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
🥇 3
1 - 6
Claude Opus 5 (Max)
Anthropic · Proprietary
13.08%±3.40% 17.14%±6.24% 20.00%±13.47% 14.81%±6.34% 13.14%±1.82% 0.30%±0.06% 8.4K
🥈 2
1 - 9
GPT 6 Astra (Max)
OpenAI · Proprietary
11.97%±5.14% 23.87%±6.79% 34.94%±20.35% 6.26%±10.37% 7.00%±3.55% 0.31%±0.06% 3.9K
🥉 1
1 - 9
Claude Fable 5.1 (Max)
Anthropic · Proprietary
10.25%±3.34% 25.46%±5.29% 12.04%±13.00% 2.19%±7.88% 11.24%±1.79% 0.31%±0.06% 5.3K
4 4
1 - 10
Claude Opus 5 (High)
Anthropic · Proprietary
9.24%±3.16% 6.30%±6.34% 13.78%±12.06% 12.96%±5.76% 12.87%±2.00% 0.31%±0.06% 10.5K
5 5
1 - 13
Claude Fable 5 (High)
Anthropic · Proprietary
7.81%±2.72% 11.21%±4.78% 12.68%±9.20% 7.69%±4.51% 7.18%±6.87% 0.31%±0.06% 16.1K
6 7
1 - 13
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
7.44%±2.68% 7.20%±4.97% 17.67%±10.21% 3.27%±5.20% 8.73%±1.64% 0.31%±0.06% 13.4K
7 6
2 - 19
Claude Opus 4.8 (High)
Anthropic · Proprietary
5.91%±2.67% 6.61%±4.97% 8.46%±9.03% 8.02%±4.59% 6.60%±5.61% 0.15%±0.62% 15.0K
8 10
2 - 20
GPT 5.5 (xHigh)
OpenAI · Proprietary
5.06%±2.10% 1.00%±4.16% 7.71%±7.68% 5.44%±3.81% 10.88%±3.10% 0.31%±0.06% 22.5K
9 16
5 - 23
Qwen3.8 Max
阿里巴巴 · Proprietary
4.18%±1.78% 9.74%±3.45% 8.44%±6.55% 0.57%±3.60% 2.95%±1.99% 0.80%±0.38% 11.7K
10 8
5 - 21
Kimi K3 (Max)
月之暗面 · Kimi K3 license
4.16%±1.25% 14.27%±2.44% 7.29%±4.47% 4.79%±2.77% 3.74%±1.38% 0.31%±0.06% 45.4K
11 17
5 - 24
Grok 4.5
SpaceXAI · Proprietary
3.94%±1.99% 3.44%±4.23% 0.94%±7.27% 5.37%±4.01% 9.63%±1.81% 0.31%±0.06% 16.2K
12 12
2 - 31
Deepseek V4.1 Flash (Max)
DeepSeek · MIT
3.84%±3.98% 12.20%±6.66% 8.51%±14.74% 3.98%±9.16% 2.22%±3.02% 0.24%±0.15% 3.0K
13 9
4 - 29
Claude Sonnet 5 (High)
Anthropic · Proprietary
3.81%±2.99% 2.98%±6.15% 5.13%±10.21% 10.15%±5.91% 6.54%±4.89% 0.23%±0.13% 13.0K
14 15
7 - 29
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
2.57%±1.57% 6.19%±3.09% 6.00%±5.80% 4.41%±3.24% 4.75%±1.29% 0.31%±0.06% 17.7K
15 20
7 - 31
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
2.16%±2.20% 3.77%±4.52% 3.51%±7.80% 2.91%±4.55% 6.11%±1.69% 0.31%±0.06% 9.4K
16 13
8 - 30
GLM 5.2 (Max)
智谱 ZAI · MIT
1.64%±1.42% 3.28%±2.85% 5.55%±4.86% 0.95%±2.66% 0.01%±2.30% 0.31%±0.06% 31.7K
17 19
7 - 31
GPT 5.5
OpenAI · Proprietary
1.60%±1.74% 1.05%±3.71% 0.66%±6.04% 1.65%±3.29% 9.74%±2.18% 0.31%±0.06% 28.6K
18 14
7 - 31
Muse Spark 1.3 (Max)
Meta · Proprietary
1.55%±2.15% 11.43%±3.52% 0.48%±7.71% 7.33%±5.00% 2.87%±2.53% 0.31%±0.06% 9.0K
19 18
10 - 30
GLM 5.3 (Max)
智谱 ZAI · MIT
1.44%±1.25% 8.97%±2.39% 5.35%±4.47% 5.13%±2.45% 2.29%±1.66% 0.31%±0.06% 29.4K
20 11
7 - 31
Hy4 preview
腾讯 · Apache 2.0
1.35%±2.12% 7.14%±4.18% 0.84%±7.79% 6.01%±4.78% 4.69%±1.33% 0.08%±0.15% 10.4K
21 29
7 - 36
Claude Sonnet 4.6
Anthropic · Proprietary
0.76%±2.63% 8.25%±6.02% 3.12%±8.97% 1.84%±5.09% 6.80%±2.74% 0.31%±0.06% 10.8K
22 22
9 - 34
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
