社区运行状况
| 注册会员 | 1376 |
| 主题 | 846 |
| 模型 | 3026 |
| 技能包 | 13874 |
| 数据集 | 1047 |
| 论文 | 585 |
| 开源项目 | 665 |
| 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 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) |  Anthropic |
53.35
|
—
|
—
|
65.82
|
| Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | Anthropic |
53.20
|
—
|
—
|
61.80
|
| GPT-6 Astra (max) |  OpenAI |
52.67
|
—
|
—
|
65.28
|
| GPT-6 Astra (xhigh) | OpenAI |
52.39
|
—
|
—
|
54.89
|
| Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | Anthropic |
51.15
|
—
|
—
|
55.77
|
| GPT-6 Astra (high) | OpenAI |
50.92
|
—
|
—
|
54.44
|
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic |
50.78
|
—
|
—
|
56.45
|
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic |
49.68
|
—
|
—
|
54.40
|
| GPT-6 Astra (medium) | OpenAI |
49.57
|
—
|
—
|
53.61
|
| Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) | Anthropic |
48.92
|
—
|
—
|
56.51
|
| Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic |
48.12
|
—
|
—
|
57.38
|
| Muse Spark 1.3 (max) |  Meta |
48.09
|
—
|
—
|
222.13
|
| GPT-6 Astra (Non-reasoning) | OpenAI |
47.85
|
76.25
|
48.00
|
—
|
| GPT-5.6 Sol (max) | OpenAI |
46.97
|
—
|
—
|
84.24
|
| Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) | Anthropic |
46.82
|
—
|
—
|
55.24
|
| Grok 4.7 (xhigh) |  SpaceXAI |
46.45
|
—
|
—
|
39.46
|
| Grok 4.7 (high) | SpaceXAI |
46.33
|
—
|
—
|
55.33
|
| MiMo-V2.6-Pro |  Xiaomi |
46.32
|
—
|
—
|
124.50
|
| GPT-6 Astra (low) | OpenAI |
45.78
|
—
|
—
|
53.32
|
| Qwen3.8 Max (0902) |  Alibaba |
45.42
|
—
|
—
|
39.24
|
| Muse Spark 1.3 (xhigh) | Meta |
45.07
|
—
|
—
|
260.35
|
| Claude Opus 5 (Adaptive Reasoning, Medium Effort) | Anthropic |
44.83
|
—
|
—
|
57.71
|
| GLM-5.3 (max) |  Z AI |
44.78
|
—
|
—
|
61.04
|
| Grok 4.6 (high) | SpaceXAI |
44.31
|
—
|
—
|
60.41
|
| Grok 4.6 (xhigh) | SpaceXAI |
44.20
|
—
|
—
|
58.19
|
| GPT-5.6 Sol (xhigh) | OpenAI |
44.01
|
—
|
—
|
72.30
|
| Step 5 Preview |  StepFun |
43.73
|
—
|
—
|
88.86
|
| Kimi K3 (max) |  Kimi |
43.59
|
—
|
—
|
40.63
|
| Grok 4.6 (medium) | SpaceXAI |
42.84
|
—
|
—
|
59.76
|
| GPT-5.6 Sol (high) | OpenAI |
42.35
|
—
|
—
|
71.20
|
| GPT-5.6 Terra (max) | OpenAI |
42.08
|
—
|
—
|
104.63
|
| GLM 5.3 Flash | Z AI |
41.81
|
—
|
—
|
89.44
|
| Gemini 3.8 Flash (high) |  Google |
40.93
|
—
|
—
|
343.52
|
| Qwen3.8 2.4T A95B | Alibaba |
39.89
|
—
|
—
|
39.06
|
| Qwen3.8-Flash-Next | Alibaba |
39.82
|
—
|
—
|
54.09
|
| Gemini 3.8 Flash (medium) | Google |
39.77
|
—
|
—
|
—
