社区运行状况
| 注册会员 | 1205 |
| 主题 | 846 |
| 模型 | 3026 |
| 技能包 | 13874 |
| 数据集 | 1047 |
| 论文 | 380 |
| 开源项目 | 602 |
| 模型名称 | 厂商 | 智能评分 | 编程能力 | 智能体能力 | 速度评分 |
|---|---|---|---|---|---|
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) |  Anthropic |
59.86
|
61.98
|
80.60
|
—
|
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic |
55.69
|
56.71
|
77.81
|
63.42
|
| GPT-5.5 (xhigh) |  OpenAI |
54.84
|
59.12
|
74.12
|
58.13
|
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | Anthropic |
53.53
|
52.51
|
71.29
|
50.77
|
| GPT-5.5 (high) | OpenAI |
53.13
|
58.53
|
71.95
|
49.12
|
| GLM-5.2 (max) |  Z AI |
50.67
|
50.66
|
75.90
|
105.25
|
| Gemini 3.5 Flash (high) |  Google |
50.20
|
44.98
|
70.30
|
153.43
|
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | Anthropic |
47.21
|
50.94
|
63.00
|
54.58
|
| GPT-5.5 (medium) | OpenAI |
47.14
|
56.21
|
69.39
|
52.65
|
| Gemini 3.1 Pro Preview | Google |
46.46
|
55.50
|
59.09
|
122.40
|
| Qwen3.7 Max |  Alibaba |
45.99
|
50.12
|
66.56
|
91.92
|
| Gemini 3.5 Flash (medium) | Google |
45.38
|
43.93
|
70.43
|
159.88
|
| MiniMax-M3 |  MiniMax |
44.44
|
43.41
|
68.62
|
62.92
|
| DeepSeek V4 Pro (Reasoning, Max Effort) |  DeepSeek |
44.27
|
47.47
|
67.19
|
63.96
|
| GPT-5.3 Codex (xhigh) | OpenAI |
44.27
|
53.10
|
60.54
|
74.38
|
| Muse Spark |  Meta |
43.06
|
47.47
|
61.99
|
—
|
| Kimi K2.6 |  Kimi |
42.84
|
47.12
|
65.97
|
44.14
|
| Claude Opus 4.7 (Non-reasoning, High Effort) | Anthropic |
42.68
|
53.07
|
64.64
|
47.31
|
| MiMo-V2.5-Pro |  Xiaomi |
42.24
|
45.53
|
67.44
|
36.76
|
| Kimi K2.7 Code | Kimi |
41.95
|
45.62
|
61.93
|
50.71
|
| GPT-5.5 (low) | OpenAI |
41.73
|
52.06
|
59.69
|
51.77
|
| DeepSeek V4 Pro (Reasoning, High Effort) | DeepSeek |
40.83
|
43.25
|
66.65
|
61.31
|
| DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek |
40.28
|
38.71
|
61.28
|
95.82
|
| GLM-5.1 (Reasoning) | Z AI |
40.16
|
43.37
|
67.05
|
68.16
|
| MiMo-V2.5 | Xiaomi |
40.14
|
42.13
|
65.53
|
71.45
|
| GPT-5.4 mini (xhigh) | OpenAI |
39.98
|
51.48
|
58.88
|
170.35
|
| Qwen3.6 Plus | Alibaba |
39.56
|
42.87
|
61.67
|
51.47
|
| Qwen3.7 Plus | Alibaba |
38.98
|
46.48
|
65.13
|
51.97
|
| GPT-5.4 nano (xhigh) | OpenAI |
38.24
|
43.91
|
47.60
|
156.69
|
| MiniMax-M2.7 | MiniMax |
38.13
|
41.93
|
61.49
|
42.60
|
| GLM-5-Turbo | Z AI |
38.06
|
36.77
|
66.13
|
—
|
| Nemotron 3 Ultra 550B A55B (Reasoning) |  NVIDIA |
37.76
|
37.55
|
57.06
|
155.34
|
| Grok 4.3 (high) |  xAI |
37.58
|
41.03
|
65.89
|
168.10
|
