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
16.08%±3.49% 21.29%±4.50% 43.48%±13.39% 2.46%±8.53% 12.47%±1.60% 0.70%±0.16% 3.9K
🥈 2
1 - 7
Claude Opus 5 (High)
Anthropic · Proprietary
12.66%±1.99% 14.57%±4.18% 20.53%±7.56% 13.26%±3.88% 14.34%±0.96% 0.63%±0.17% 13.2K
🥉 3
1 - 9
Claude Opus 5 (Max)
Anthropic · Proprietary
11.18%±2.30% 13.06%±4.68% 16.76%±8.24% 10.27%±4.50% 15.14%±0.87% 0.67%±0.17% 10.2K
4 4
1 - 8
Claude Fable 5 (High)
Anthropic · Proprietary
10.88%±1.74% 6.87%±3.85% 21.90%±6.36% 13.25%±3.12% 11.68%±1.84% 0.70%±0.16% 20.4K
5 5
2 - 10
GPT 5.6 Sol (xHigh)
OpenAI · Proprietary
10.16%±1.76% 7.52%±3.73% 24.62%±6.56% 10.55%±3.32% 7.41%±1.07% 0.70%±0.16% 16.7K
6 6
2 - 10
Claude Opus 4.8 (High)
Anthropic · Proprietary
10.02%±1.78% 3.54%±3.71% 23.29%±6.34% 13.57%±3.21% 9.33%±1.77% 0.39%±0.47% 21.3K
7 8
2 - 20
Claude Sonnet 5 (High)
Anthropic · Proprietary
8.55%±2.37% 5.84%±4.97% 14.76%±8.49% 11.06%±5.11% 10.57%±1.36% 0.54%±0.19% 16.5K
8 7
3 - 16
Kimi K3 (Max)
月之暗面 · Kimi K3 license
8.47%±0.81% 15.09%±1.63% 16.50%±2.79% 3.19%±1.54% 6.88%±0.63% 0.70%±0.16% 57.8K
9 9
5 - 20
GPT 5.5 (xHigh)
OpenAI · Proprietary
7.37%±1.25% 2.94%±2.88% 10.82%±4.34% 9.69%±2.31% 12.71%±1.48% 0.70%±0.16% 29.8K
10 10
4 - 22
Hy4 preview
腾讯 · Apache 2.0
7.13%±1.84% 12.16%±3.50% 13.82%±6.90% 0.98%±3.78% 10.12%±0.94% 0.56%±0.19% 8.3K
11 12
7 - 21
GLM 5.2 (Max)
智谱 ZAI · MIT
6.82%±0.89% 9.81%±1.88% 14.18%±3.17% 5.03%±1.57% 4.39%±0.77% 0.70%±0.16% 41.0K
12 18
7 - 22
DeepSeek V4 Pro (High) (0813)
DeepSeek · MIT
6.72%±1.06% 12.98%±2.21% 7.91%±3.73% 3.49%±2.27% 8.54%±0.83% 0.70%±0.16% 20.8K
13 15
7 - 22
GPT 5.5 (High)
OpenAI · Proprietary
6.42%±1.25% 2.27%±2.72% 11.54%±4.30% 7.99%±2.16% 9.60%±1.99% 0.70%±0.16% 36.1K
14 11
7 - 28
Claude Opus 4.7 (High)
Anthropic · Proprietary
6.39%±1.78% 1.92%±3.89% 9.45%±5.62% 10.10%±3.14% 9.83%±3.47% 0.64%±0.17% 14.5K
15 14
7 - 28
Claude Opus 4.7
Anthropic · Proprietary
6.36%±1.88% 1.02%±4.22% 13.39%±6.07% 10.08%±3.22% 6.69%±3.56% 0.63%±0.17% 15.0K
16 13
7 - 25
Grok 4.5
SpaceXAI · Proprietary
6.33%±1.40% 8.53%±2.98% 7.14%±4.91% 6.60%±2.74% 8.66%±1.35% 0.70%±0.16% 21.1K
17 16
8 - 28
Qwen3.8 Max
阿里巴巴 · Proprietary
5.31%±1.28% 9.19%±2.84% 7.25%±4.38% 4.19%±2.50% 6.39%±1.16% 0.46%±0.31% 12.4K
18 17
8 - 30
Gemini 3.8 Flash (High)
Google · Proprietary
5.29%±2.20% 6.57%±5.75% 11.32%±7.14% 3.40%±4.27% 4.51%±1.42% 0.63%±0.19% 3.8K
19 21
8 - 28
GPT 5.5
OpenAI · Proprietary
5.22%±1.06% 3.17%±2.44% 6.97%±3.59% 7.08%±1.89% 8.17%±1.51% 0.70%±0.16% 39.6K
20 19
10 - 30
Grok 4.6 (xHigh)
SpaceXAI · Proprietary