|
| DeepSeek V4.1 Flash (Reasoning, Max Effort) |  DeepSeek |
39.46
|
—
|
—
|
225.62
|
| Claude Opus 5 (Adaptive Reasoning, Low Effort) | Anthropic |
39.35
|
—
|
—
|
59.92
|
| GPT-5.6 Sol (medium) | OpenAI |
39.24
|
—
|
—
|
63.69
|
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic |
38.16
|
—
|
—
|
77.33
|
| GPT-5.6 Terra (xhigh) | OpenAI |
37.95
|
—
|
—
|
93.60
|
| GPT-5.6 Luna (max) | OpenAI |
37.32
|
—
|
—
|
158.73
|
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | DeepSeek |
36.00
|
—
|
—
|
73.73
|
| Agnes 3.0 Flash |  Sapiens AI |
35.50
|
—
|
—
|
—
|
| Agnes 2.5 Pro Beta | Sapiens AI |
35.24
|
—
|
—
|
—
|
| Grok 4.6 (low) | SpaceXAI |
35.12
|
—
|
—
|
56.85
|
| DeepSeek V4 Flash Vision (Reasoning, Max Effort) | DeepSeek |
34.84
|
—
|
—
|
236.34
|
| GPT-5.6 Luna (xhigh) | OpenAI |
34.56
|
—
|
—
|
160.07
|
| Kimi K3 (low) | Kimi |
34.46
|
—
|
—
|
37.47
|
| Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic |
34.38
|
—
|
—
|
71.15
|
| GPT-5.6 Terra (high) | OpenAI |
34.24
|
—
|
—
|
88.18
|
| Qwen3.8 27B (xhigh) | Alibaba |
33.70
|
—
|
—
|
44.55
|
| Motif 3 |  Motif Technologies |
33.57
|
—
|
—
|
—
|
| GPT-5.6 Sol (low) | OpenAI |
33.47
|
—
|
—
|
67.07
|
| Gemini 3.8 Flash (low) | Google |
33.45
|
—
|
—
|
—
|
| GPT-5.3 Codex (xhigh) | OpenAI |
32.50
|
—
|
—
|
175.62
|
| Motif 3 (Beta) | Motif Technologies |
32.31
|
—
|
—
|
—
|
| GPT-5.6 Luna (high) | OpenAI |
32.12
|
—
|
—
|
140.34
|
| Claude Sonnet 5 (Adaptive Reasoning, High Effort) | Anthropic |
31.66
|
—
|
—
|
70.45
|
| K2 Horizon 375B A23B |  Institute of Foundation Models |
30.50
|
—
|
—
|
—
|
| Apodex 1.1 |  Apodex |
30.37
|
—
|
—
|
—
|
| GPT-5.6 Terra (medium) | OpenAI |
30.09
|
—
|
—
|
90.26
|
| Gemini 3.1 Pro Preview | Google |
29.72
|
—
|
—
|
121.84
|
| MiniMax-M3 |  MiniMax |
29.22
|
—
|
—
|
156.24
|
| GPT-5.6 Sol (Non-reasoning) | OpenAI |
28.33
|
—
|
—
|
63.82
|
| Nex-N2-Pro (based on Qwen3.5-397B-A17B) |  Nex AGI |
28.20
|
—
|
—
|
—
|
| Solar Pro 4 |  Upstage |
28.15
|
—
|
—
|
66.12
|
| Claude Sonnet 5 (Adaptive Reasoning, Medium Effort) | Anthropic |
28.05
|
—
|
—
|
67.05
|
| Inkling Small |  Thinking Machines |
27.78
|
—
|
—
|
193.56
|
| Qwen3.8 27B (medium) | Alibaba |
27.55
|
—
|
—
|
52.75
|
| GPT-5.6 Terra (low) | OpenAI |
27.50
|
—
|
—
|
86.66
|
| JT-4.1 Flash 236B A21B |  China Mobile |
27.29
|
—
|
—
|
—
|
| Agnes 2.5 Pro Alpha | Sapiens AI |
26.77
|
—
|
—
|
187.05
|
| Quasar 438B (max, based on GLM-5.2) |  Multiverse Computing |
26.74
|
—
|
—
|
150.61
|