| DeepSeek V4 Flash (Reasoning, High Effort) | DeepSeek |
37.36
|
39.76
|
62.33
|
—
|
| Qwen3.6 27B (Reasoning) | Alibaba |
37.05
|
36.50
|
62.85
|
55.53
|
| MiMo-V2-Omni-0327 | Xiaomi |
36.39
|
36.89
|
58.63
|
70.11
|
| Grok 4.3 (medium) | xAI |
36.00
|
35.06
|
57.47
|
155.59
|
| Claude Sonnet 4.6 (Non-reasoning, High Effort) | Anthropic |
35.89
|
46.43
|
61.62
|
43.36
|
| Grok 4.3 (low) | xAI |
35.44
|
31.64
|
50.42
|
125.56
|
| GLM-5.1 (Non-reasoning) | Z AI |
35.37
|
35.77
|
66.04
|
54.14
|
| MiMo-V2-Omni | Xiaomi |
34.99
|
35.46
|
58.56
|
69.53
|
| Gemini 3.5 Flash (minimal) | Google |
34.91
|
47.09
|
50.96
|
152.37
|
| Kimi K2.6 (Non-reasoning) | Kimi |
34.58
|
38.41
|
58.73
|
43.68
|
| GLM 5V Turbo (Reasoning) | Z AI |
34.49
|
36.22
|
61.07
|
—
|
| Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Anthropic |
34.26
|
42.98
|
57.45
|
44.02
|
| Qwen3.5 397B A17B (Reasoning) | Alibaba |
33.68
|
41.28
|
55.83
|
51.07
|
| Hy3-preview (Reasoning) |  Tencent |
33.58
|
36.46
|
55.67
|
123.94
|
| GPT-5.5 Instant (May 2026) | OpenAI |
33.52
|
45.07
|
38.08
|
—
|
| MiMo-V2-Flash (Feb 2026) | Xiaomi |
33.22
|
33.48
|
48.76
|
157.94
|
| GPT-5.5 (Non-reasoning) | OpenAI |
32.74
|
48.61
|
50.24
|
49.17
|
| Qwen3.5 122B A10B (Reasoning) | Alibaba |
32.28
|
34.71
|
53.00
|
136.56
|
| Qwen3.5 397B A17B (Non-reasoning) | Alibaba |
31.98
|
37.43
|
53.32
|
51.51
|
| Qwen3.6 35B A3B (Reasoning) | Alibaba |
31.65
|
35.15
|
58.34
|
170.68
|
| DeepSeek V4 Pro (Non-reasoning) | DeepSeek |
31.22
|
38.36
|
63.27
|
75.53
|
| Qwen3.5 Omni Plus | Alibaba |
30.64
|
27.64
|
52.83
|
52.06
|
| Ring-2.6-1T |  InclusionAI |
30.57
|
33.31
|
51.51
|
130.82
|
| o3 | OpenAI |
30.40
|
38.40
|
36.09
|
98.01
|
| GPT-5.4 nano (medium) | OpenAI |
30.16
|
35.03
|
41.64
|
155.66
|
| Mistral Medium 3.5 |  Mistral |
29.95
|
35.42
|
53.16
|
80.81
|
| GPT-5.4 mini (medium) | OpenAI |
29.81
|
37.46
|
40.27
|
159.52
|
| Step 3.7 Flash |  StepFun |
29.73
|
37.09
|
59.53
|
358.19
|
| Claude 4.5 Haiku (Reasoning) | Anthropic |
29.58
|
32.61
|
40.16
|
106.64
|
| Gemma 4 31B (Reasoning) | Google |
29.35
|
38.71
|
40.94
|
33.79
|
| Command A+ |  Cohere |
29.29
|
29.28
|
40.90
|
194.41
|
| Qwen3.6 27B (Non-reasoning) | Alibaba |
29.28
|
26.56
|
60.86
|
57.73
|
| DeepSeek V4 Flash (Non-reasoning) | DeepSeek |
28.65
|
35.15
|
61.33
|
103.10
|
| JT-35B-Flash |  China Mobile |
28.36
|
28.88
|
52.25
|
—
|
| Qwen3.5 122B A10B (Non-reasoning) | Alibaba |
28.12
|
31.58
|
49.51
|
161.53
|
| MiMo-V2.5-Pro (Non-reasoning) | Xiaomi |
27.86