4.54%±1.41% 5.93%±3.26% 3.87%±4.76% 4.42%±2.87% 7.78%±1.17% 0.70%±0.16% 11.5K
21 24
14 - 30
Deepseek V4 Flash (High) (20260731)
DeepSeek · MIT
4.24%±0.90% 10.60%±2.03% 5.34%±3.09% 0.90%±1.76% 3.69%±0.73% 0.68%±0.16% 32.5K
22 22
14 - 30
GLM 5.3 (Max)
智谱 ZAI · MIT
4.15%±0.82% 11.74%±1.80% 7.03%±2.79% 1.72%±1.56% 0.47%±0.84% 0.70%±0.16% 33.8K
23 20
11 - 32
Claude Opus 4.6
Anthropic · Proprietary
4.06%±1.65% 1.68%±3.92% 4.76%±5.52% 4.47%±3.05% 8.69%±1.88% 0.70%±0.16% 14.4K
24 23
14 - 31
GLM 5.3 Flash
智谱 ZAI · MIT
3.82%±1.19% 13.44%±2.56% 5.77%±3.99% 1.28%±2.39% 2.11%±1.09% 0.70%±0.16% 12.0K
25 26
15 - 31
GPT 5.4 (High)
OpenAI · Proprietary
3.75%±1.09% 1.38%±2.62% 3.54%±3.70% 5.64%±2.08% 7.51%±1.02% 0.70%±0.16% 38.4K
26 27
15 - 33
Qwen3.8 Flash Next
阿里巴巴 · Qwen-community-1.0
3.38%±1.48% 11.55%±3.06% 2.58%±5.11% 0.04%±3.31% 3.25%±0.77% 0.50%±0.26% 12.2K
27 25
15 - 33
GPT 5.6 Terra (xHigh)
OpenAI · Proprietary
3.27%±1.40% 1.36%±3.59% 1.63%±4.59% 9.50%±2.69% 5.85%±1.59% 0.70%±0.16% 10.4K
28 29
8 - 37
Claude Opus 4.8
Anthropic · Proprietary
3.03%±3.55% 5.95%±4.12% 10.89%±6.39% 10.82%±3.63% 8.73%±2.08% 21.26%±15.16% 20.3K
29 28
19 - 34
GPT 5.6 Luna (xHigh)
OpenAI · Proprietary
2.45%±1.29% 2.64%±3.12% 0.15%±4.15% 2.59%±2.70% 6.44%±1.30% 0.70%±0.16% 11.5K
30 30
25 - 35
Qwen 3.8 27B
阿里巴巴 · Apache 2.0
1.45%±1.14% 6.57%±2.70% 2.84%±3.77% 1.11%±2.32% 1.19%±0.98% 0.16%±0.23% 14.1K
31 32
26 - 37
DeepSeek V4 Pro
DeepSeek · MIT
0.74%±1.27% 1.33%±3.27% 1.83%±4.29% 0.89%±2.29% 5.28%±1.00% 0.19%±0.26% 18.8K
32 33
28 - 38
Claude Sonnet 4.6
Anthropic · Proprietary
0.25%±1.46% 4.15%±3.83% 3.23%±4.46% 0.81%±2.87% 8.82%±1.79% 0.62%±0.22% 16.1K
33 36
19 - 43
Kimi K2.6
月之暗面 · Modified MIT
0.13%±3.25% 2.18%±7.44% 4.72%±10.83% 6.81%±7.04% 9.42%±5.36% 0.70%±0.16% 6.6K
34 31
23 - 44
Kimi K2.7 Code
月之暗面 · Modified MIT
0.19%±3.19% 1.05%±7.23% 0.08%±10.39% 0.85%±7.06% 3.49%±3.34% 0.70%±0.16% 6.5K
35 35
30 - 39
Gemini 3.7 Flash (High)
Google · Proprietary
0.87%±1.03% 6.86%±2.61% 4.01%±3.13% 6.20%±2.14% 1.63%±1.29% 0.63%±0.18% 14.9K
36 34
29 - 40
Muse Spark 1.2 (xHigh)
Meta · Proprietary
1.03%±1.37% 2.83%±3.49% 8.24%±4.31% 7.25%±2.91% 6.81%±1.79% 0.70%±0.16% 13.0K
37 38
32 - 42
Qwen3.7 Max
阿里巴巴 · Proprietary
1.68%±1.09% 1.20%±2.85% 6.95%±3.25% 3.30%±1.98% 2.98%±1.76% 0.07%±0.32% 21.7K
38 40
30 - 45
Hy3
腾讯 · Apache 2.0
1.84%±1.64% 1.79%±3.70% 1.70%±5.25% 1.10%±3.29% 2.42%±3.05% 2.19%±0.81% 14.6K
39 39
33 - 45
GLM 5.1
智谱 ZAI · MIT
2.44%±1.11% 2.13%±2.57% 5.25%±2.85% 1.01%±2.16% 6.26%±2.67% 1.81%±0.82% 37.2K
40 37
34 - 45
Muse Spark 1.1
Meta · Proprietary
2.87%±0.74% 0.83%±1.89% 10.75%±2.04% 6.31%±1.46% 1.17%±1.34% 0.69%±0.16% 55.0K