0.69%±2.27% 4.68%±4.80% 0.80%±8.04% 0.58%±4.51% 7.58%±3.25% 0.31%±0.06% 8.5K
23 23
12 - 31
GLM 5.3 Flash
智谱 ZAI · MIT
0.54%±1.40% 12.33%±2.71% 2.37%±4.93% 6.22%±3.16% 6.09%±1.77% 0.31%±0.06% 15.8K
24 27
10 - 36
DeepSeek V4 Pro
DeepSeek · MIT
0.32%±2.21% 1.48%±4.87% 2.23%±7.82% 0.71%±4.24% 5.87%±1.77% 0.16%±0.14% 14.5K
25 31
12 - 32
Muse Spark 1.1
Meta · Proprietary
0.07%±1.20% 10.91%±2.35% 5.48%±3.95% 5.30%±2.68% 0.09%±2.40% 0.30%±0.06% 43.6K
26 30
11 - 37
Muse Spark 1.2 (xHigh)
Meta · Proprietary
0.08%±2.36% 4.06%±4.55% 1.28%±7.90% 3.73%±4.84% 0.23%±4.09% 0.31%±0.06% 11.6K
27 24
12 - 36
GPT 5.4 (High)
OpenAI · Proprietary
0.24%±1.75% 2.07%±3.80% 6.96%±6.17% 0.82%±3.55% 6.69%±2.04% 0.31%±0.06% 27.6K
28 25
12 - 37
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
0.27%±1.92% 3.56%±3.82% 0.34%±6.62% 1.46%±3.75% 3.71%±2.68% 0.31%±0.06% 10.6K
29 34
12 - 38
Gemini 3.6 Flash (High)
Google · Proprietary
0.68%±2.23% 0.73%±4.59% 0.11%±7.53% 2.79%±4.26% 5.60%±3.51% 0.24%±0.15% 8.5K
30 21
14 - 37
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
0.79%±1.47% 0.84%±3.01% 0.88%±5.01% 5.46%±3.37% 0.53%±1.35% 0.31%±0.06% 26.1K
31 32
16 - 39
Qwen3.7 Max
阿里巴巴 · Proprietary
2.17%±2.16% 5.50%±4.28% 3.30%±6.43% 0.76%±3.65% 1.12%±5.93% 0.15%±0.37% 16.0K
32 26
23 - 39
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
2.90%±1.49% 7.93%±2.99% 4.76%±5.02% 9.19%±3.70% 7.77%±1.30% 0.71%±0.22% 17.6K
33 36
22 - 41
Mimo V2.5 Pro
小米 · MIT
3.12%±2.18% 6.15%±4.45% 2.58%±7.14% 2.46%±3.90% 4.12%±4.76% 0.29%±0.42% 16.1K
34 28
24 - 40
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
3.37%±1.58% 4.84%±3.21% 6.49%±5.35% 4.16%±3.49% 11.05%±2.17% 0.02%±0.16% 13.5K
35 35
23 - 41
Qwen3.7 Plus
阿里巴巴 · Proprietary
3.58%±2.40% 5.73%±5.48% 11.36%±7.71% 1.64%±4.91% 1.73%±4.42% 0.90%±0.83% 8.9K
36 38
27 - 41
Gemini 3.1 Pro Preview
Google · Proprietary
3.95%±1.90% 3.46%±3.87% 1.96%±5.87% 0.07%±3.11% 18.50%±4.85% 0.31%±0.06% 31.6K
37 39
24 - 42
Inkling Small
Thinky · Apache 2.0
4.87%±3.08% 16.14%±7.45% 12.86%±10.32% 1.34%±6.90% 3.83%±2.72% 0.49%±0.91% 4.8K
38 33
31 - 42
Hy3
腾讯 · Apache 2.0
5.29%±2.26% 14.13%±5.12% 6.33%±7.55% 0.92%±4.47% 2.56%±3.36% 2.52%±1.14% 10.9K
39 43
30 - 43
Gemini 3.5 Flash Lite
Google · Proprietary
6.00%±3.12% 14.70%±6.34% 1.25%±9.45% 0.60%±5.53% 12.28%±6.85% 1.16%±1.75% 9.5K
40 37
33 - 42
Minimax M3
MiniMax · MiniMax Community License
6.58%±1.80% 13.91%±4.52% 15.23%±5.50% 4.64%±3.66% 0.99%±2.61% 0.15%±0.41% 16.3K
41 40
34 - 43
Inkling
Thinky · Apache 2.0
7.31%±2.16% 16.89%±5.47% 19.12%±6.48% 0.37%±4.57% 0.01%±3.69% 0.19%±0.44% 16.4K
42 41
37 - 43
Mistral Medium 3.5
Mistral · Modified MIT
10.07%±2.83% 13.96%±6.04% 21.37%±6.76% 6.98%±5.61% 18.71%±8.11% 3.30%±2.66% 4.1K
43 42
40 - 43
Minimax M2.7
MiniMax · Modified MIT
11.51%±2.51% 19.71%±5.09% 16.47%±6.50% 2.35%±4.49% 19.18%±7.44% 0.14%±0.15% 15.5K
🔍

没有找到匹配的模型,换个关键词试试?No matching models found. Try a different keyword?