|
36.78
|
50.75
|
43.38
|
| Gemini 2.5 Pro | Google |
26.98
|
31.95
|
32.68
|
128.68
|
| Hy3-preview (Non-reasoning) | Tencent |
26.10
|
34.33
|
46.70
|
129.00
|
| Ling-2.6-1T | InclusionAI |
26.05
|
33.05
|
48.21
|
—
|
| Step 3.5 Flash 2603 | StepFun |
26.00
|
34.56
|
48.23
|
206.81
|
| Doubao Seed Code |  ByteDance Seed |
25.98
|
31.26
|
36.45
|
—
|
| Gemma 4 26B A4B (Reasoning) | Google |
25.69
|
22.44
|
32.15
|
—
|
| NVIDIA Nemotron 3 Super 120B A12B (Reasoning) | NVIDIA |
25.41
|
31.19
|
40.18
|
148.98
|
| Mercury 2 |  Inception |
25.33
|
30.56
|
39.74
|
943.74
|
| Gemini 3.1 Flash-Lite | Google |
25.04
|
30.13
|
25.67
|
280.35
|
| Qwen3.5 9B (Reasoning) | Alibaba |
24.97
|
25.34
|
37.42
|
57.90
|
| Gemma 4 31B (Non-reasoning) | Google |
24.85
|
33.90
|
39.39
|
34.76
|
| Grok 4.3 (Non-reasoning) | xAI |
24.75
|
25.09
|
48.80
|
151.31
|
| K-EXAONE (Reasoning) |  LG AI Research |
24.70
|
27.03
|
38.14
|
—
|
| Trinity Large Thinking |  Arcee AI |
24.47
|
27.19
|
42.61
|
181.80
|
| Qwen3.6 35B A3B (Non-reasoning) | Alibaba |
24.15
|
17.60
|
52.53
|
185.28
|
| gpt-oss-120b (high) | OpenAI |
23.83
|
28.62
|
37.87
|
340.25
|
| Claude 4.5 Haiku (Non-reasoning) | Anthropic |
23.71
|
29.64
|
32.59
|
94.62
|
| Qwen3.5 35B A3B (Non-reasoning) | Alibaba |
23.38
|
16.83
|
48.04
|
179.60
|
| MiMo-V2-Flash (Non-reasoning) | Xiaomi |
23.07
|
25.81
|
47.34
|
150.62
|
| EXAONE 4.5 33B | LG AI Research |
22.96
|
22.97
|
36.50
|
—
|
| HyperNova 60B 2605 |  Multiverse Computing |
22.14
|
26.65
|
32.02
|
345.80
|
| Gemma 4 12B (Reasoning) | Google |
22.00
|
24.85
|
24.63
|
122.27
|
| ERNIE 5.0 Thinking Preview |  Baidu |
21.92
|
29.17
|
39.74
|
—
|
| Nova 2.0 Pro Preview (medium) |  Amazon |
21.77
|
30.40
|
46.95
|
120.78
|
| Nemotron Cascade 2 30B A3B | NVIDIA |
21.25
|
25.75
|
26.15
|
—
|
| Qwen3 Coder Next | Alibaba |
21.18
|
22.89
|
42.10
|
74.38
|
| Nova 2.0 Omni (medium) | Amazon |
20.95
|
15.11
|
38.20
|
—
|
| Mistral Small 4 (Reasoning) | Mistral |
20.75
|
24.27
|
25.87
|
161.96
|
| North Mini Code | Cohere |
20.56
|
33.44
|
21.66
|
160.27
|
| Nova 2.0 Lite (high) | Amazon |
20.50
|
23.42
|
37.34
|
123.66
|
| Qwen3.5 9B (Non-reasoning) | Alibaba |
20.32
|
21.35
|
41.10
|
—
|
| Magistral Medium 1.2 | Mistral |
20.11
|
21.66
|
24.45
|
40.09
|
| Gemma 4 26B A4B (Non-reasoning) | Google |
20.10
|
29.09
|
28.93
|
42.73
|
| Qwen3.5 4B (Reasoning) | Alibaba |
20.09
|
17.49
|
32.46
|
25.14
|
| Qwen3 Next 80B A3B (Reasoning) | Alibaba |
19.77
|
19.49
|
23.56
|
170.32
|