| Qwen3.8 27B (low) | Alibaba |
26.20
|
—
|
—
|
52.78
|
| GPT-5.5 Instant (June 2026) | OpenAI |
26.01
|
—
|
—
|
143.56
|
| MiMo-V2.5-Pro | Xiaomi |
25.99
|
—
|
—
|
46.47
|
| Kimi K2.7 Code | Kimi |
25.81
|
—
|
—
|
60.99
|
| K2 Horizon MoVA 36B A4B |  MBZUAI Institute of Foundation Models |
25.67
|
—
|
—
|
—
|
| K2 Horizon MoVA 36B A4B | Institute of Foundation Models |
25.30
|
—
|
—
|
—
|
| Hy3 |  Tencent |
25.30
|
—
|
—
|
90.60
|
| MiMo-V2.5 | Xiaomi |
25.17
|
—
|
—
|
34.26
|
| Qwen3.7 Plus | Alibaba |
25.16
|
—
|
—
|
68.54
|
| GPT-5.6 Luna (medium) | OpenAI |
25.04
|
—
|
—
|
148.34
|
| Inkling (xhigh) | Thinking Machines |
24.98
|
—
|
—
|
99.87
|
| Ling 3.0 Flash |  InclusionAI |
24.94
|
—
|
—
|
326.31
|
| Solar Open2 250B | Upstage |
24.74
|
—
|
—
|
—
|
| Ling-3.0-flash-VL | InclusionAI |
24.57
|
—
|
—
|
148.07
|
| Claude Sonnet 5 (Adaptive Reasoning, Low Effort) | Anthropic |
24.26
|
—
|
—
|
63.81
|
| Claude Sonnet 5 (Non-reasoning, High Effort) | Anthropic |
23.20
|
—
|
—
|
65.08
|
| Nemotron 3 Ultra 550B A55B (Reasoning) |  NVIDIA |
22.93
|
—
|
—
|
178.96
|
| A.X-K2 |  SK Telecom |
22.70
|
—
|
—
|
—
|
| Ling-3.0-flash-Fin | InclusionAI |
22.60
|
—
|
—
|
156.20
|
| MiMo-V2-Flash (Feb 2026) | Xiaomi |
22.44
|
—
|
—
|
—
|
| Gemini 3.5 Flash-Lite | Google |
22.17
|
—
|
—
|
386.37
|
| DeepSeek V4 Flash (Non-reasoning) | DeepSeek |
22.07
|
—
|
—
|
—
|
| G9v3-39A5B |  AI9Stars |
21.83
|
—
|
—
|
—
|
| KAT Coder Pro V2 |  KwaiKAT |
21.70
|
—
|
—
|
—
|
| Qwen3.5 397B A17B (Non-reasoning) | Alibaba |
21.44
|
—
|
—
|
89.37
|
| K2 Horizon 7B | MBZUAI Institute of Foundation Models |
21.05
|
—
|
—
|
—
|
| GPT-5.6 Luna (low) | OpenAI |
21.01
|
—
|
—
|
145.32
|
| GPT-5.6 Terra (Non-reasoning) | OpenAI |
20.78
|
—
|
—
|
84.31
|
| K2 Horizon 7B | Institute of Foundation Models |
20.60
|
—
|
—
|
—
|
| Qwen3.5 Omni Plus | Alibaba |
20.38
|
—
|
—
|
92.85
|
| o3 | OpenAI |
20.20
|
—
|
—
|
137.60
|
| Qwen3.8 27B (Non-reasoning) | Alibaba |
20.15
|
—
|
—
|
49.09
|
| K-EXAONE 2.0 0803 |  LG AI Research |
19.69
|
—
|
—
|
—
|
| Step 3.7 Flash | StepFun |
19.48
|
—
|
—
|
194.84
|
| LongCat 2.0 |  LongCat |
19.11
|
—
|
—
|
—
|
| Gemma 4 31B (Reasoning) | Google |
18.98
|
—
|
—
|
35.45
|
| JT-35B-Flash | China Mobile |
18.66
|
—
|
—
|
—
|
| Qwen3.5 397B A17B (Reasoning) | Alibaba |
18.42
|
—
|
—
|
88.86
|
| MiMo-V2.5-Pro (Non-reasoning) | Xiaomi |
18.29
|
—
|
—
|
46.52
|
| Qwen3.6 35B A3B (Reasoning) | Alibaba |
18.23
|
—
|
—
|
116.60
|
| Qwen3.5 122B A10B (Non-reasoning) | Alibaba |
