| 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 - 3 |
Claude Opus 5.5 (Max)
Anthropic · Proprietary
|
23.35%±5.32% | 31.07%±5.72% | 51.88%±21.52% | 13.99%±3.65% | 15.45%±1.07% | 0.40%±0.19% | 3.3K |
| 🥈 | 2 1 - 9 |
Claude Sonnet 5.5 (Max)
Anthropic · Proprietary
|
17.07%±6.34% | 24.71%±8.63% | 37.26%±24.68% | 7.40%±6.19% | 13.91%±2.05% | 0.50%±0.06% | 2.5K |
| 🥉 | 4 1 - 9 |
Claude Fable 5.1 (Max)
Anthropic · Proprietary
|
15.23%±3.57% | 18.22%±5.32% | 32.00%±13.58% | 10.90%±3.17% | 13.81%±2.17% | 0.49%±0.06% | 6.2K |
| 4 | 6 2 - 9 |
Gemini 4 Argon (High)
Google · Proprietary
|
14.79%±1.96% | 19.74%±3.15% | 30.22%±7.43% | 14.31%±1.72% | 4.16%±2.08% | 0.18%±0.23% | 11.3K |
| 5 | 3 2 - 14 |
GPT-6 Astra (Max)
OpenAI · Proprietary
|
11.71%±3.88% | 18.80%±6.26% | 14.30%±14.14% | 11.86%±3.68% | 14.46%±2.63% | 0.50%±0.06% | 4.8K |
| 6 | 5 2 - 13 |
GPT-6.1 Sol (Max)
OpenAI · Proprietary
|
11.65%±3.38% | 12.49%±5.72% | 25.24%±12.69% | 9.31%±2.91% | 9.74%±2.28% | 0.50%±0.06% | 4.4K |
| 7 | 7 2 - 14 |
Muse Wonder Full (Max)
Meta · Proprietary
|
10.83%±2.90% | 14.06%±5.04% | 21.25%±10.61% | 8.25%±3.06% | 9.75%±1.54% | 0.31%±0.26% | 4.2K |
| 8 | 9 2 - 14 |
Claude Opus 5 (Max)
Anthropic · Proprietary
|
9.55%±3.39% | 12.84%±5.37% | 18.19%±12.32% | 4.62%±3.59% | 13.69%±1.79% | 0.50%±0.06% | 9.1K |
| 9 | 17 5 - 14 |
Gemini 3.8 Flash (High)
Google · Proprietary
|
8.17%±2.24% | 11.00%±3.75% | 13.87%±8.14% | 5.39%±2.35% | 12.53%±1.39% | 0.24%±0.31% | 11.6K |
| 10 | 11 2 - 30 |
Kimi K3.1 Pro (Max)
月之暗面 · Proprietary
|
7.69%±5.95% | 1.09%±11.64% | 23.94%±22.54% | 4.46%±5.78% | 9.20%±3.36% | 0.50%±0.06% | 1.2K |
| 11 | 10 5 - 19 |
Claude Fable 5 (High)
Anthropic · Proprietary
|
6.66%±2.60% | 5.84%±4.54% | 12.89%±8.66% | 3.24%±3.49% | 15.00%±2.56% | 0.50%±0.06% | 17.0K |
| 12 | 12 5 - 21 |
GPT-5.6 Sol (xHigh)
OpenAI · Proprietary
|
6.13%±2.77% | 2.39%±5.05% | 14.99%±9.43% | 5.17%±3.17% | 9.69%±2.02% | 0.18%±0.33% | 14.4K |
| 13 | 8 5 - 25 |
GPT-6 Sol (Max)
OpenAI · Proprietary
|
5.88%±3.31% | 8.31%±6.40% | 5.47%±11.53% | 5.46%±3.51% | 13.74%±1.39% | 0.38%±0.11% | 3.2K |
| 14 | 19 6 - 31 |
Grok 4.7 (xHigh)
SpaceXAI · Proprietary
|