| Nova 2.0 Pro Preview (low) | Amazon |
19.50
|
24.50
|
37.71
|
119.96
|
| Ling 2.6 Flash | InclusionAI |
19.25
|
23.17
|
38.06
|
—
|
| Nova 2.0 Lite (medium) | Amazon |
19.00
|
23.88
|
32.85
|
126.88
|
| Qwen3.5 Omni Flash | Alibaba |
18.99
|
14.04
|
41.63
|
240.21
|
| JT-MINI | China Mobile |
18.53
|
21.19
|
42.36
|
—
|
| Nova 2.0 Lite (low) | Amazon |
17.81
|
13.64
|
27.77
|
135.37
|
| gpt-oss-120b (low) | OpenAI |
17.70
|
15.53
|
28.04
|
351.53
|
| GPT-5.4 nano (Non-Reasoning) | OpenAI |
17.61
|
27.89
|
25.92
|
160.48
|
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA |
17.53
|
18.97
|
19.14
|
43.62
|
| LongCat Flash Lite |  LongCat |
17.22
|
16.52
|
38.76
|
—
|
| K-EXAONE (Non-reasoning) | LG AI Research |
16.74
|
13.53
|
31.22
|
—
|
| GPT-5.4 mini (Non-Reasoning) | OpenAI |
16.62
|
25.32
|
25.01
|
156.77
|
| Nova 2.0 Omni (low) | Amazon |
16.56
|
13.95
|
22.61
|
—
|
| Nova 2.0 Pro Preview (Non-reasoning) | Amazon |
16.42
|
20.49
|
23.88
|
117.89
|
| Mi:dm K 2.5 Pro |  Korea Telecom |
16.42
|
12.57
|
36.76
|
—
|
| Mistral Large 3 | Mistral |
16.19
|
22.68
|
21.70
|
50.50
|
| Qwen3.5 4B (Non-reasoning) | Alibaba |
16.00
|
13.67
|
36.26
|
22.87
|
| INTELLECT-3 |  Prime Intellect |
15.61
|
19.10
|
19.81
|
—
|
| Devstral 2 | Mistral |
15.49
|
23.66
|
21.86
|
50.24
|
| Solar Open 100B (Reasoning) |  Upstage |
15.15
|
10.47
|
24.29
|
—
|
| Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA |
14.93
|
14.81
|
23.87
|
281.06
|
| gpt-oss-20B (high) | OpenAI |
14.89
|
18.53
|
27.60
|
207.75
|
| gpt-oss-20B (low) | OpenAI |
14.34
|
14.37
|
21.86
|
224.30
|
| Llama 4 Maverick | Meta |
14.27
|
15.58
|
7.22
|
93.53
|
| Solar Pro 3 | Upstage |
14.14
|
13.27
|
34.92
|
—
|
| Qwen3 Next 80B A3B Instruct | Alibaba |
13.72
|
15.27
|
14.19
|
167.39
|
| Gemma 4 12B (Non-reasoning) | Google |
13.19
|
17.49
|
12.38
|
—
|
| Devstral Small 2 | Mistral |
13.14
|
20.72
|
20.79
|
49.52
|
| Motif-2-12.7B-Reasoning |  Motif Technologies |
12.79
|
11.94
|
19.17
|
—
|
| Nova Premier | Amazon |
12.73
|
13.84
|
16.43
|
31.93
|
| Gemma 4 E4B (Reasoning) | Google |
12.50
|
13.70
|
6.92
|
—
|
| Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA |
12.42
|
15.15
|
9.36
|
48.06
|
| Mistral Small 4 (Non-reasoning) | Mistral |
12.37
|
16.45
|
18.55
|
151.64
|
| MiniCPM5-1B (Reasoning) |  OpenBMB |
11.96
|
1.47
|
27.00
|
—
|
| Magistral Small 1.2 | Mistral |
11.95
|
14.76
|
17.33
|
106.26
|
| Sarvam 105B (high) |  Sarvam |
11.94
|
9.81
|
24.69
|
107.64
|
| Nova 2.0 Lite (Non-reasoning) | Amazon |