17.75
|
—
|
—
|
144.86
|
| Muse Glimmer (high) | Meta |
17.48
|
—
|
—
|
94.19
|
| Doubao Seed Code |  ByteDance Seed |
16.95
|
—
|
—
|
—
|
| Claude 4.5 Haiku (Reasoning) | Anthropic |
16.88
|
—
|
—
|
90.31
|
| Gemma 4 26B A4B (Reasoning) | Google |
16.67
|
—
|
—
|
—
|
| Ring-2.6-1T | InclusionAI |
16.62
|
—
|
—
|
130.31
|
| K2 Horizon 3.7B | MBZUAI Institute of Foundation Models |
16.16
|
—
|
—
|
—
|
| K2 Horizon 3.7B | Institute of Foundation Models |
15.61
|
—
|
—
|
—
|
| Qwen3.5 122B A10B (Reasoning) | Alibaba |
15.57
|
—
|
—
|
127.35
|
| GPT-5.6 Luna (Non-reasoning) | OpenAI |
15.53
|
—
|
—
|
150.74
|
| Claude 4.5 Haiku (Non-reasoning) | Anthropic |
15.41
|
—
|
—
|
87.79
|
| Ling 3.0 Tiny | InclusionAI |
15.29
|
—
|
—
|
56.87
|
| Qwen3.6 35B A3B (Non-reasoning) | Alibaba |
15.23
|
—
|
—
|
123.65
|
| Granite 4.2 30B |  IBM |
14.83
|
—
|
—
|
72.96
|
| ERNIE 5.0 Thinking Preview |  Baidu |
14.26
|
—
|
—
|
—
|
| Mistral Medium 3.5 |  Mistral |
14.19
|
—
|
—
|
138.12
|
| Gemma 4 12B (Reasoning) | Google |
14.18
|
—
|
—
|
112.69
|
| Nova 2.0 Pro Preview (medium) |  Amazon |
14.16
|
—
|
—
|
114.70
|
| Gemma 4 31B (Non-reasoning) | Google |
13.92
|
—
|
—
|
35.71
|
| Mercury 2 |  Inception |
13.77
|
—
|
—
|
655.23
|
| Qwen3.5 9B (Reasoning) | Alibaba |
13.65
|
—
|
—
|
57.38
|
| Nova 2.0 Omni (medium) | Amazon |
13.65
|
—
|
—
|
—
|
| Apriel-v1.6-15B-Thinker |  ServiceNow |
13.40
|
—
|
—
|
—
|
| Nova 2.0 Lite (high) | Amazon |
13.37
|
—
|
—
|
162.85
|
| Qwen3.5 9B (Non-reasoning) | Alibaba |
13.27
|
—
|
—
|
91.69
|
| EXAONE 4.5 33B | LG AI Research |
13.21
|
—
|
—
|
—
|
| Command A+ |  Cohere |
13.13
|
—
|
—
|
234.25
|
| Gemma 4 26B A4B (Non-reasoning) | Google |
13.13
|
—
|
—
|
75.49
|
| Qwen3.5 4B (Reasoning) | Alibaba |
13.12
|
—
|
—
|
20.29
|
| Nemotron 3.5 Lightning | NVIDIA |
12.86
|
—
|
—
|
296.36
|
| Nemotron 3 Super 120B A12B (Reasoning) | NVIDIA |
12.83
|
—
|
—
|
166.73
|
| Nova 2.0 Pro Preview (low) | Amazon |
12.78
|
—
|
—
|
112.44
|
| Nova 2.0 Lite (medium) | Amazon |
12.48
|
—
|
—
|
159.80
|
| Qwen3.5 Omni Flash | Alibaba |
12.47
|
—
|
—
|
246.29
|
| MiniCPM5-2B |  OpenBMB |
12.46
|
—
|
—
|
—
|
| JT-MINI | China Mobile |
12.21
|
—
|
—
|
—
|
| Magistral Medium 1.2 | Mistral |
11.83
|
—
|
—
|
—
|
| Nova 2.0 Lite (low) | Amazon |
11.80
|
—
|
—
|
157.41
|
| HyperNova 60B 2605 (high, based on gpt-oss-120b) | Multiverse Computing |
11.74
|
—
|
—
|
—
|
| Nemotron Cascade 2 30B A3B | NVIDIA |
11.67
|
—
|
—
|
—
|
| gpt-oss-120b (high) | OpenAI |