4.79%±3.45% | 12.13%±5.97% | 3.90%±12.23% | 0.58%±3.69% | 9.08%±1.51% | 0.42%±0.09% | 5.3K |
| 15 | 16 10 - 27 |
MiMo-V2.6-Pro
小米 · MIT
|
4.01%±1.70% | 8.48%±3.17% | 5.30%±5.84% | 1.68%±1.91% | 6.00%±1.31% | 0.41%±0.59% | 12.6K |
| 16 | 33 10 - 32 |
Gemini 3.7 Flash (High)
Google · Proprietary
|
3.06%±1.84% | 3.59%±3.33% | 3.95%±6.00% | 1.64%±2.43% | 8.56%±3.27% | 0.33%±0.32% | 21.0K |
| 17 | 18 10 - 33 |
Muse Spark 1.3 (Max)
Meta · Proprietary
|
2.58%±1.68% | 3.08%±3.19% | 4.56%±5.75% | 1.80%±1.93% | 3.40%±1.82% | 0.48%±0.06% | 26.9K |
| 18 | 13 10 - 34 |
DeepSeek-V4.1-Flash-20261017 (Max)
DeepSeek · MIT
|
2.47%±1.82% | 7.12%±3.61% | 0.70%±6.26% | 0.83%±2.02% | 4.22%±1.06% | 0.35%±0.12% | 9.7K |
| 19 | 23 11 - 33 |
Hy4 preview
腾讯 · Apache 2.0
|
2.17%±1.36% | 5.30%±2.60% | 5.70%±4.76% | 0.25%±1.46% | 3.24%±1.07% | 0.14%±0.21% | 27.3K |
| 20 | 15 10 - 38 |
Muse Wonder (Max)
Meta · Proprietary
|
1.95%±3.23% | 5.94%±6.66% | 3.78%±10.71% | 2.07%±3.92% | 8.10%±2.45% | 0.47%±0.09% | 3.3K |
| 21 | 21 13 - 33 |
DeepSeek-V4.1-Flash-20260910 (Max)
DeepSeek · MIT
|
1.63%±0.73% | 4.91%±1.38% | 3.05%±2.51% | 0.46%±0.87% | 1.03%±0.66% | 0.34%±0.07% | 76.8K |
| 22 | 25 12 - 35 |
Kimi K3 (Max)
月之暗面 · Kimi K3 license
|
1.43%±1.55% | 4.45%±2.90% | 3.38%±4.99% | 0.15%±2.10% | 3.45%±3.02% | 0.50%±0.06% | 52.6K |
| 23 | 20 14 - 35 |
GPT-6 Luna (Max)
OpenAI · Proprietary
|
1.18%±0.89% | 0.30%±1.78% | 2.60%±3.01% | 2.84%±0.98% | 9.96%±0.73% | 0.38%±0.09% | 52.6K |
| 24 | 26 14 - 38 |
GLM-5.3 (Max)
智谱 ZAI · MIT
|
0.39%±1.64% | 0.54%±3.19% | 5.56%±5.36% | 1.99%±1.97% | 3.59%±2.64% | 0.50%±0.06% | 32.3K |
| 25 | 30 12 - 40 |
GPT-5.6 Terra (xHigh)
OpenAI · Proprietary
|
0.33%±2.63% | 3.53%±4.73% | 2.40%±9.09% | 0.61%±3.38% | 3.00%±4.27% | 0.50%±0.06% | 9.5K |
| 26 | 28 15 - 36 |
Qwen3.8-Max
阿里巴巴 · Proprietary
|
0.32%±1.22% | 4.25%±2.40% | 1.37%±3.99% | 0.99%±1.49% | 3.01%±1.80% | 0.91%±0.52% | 25.4K |
| 27 | 29 13 - 39 |
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
|
0.28%±2.25% | 3.16%±4.29% | 1.13%±7.30% | 1.62%±2.56% | 7.19%±2.70% | 0.32%±0.18% | 11.2K |
| 28 | 22 12 - 40 |
MiMo-V2.6-Flash
小米 · MIT
|
0.20%±2.78% | 4.17%±5.19% | 3.33%±9.24% | 2.92%±2.99% | 1.69%±2.64% | 2.03%±1.18% | 7.0K |
