% | 17.36%±3.09% | 0.10%±2.41% | 1.29%±0.46% | 15.7K |
| 48 | 47 40 - 52 |
Qwen3.7-Plus
阿里巴巴 · Proprietary
|
9.23%±2.51% | 11.23%±5.77% | 12.84%±4.00% | 15.30%±4.49% | 4.39%±3.39% | 4.38%±5.84% | 7.7K |
| 49 | 49 43 - 52 |
MiniMax-M3
MiniMax · MiniMax Community License
|
10.17%±1.56% | 17.85%±4.48% | 14.23%±2.77% | 13.86%±3.50% | 1.58%±2.73% | 0.63%±0.71% | 13.5K |
| 50 | 50 48 - 54 |
Mistral Medium 3.5
Mistral · Modified MIT
|
13.89%±2.55% | 20.31%±6.71% | 17.31%±3.97% | 18.89%±5.37% | 6.03%±6.87% | 3.00%±1.65% | 4.1K |
| 51 | 51 48 - 54 |
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
NVIDIA · OpenMDW-1.1
|
14.26%±2.87% | 22.90%±8.73% | 15.40%±5.41% | 15.14%±5.14% | 12.50%±4.38% | 4.48%±1.74% | 1.9K |
| 52 | 53 50 - 55 |
Inkling
Thinky · Apache 2.0
|
16.95%±2.22% | 28.47%±6.12% | 19.26%±2.79% | 27.70%±5.45% | 0.64%±4.92% | 1.18%±1.22% | 12.6K |
| 53 | 52 48 - 55 |
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
17.11%±6.84% | 26.82%±16.16% | 11.85%±12.04% | 26.43%±15.81% | 22.41%±20.24% | 0.70%±1.85% | 3.6K |
| 54 | 54 50 - 55 |
Inkling-Small
Thinky · Apache 2.0
|
18.22%±2.68% | 29.57%±8.09% | 22.33%±2.86% | 28.40%±6.22% | 1.78%±3.73% | 2.60%±1.77% | 4.2K |
| 55 | 55 52 - 55 |
Solar Pro 4
Upstage · Proprietary
|
21.28%±3.14% | 32.26%±9.84% | 22.42%±3.99% | 17.54%±5.69% | 41.80%±11.56% | 2.62%±1.96% | 3.6K |
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
Meta
Google
月之暗面
DeepSeek
SpaceXAI
智谱 ZAI
小米
腾讯
阿里巴巴
MiniMax
阶跃星辰
Mistral
NVIDIA