11.60
|
—
|
—
|
213.55
|
| K2 Think V2 | Institute of Foundation Models |
11.50
|
—
|
—
|
—
|
| LongCat Flash Lite | LongCat |
11.47
|
—
|
—
|
—
|
| HyperCLOVA X SEED Think (32B) |  Naver |
11.36
|
—
|
—
|
—
|
| Mistral Small 4 (Reasoning) | Mistral |
11.27
|
—
|
—
|
155.21
|
| Qwen3 Next 80B A3B (Reasoning) | Alibaba |
11.20
|
—
|
—
|
175.21
|
| Nova 2.0 Omni (low) | Amazon |
11.11
|
—
|
—
|
—
|
| Granite 4.2 8B | IBM |
11.08
|
—
|
—
|
88.90
|
| Mi:dm K 2.5 Pro |  Korea Telecom |
11.04
|
—
|
—
|
—
|
| G9v3-3B | AI9Stars |
10.84
|
—
|
—
|
—
|
| Trinity Large Thinking |  Arcee AI |
10.82
|
—
|
—
|
303.05
|
| Qwen3.5 4B (Non-reasoning) | Alibaba |
10.81
|
—
|
—
|
13.59
|
| INTELLECT-3 |  Prime Intellect |
10.61
|
—
|
—
|
—
|
| Solar Open 100B (Reasoning) | Upstage |
10.36
|
—
|
—
|
—
|
| Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA |
10.25
|
—
|
—
|
268.74
|
| gpt-oss-120b (low) | OpenAI |
10.21
|
—
|
—
|
208.17
|
| Llama 4 Maverick | Meta |
9.99
|
—
|
—
|
111.79
|
| Nova 2.0 Pro Preview (Non-reasoning) | Amazon |
9.96
|
—
|
—
|
103.04
|
| gpt-oss-20b (low) | OpenAI |
9.95
|
—
|
—
|
216.26
|
| North Mini Code | Cohere |
9.91
|
—
|
—
|
98.44
|
| K2-V2 (high) | Institute of Foundation Models |
9.87
|
—
|
—
|
—
|
| Qwen3 Next 80B A3B Instruct | Alibaba |
9.64
|
—
|
—
|
174.79
|
| DiffusionGemma 26B A4B | Google |
9.51
|
—
|
—
|
—
|
| Gemma 4 12B (Non-reasoning) | Google |
9.38
|
—
|
—
|
112.37
|
| Mistral Large 3 | Mistral |
9.27
|
—
|
—
|
74.75
|
| Qwen3 Coder Next | Alibaba |
9.24
|
—
|
—
|
101.28
|
| Motif-2-12.7B-Reasoning | Motif Technologies |
9.19
|
—
|
—
|
—
|
| Nova Premier | Amazon |
9.16
|
—
|
—
|
—
|
| Granite 4.2 3B | IBM |
9.06
|
—
|
—
|
221.61
|
| K2-V2 (medium) | Institute of Foundation Models |
9.02
|
—
|
—
|
—
|
| Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA |
9.01
|
—
|
—
|
160.78
|
| Mistral Small 4 (Non-reasoning) | Mistral |
8.99
|
—
|
—
|
151.34
|
| Tri-21B-Think |  Trillion Labs |
8.99
|
—
|
—
|
—
|
| gpt-oss-20b (high) | OpenAI |
8.97
|
—
|
—
|
170.30
|
| Gemma 4 E4B (Reasoning) | Google |
8.91
|
—
|
—
|
45.85
|
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA |
8.90
|
—
|
—
|
131.35
|
| MiniCPM5-1B (Reasoning) | OpenBMB |
8.80
|
—
|
—
|
—
|
| Sarvam 105B (high) |  Sarvam |
8.79
|
—
|
—
|
—
|
| Nova 2.0 Lite (Non-reasoning) | Amazon |
8.74
|
—
|
—
|
149.07
|
| MiniCPM5-1B (Non-reasoning) | OpenBMB |
8.69
|
—
|
—
|
—
|
| Devstral 2 | Mistral |
8.62
|
—
|
—
|
132.07
|
| Magistral Small 1.2 | Mistral |