| 29 | 14 12 - 42 |
Claude Sonnet 5 (High)
Anthropic · Proprietary
|
0.02%±3.23% | 4.91%±6.51% | 4.49%±10.50% | 2.08%±4.02% | 14.00%±2.54% | 0.43%±0.14% | 13.1K |
| 30 | 34 17 - 39 |
GLM-5.3-Flash
智谱 ZAI · MIT
|
0.30%±1.40% | 3.15%±2.81% | 0.71%±4.55% | 0.27%±1.70% | 7.83%±2.28% | 0.37%±0.10% | 31.4K |
| 31 | 24 20 - 40 |
GLM-5.2 (Max)
智谱 ZAI · MIT
|
0.96%±1.66% | 3.64%±3.20% | 3.57%±5.33% | 2.29%±2.27% | 4.68%±2.73% | 0.39%±0.13% | 34.2K |
| 32 | 37 11 - 50 |
Beam 1.0 501B A23B
Reflection · Apache 2.0
|
1.48%±5.06% | 0.43%±8.27% | 1.81%±18.20% | 6.55%±5.08% | 4.04%±5.04% | 0.13%±0.38% | 2.9K |
| 33 | 31 14 - 48 |
DeepSeek-V4-Pro (High, 20260813)
DeepSeek · MIT
|
1.70%±3.53% | 8.94%±7.38% | 0.57%±11.57% | 1.52%±3.79% | 1.84%±3.22% | 0.14%±0.50% | 2.3K |
| 34 | 40 21 - 47 |
Gemini 3.1 Pro Preview
Google · Proprietary
|
2.02%±2.40% | 13.46%±4.49% | 0.58%±7.21% | 0.05%±3.86% | 8.93%±4.73% | 0.45%±0.09% | 30.0K |
| 35 | 45 26 - 45 |
Muse Spark 1.1
Meta · Proprietary
|
2.60%±1.22% | 0.60%±2.41% | 9.99%±3.58% | 5.15%±1.98% | 5.51%±2.70% | 0.06%±0.16% | 56.1K |
| 36 | 36 16 - 50 |
MiniMax-M3.1-Flash
MiniMax · MiniMax Community License
|
2.92%±4.24% | 0.32%±8.48% | 1.43%±13.92% | 5.71%±5.61% | 13.35%±3.59% | 0.34%±0.17% | 2.7K |
| 37 | 32 24 - 47 |
GPT-6 Luna (Medium)
OpenAI · Proprietary
|
2.97%±1.89% | 6.40%±4.05% | 6.33%±5.97% | 2.19%±2.30% | 2.89%±4.01% | 0.09%±0.51% | 8.3K |
| 38 | 27 24 - 49 |
Claude Haiku 5.5 (High)
Anthropic · Proprietary
|
3.34%±2.12% | 2.31%±4.94% | 14.27%±6.53% | 2.17%±2.58% | 7.78%±1.87% | 0.16%±0.51% | 7.9K |
| 39 | 42 23 - 50 |
Mistral Large 4
Mistral · Proprietary
|
3.88%±3.23% | 0.79%±7.12% | 5.14%±9.88% | 0.98%±3.98% | 3.69%±3.66% | 15.96%±3.43% | 4.1K |
| 40 | 46 31 - 49 |
Muse Spark 1.2 (xHigh)
Meta · Proprietary
|
4.69%±1.67% | 4.83%±3.57% | 10.68%±5.09% | 3.39%±2.11% | 4.26%±3.58% | 0.06%±0.26% | 19.2K |
| 41 | 38 32 - 49 |
Qwen3.8-Flash-Next
阿里巴巴 · Qwen-community-1.0
|
4.91%±1.43% | 0.63%±2.86% | 4.63%±4.62% | 4.80%±1.72% | 23.14%±1.91% | 0.46%±0.24% | 33.3K |
| 42 | 35 28 - 50 |
Step 5 Preview
阶跃星辰 · Proprietary
|
5.03%±2.86% | 5.18%±6.47% | 12.51%±9.00% | 0.89%±3.59% | 8.51%±2.94% | 0.23%±0.44% | 4.8K |