11.83
|
12.53
|
21.06
|
108.24
|
| MiniCPM5-1B (Non-reasoning) | OpenBMB |
11.74
|
0.46
|
27.49
|
—
|
| EXAONE 4.0 32B (Reasoning) | LG AI Research |
10.59
|
13.98
|
9.53
|
—
|
| Nova 2.0 Omni (Non-reasoning) | Amazon |
10.53
|
13.84
|
14.91
|
—
|
| Qwen3.5 2B (Reasoning) | Alibaba |
10.24
|
3.45
|
23.00
|
22.58
|
| Nanbeige4.1-3B |  Nanbeige |
10.05
|
8.87
|
7.21
|
—
|
| Llama 4 Scout | Meta |
10.04
|
6.68
|
5.17
|
110.54
|
| Ministral 3 14B | Mistral |
9.96
|
10.90
|
17.39
|
93.49
|
| Falcon-H1R-7B |  TII UAE |
9.79
|
9.81
|
9.26
|
—
|
| Qwen3 Omni 30B A3B (Reasoning) | Alibaba |
9.63
|
12.71
|
10.61
|
86.26
|
| Step3 VL 10B | StepFun |
9.47
|
13.91
|
5.36
|
—
|
| Gemma 4 E2B (Reasoning) | Google |
9.26
|
9.00
|
6.92
|
—
|
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | NVIDIA |
9.08
|
13.09
|
3.80
|
51.45
|
| ERNIE 4.5 300B A47B | Baidu |
9.02
|
14.53
|
0.00
|
—
|
| Solar Pro 2 (Reasoning) | Upstage |
8.99
|
12.09
|
11.43
|
—
|
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | NVIDIA |
8.96
|
11.75
|
7.12
|
282.61
|
| Ministral 3 8B | Mistral |
8.92
|
9.97
|
16.66
|
87.20
|
| Gemma 4 E4B (Non-reasoning) | Google |
8.91
|
6.36
|
8.67
|
—
|
| Granite 4.1 30B |  IBM |
8.86
|
10.12
|
14.04
|
—
|
| NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA |
8.84
|
8.34
|
9.43
|
61.26
|
| NVIDIA Nemotron 3 Nano 4B | NVIDIA |
8.77
|
10.02
|
9.75
|
—
|
| Qwen3.5 2B (Non-reasoning) | Alibaba |
8.76
|
4.92
|
27.19
|
24.31
|
| Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA |
8.68
|
10.47
|
8.38
|
48.14
|
| Llama 3.3 Instruct 70B | Meta |
8.59
|
10.70
|
9.09
|
90.69
|
| Kimi Linear 48B A3B Instruct | Kimi |
8.53
|
14.21
|
—
|
—
|
| Llama 3.1 Instruct 405B | Meta |
8.50
|
14.50
|
6.34
|
47.94
|
| LFM2.5-8B-A1B |  Liquid AI |
8.32
|
5.62
|
5.36
|
222.57
|
| Ring-flash-2.0 | InclusionAI |
8.16
|
10.64
|
0.00
|
—
|
| Solar Pro 2 (Non-reasoning) | Upstage |
7.77
|
11.29
|
12.71
|
—
|
| Command A | Cohere |
7.67
|
9.88
|
5.07
|
72.21
|
| Llama 3.1 Nemotron Instruct 70B | NVIDIA |
7.64
|
10.78
|
7.70
|
295.40
|
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA |
7.39
|
15.76
|
8.48
|
61.26
|
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA |
7.38
|
7.49
|
7.80
|
109.39
|
| MiniCPM-V 4.6 1.3B | OpenBMB |
6.92
|
0.69
|
29.24
|
—
|
| Granite 4.1 8B | IBM |
6.67
|
7.25
|
10.67
|
121.18
|
| Sarvam 30B (high) | Sarvam |
6.64
|
7.92
|
11.50
|
165.56
|
| Gemma 4 E2B (Non-reasoning) | Google |
6.41
|
8.31
|
7.41
|
—
|
| R1 1776 |  Perplexity |