41 44
35 - 48
Minimax M3
MiniMax · MiniMax Community License
3.78%±1.12% 8.11%±3.12% 8.95%±3.36% 6.27%±2.20% 4.07%±1.00% 0.36%±0.21% 21.5K
42 45
36 - 48
Mimo V2.5 Pro
小米 · MIT
3.97%±1.11% 4.99%±2.98% 9.69%±3.16% 2.32%±2.09% 2.42%±1.96% 0.44%±0.39% 21.8K
43 46
35 - 49
Qwen3.7 Plus
阿里巴巴 · Proprietary
4.21%±1.46% 6.01%±4.05% 12.83%±3.96% 3.44%±3.10% 1.68%±2.23% 0.45%±0.45% 11.9K
44 41
38 - 49
Gemini 3.5 Flash (High)
Google · Proprietary
4.43%±1.01% 2.35%±2.43% 3.25%±3.02% 9.21%±1.83% 6.96%±2.17% 0.37%±0.26% 49.5K
45 42
37 - 49
Gemini 3.6 Flash (High)
Google · Proprietary
4.58%±1.31% 2.89%±3.49% 8.88%±3.75% 4.14%±2.62% 7.65%±1.89% 0.67%±0.17% 10.7K
46 43
41 - 49
Gemini 3.1 Pro Preview
Google · Proprietary
4.91%±1.13% 4.76%±2.80% 0.78%±3.30% 3.01%±1.92% 16.34%±2.04% 0.33%±0.43% 42.1K
47 47
41 - 51
Gemini 3.5 Flash (Medium)
Google · Proprietary
5.68%±1.85% 9.30%±4.58% 5.06%±5.04% 5.93%±3.47% 7.93%±3.43% 0.16%±1.15% 8.0K
48 48
43 - 51
Inkling Small
Thinky · Apache 2.0
7.19%±2.00% 20.15%±6.11% 18.31%±5.32% 8.55%±4.86% 11.66%±1.40% 0.58%±0.73% 6.2K
49 50
47 - 51
Inkling
Thinky · Apache 2.0
7.52%±1.31% 15.90%±3.96% 18.89%±3.49% 11.23%±2.92% 8.05%±1.29% 0.35%±0.25% 22.5K
50 49
47 - 52
Mistral Medium 3.5
Mistral · Modified MIT
8.13%±1.89% 17.19%±5.00% 12.23%±5.33% 4.32%±4.25% 5.41%±2.38% 1.49%±0.94% 5.0K
51 51
41 - 55
Solar Pro 4
Upstage · Proprietary
8.32%±4.05% 9.13%±9.16% 10.78%±11.67% 0.58%±8.34% 21.92%±8.84% 0.36%±1.25% 3.5K
52 54
50 - 55
Minimax M2.7
MiniMax · Modified MIT
10.96%±1.36% 10.40%±3.66% 20.45%±3.33% 6.51%±3.09% 17.98%±2.82% 0.53%±0.24% 21.9K
53 53
51 - 57
Gemini 3.5 Flash Lite
Google · Proprietary
12.78%±1.56% 13.57%±4.43% 19.62%±3.52% 11.03%±3.37% 18.48%±3.22% 1.20%±0.83% 13.2K
54 52
51 - 57
Grok 4.3 (High)
SpaceXAI · Proprietary
12.83%±1.42% 14.73%±2.96% 16.18%±2.81% 12.55%±1.94% 21.19%±5.27% 0.50%±0.17% 36.6K
55 56
51 - 57
Grok Build 0.1
SpaceXAI · Proprietary
13.36%±1.49% 9.26%±3.05% 15.78%±3.06% 6.90%±2.80% 35.26%±5.02% 0.38%±0.17% 42.2K
56 55
53 - 57
Gemini 3 Flash
Google · Proprietary
14.21%±1.40% 13.33%±2.69% 14.76%±2.47% 11.99%±1.93% 29.29%±4.25% 1.67%±3.29% 41.8K
57 57
53 - 58
Nemotron 3 Ultra
NVIDIA · OpenMDW-1.1
15.96%±3.17% 19.46%±7.38% 18.32%±7.57% 11.14%±6.49% 31.26%±8.90% 0.40%±0.25% 6.7K
58 58
57 - 59
Grok 4.3
SpaceXAI · Proprietary
20.82%±2.13% 17.19%±2.82% 17.85%±2.46% 13.31%±1.93% 56.30%±9.71% 0.56%±0.17% 41.2K
59 59
58 - 59
Gemma 4 31B
Google · Apache 2.0
24.13%±3.47% 7.17%±2.94% 7.81%±3.35% 10.14%±2.68% 59.04%±13.44% 36.48%±9.20% 30.3K
🔍

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