| 43 | 41 32 - 50 |
GPT-6 Luna (Low)
OpenAI · Proprietary
|
5.53%±2.16% | 11.19%±4.67% | 9.55%±6.66% | 4.41%±2.58% | 0.45%±4.38% | 0.50%±0.06% | 5.5K |
| 44 | 47 31 - 51 |
Qwen3.7-Plus
阿里巴巴 · Proprietary
|
5.82%±2.95% | 6.55%±6.01% | 12.53%±9.04% | 3.89%±4.33% | 4.12%±6.63% | 1.14%±1.55% | 9.1K |
| 45 | 39 33 - 50 |
Qwen3.8-27B
阿里巴巴 · Apache 2.0
|
5.87%±1.56% | 3.43%±3.16% | 9.26%±4.87% | 4.70%±2.08% | 17.47%±3.67% | 0.28%±0.35% | 21.6K |
| 46 | 43 32 - 50 |
Qwen3.7-Max
阿里巴巴 · Proprietary
|
6.08%±2.32% | 15.34%±4.80% | 8.83%±6.91% | 3.94%±3.26% | 1.86%±6.70% | 0.16%±0.54% | 16.3K |
| 47 | 48 33 - 51 |
MiMo-V2.5-Pro
小米 · MIT
|
6.55%±2.18% | 12.94%±4.36% | 10.44%±6.36% | 6.67%±3.09% | 2.64%±5.96% | 0.73%±0.72% | 17.7K |
| 48 | 50 35 - 54 |
Mistral Medium 3.5
Mistral · Modified MIT
|
8.70%±3.52% | 18.39%±7.02% | 13.57%±10.35% | 3.40%±4.44% | 1.78%±9.12% | 2.89%±2.38% | 4.7K |
| 49 | 44 39 - 54 |
Hy3
腾讯 · Apache 2.0
|
9.03%±2.58% | 15.35%±5.14% | 12.15%±7.28% | 4.15%±3.61% | 16.51%±8.40% | 0.73%±0.57% | 11.7K |
| 50 | 51 36 - 55 |
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
NVIDIA · OpenMDW-1.1
|
9.69%±4.40% | 14.04%±9.92% | 18.14%±12.51% | 4.86%±5.11% | 12.23%±12.58% | 0.47%±1.36% | 1.4K |
| 51 | 49 46 - 54 |
MiniMax-M3
MiniMax · MiniMax Community License
|
10.74%±2.18% | 19.61%±4.86% | 18.06%±5.88% | 8.37%±3.39% | 4.05%±5.60% | 0.27%±0.75% | 16.7K |
| 52 | 53 48 - 55 |
Inkling
Thinky · Apache 2.0
|
11.98%±3.08% | 24.13%±6.12% | 22.02%±7.63% | 4.59%±3.92% | 4.14%±14.39% | 1.09%±1.28% | 15.7K |
| 53 | 54 48 - 55 |
Inkling-Small
Thinky · Apache 2.0
|
14.91%±3.30% | 28.64%±8.01% | 24.90%±7.93% | 15.43%±5.15% | 4.64%±7.64% | 0.46%±0.84% | 5.0K |
| 54 | 52 48 - 55 |
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
|
15.21%±6.22% | 25.19%±13.75% | 25.55%±15.62% | 19.23%±12.82% | 3.32%±13.17% | 0.14%±0.44% | 4.9K |
| 55 | 55 51 - 55 |
Solar Pro 4
Upstage · Proprietary
|
17.62%±3.94% | 33.62%±10.12% | 18.26%±11.12% | 10.03%±5.05% | 30.42%±11.83% | 2.16%±2.13% | 4.0K |
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
Google
OpenAI
Meta
月之暗面
SpaceXAI
小米
DeepSeek
腾讯
智谱 ZAI
阿里巴巴
MiniMax
Mistral
阶跃星辰
NVIDIA