6.31
|
—
|
—
|
—
|
| Llama 3.2 Instruct 90B (Vision) | Meta |
6.23
|
—
|
—
|
57.37
|
| EXAONE 4.0 32B (Non-reasoning) | LG AI Research |
6.01
|
9.42
|
1.36
|
—
|
| Ministral 3 3B | Mistral |
5.63
|
4.78
|
11.44
|
179.19
|
| Jamba 1.7 Large |  AI21 Labs |
5.30
|
7.77
|
4.48
|
59.48
|
| Granite 4.0 H Small | IBM |
5.24
|
8.50
|
5.75
|
400.47
|
| Qwen3 Omni 30B A3B Instruct | Alibaba |
5.11
|
7.22
|
5.46
|
94.96
|
| Qwen3.5 0.8B (Reasoning) | Alibaba |
4.97
|
0.00
|
15.89
|
29.45
|
| LFM2 24B A2B | Liquid AI |
4.95
|
3.63
|
3.70
|
115.80
|
| Phi-4 |  Microsoft |
4.87
|
11.21
|
0.00
|
35.92
|
| Nova Micro | Amazon |
4.74
|
4.14
|
4.68
|
305.69
|
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | NVIDIA |
4.58
|
5.86
|
6.43
|
212.63
|
| Phi-4 Multimodal Instruct | Microsoft |
4.53
|
—
|
—
|
14.25
|
| Qwen3.5 0.8B (Non-reasoning) | Alibaba |
4.42
|
0.96
|
21.73
|
20.84
|
| Jamba Reasoning 3B | AI21 Labs |
4.13
|
2.47
|
5.26
|
—
|
| Reka Flash 3 |  Reka AI |
4.06
|
8.91
|
0.00
|
—
|
| Ling-mini-2.0 | InclusionAI |
3.75
|
5.02
|
4.39
|
—
|
| Llama 3.2 Instruct 11B (Vision) | Meta |
3.33
|
4.25
|
4.87
|
49.32
|
| Granite 4.1 3B | IBM |
3.17
|
5.49
|
6.53
|
—
|
| Phi-4 Mini Instruct | Microsoft |
3.03
|
3.59
|
2.73
|
42.47
|
| Exaone 4.0 1.2B (Reasoning) | LG AI Research |
2.90
|
3.09
|
5.46
|
—
|
| Exaone 4.0 1.2B (Non-reasoning) | LG AI Research |
2.77
|
2.47
|
6.82
|
—
|
| LFM2.5-1.2B-Thinking | Liquid AI |
2.75
|
1.39
|
6.53
|
—
|
| Jamba 1.7 Mini | AI21 Labs |
2.73
|
3.09
|
4.19
|
—
|
| LFM2 2.6B | Liquid AI |
2.71
|
1.35
|
4.48
|
339.38
|
| LFM2.5-1.2B-Instruct | Liquid AI |
2.71
|
0.77
|
3.61
|
492.70
|
| Granite 4.0 H 1B | IBM |
2.66
|
2.74
|
6.53
|
—
|
| Gemma 3 270M | Google |
2.41
|
0.00
|
3.02
|
—
|
| Apertus 70B Instruct |  Swiss AI Initiative |
2.40
|
1.89
|
4.29
|
—
|
| Granite 4.0 Micro | IBM |
2.37
|
4.98
|
4.19
|
—
|
| Granite 4.0 1B | IBM |
2.07
|
2.89
|
7.60
|
—
|
| LFM2 8B A1B | Liquid AI |
1.78
|
2.28
|
3.51
|
—
|
| LFM2.5-VL-1.6B | Liquid AI |
1.01
|
1.00
|
2.83
|
487.31
|
| Apertus 8B Instruct | Swiss AI Initiative |
1.00
|
1.35
|
3.80
|
—
|
| Granite 4.0 350M | IBM |
1.00
|
0.31
|
4.39
|
—
|
| Granite 4.0 H 350M | IBM |
1.00
|
0.58
|
4.87
|
—
|
| Tiny Aya Global | Cohere |
1.00
|
1.20
|
0.00
|
—
|
| EXAONE 4.5 33B (Non-reasoning) | LG AI Research |
—
|
—
|
—
|
—
|
| GPT-5.5 Pro (xhigh) | OpenAI |
—
|
—
|
—
|
—
|
| Gemini 3 Deep Think | Google |
—
|
—
|
—
|
—
|
| Mi:dm K 2.5 Pro Preview | Korea Telecom |
—
|
11.94
|
—
|
—
|