8.59
|
—
|
—
|
—
|
| Nanbeige4.1-3B |  Nanbeige |
8.40
|
—
|
—
|
—
|
| LFM2.5-2.6B |  Liquid AI |
8.39
|
—
|
—
|
—
|
| EXAONE 4.0 32B (Reasoning) | LG AI Research |
8.18
|
—
|
—
|
—
|
| Nova 2.0 Omni (Non-reasoning) | Amazon |
8.15
|
—
|
—
|
—
|
| Llama 4 Scout | Meta |
8.08
|
—
|
—
|
99.57
|
| Hermes 4 - Llama-3.1 70B (Reasoning) |  Nous Research |
7.91
|
—
|
—
|
—
|
| Falcon-H1R-7B |  TII UAE |
7.83
|
—
|
—
|
—
|
| Gemma 4 E2B (Reasoning) | Google |
7.77
|
—
|
—
|
—
|
| Qwen3 Omni 30B A3B (Reasoning) | Alibaba |
7.76
|
—
|
—
|
99.55
|
| Step3 VL 10B | StepFun |
7.69
|
—
|
—
|
—
|
| Llama 3.3 Instruct 70B | Meta |
7.66
|
—
|
—
|
78.80
|
| Devstral Small 2 | Mistral |
7.54
|
—
|
—
|
131.18
|
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | NVIDIA |
7.53
|
—
|
—
|
—
|
| ERNIE 4.5 300B A47B | Baidu |
7.50
|
—
|
—
|
—
|
| Hermes 4 - Llama-3.1 405B (Reasoning) | Nous Research |
7.49
|
—
|
—
|
40.25
|
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | NVIDIA |
7.48
|
—
|
—
|
133.95
|
| Gemma 4 E4B (Non-reasoning) | Google |
7.46
|
—
|
—
|
44.80
|
| NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA |
7.43
|
—
|
—
|
115.41
|
| Hermes 4 - Llama-3.1 405B (Non-reasoning) | Nous Research |
7.41
|
—
|
—
|
41.27
|
| NVIDIA Nemotron 3 Nano 4B | NVIDIA |
7.38
|
—
|
—
|
—
|
| Llama Nemotron Super 49B v1.5 (Non-reasoning) | NVIDIA |
7.36
|
—
|
—
|
123.46
|
| K2-V2 (low) | Institute of Foundation Models |
7.31
|
—
|
—
|
—
|
| Kimi Linear 48B A3B Instruct | Kimi |
7.30
|
—
|
—
|
—
|
| Llama 3.1 Instruct 405B | Meta |
7.29
|
—
|
—
|
—
|
| LFM2.5-8B-A1B | Liquid AI |
7.22
|
—
|
—
|
—
|
| Ring-flash-2.0 | InclusionAI |
7.15
|
—
|
—
|
—
|
| Olmo 3.1 32B Think |  Allen Institute for AI |
7.12
|
—
|
—
|
—
|
| Command A | Cohere |
6.96
|
—
|
—
|
60.42
|
| Qwen3.5 2B (Reasoning) | Alibaba |
6.94
|
—
|
—
|
—
|
| Llama 3.1 Nemotron Instruct 70B | NVIDIA |
6.94
|
—
|
—
|
163.14
|
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | NVIDIA |
6.85
|
—
|
—
|
174.10
|
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | NVIDIA |
6.84
|
—
|
—
|
158.86
|
| Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research |
6.66
|
—
|
—
|
—
|
| Sarvam 30B (high) | Sarvam |
6.56
|
—
|
—
|
—
|
| Olmo 3.1 32B Instruct | Allen Institute for AI |
6.50
|
—
|
—
|
—
|
| Gemma 4 E2B (Non-reasoning) | Google |
6.48
|
—
|
—
|
—
|
| R1 1776 |  Perplexity |
6.44
|
—
|
—
|
—
|
| Llama 3.2 Instruct 90B (Vision) | Meta |
6.41
|
—
|
—
|
—
|
| Celeris-1 |  Celeris |
6.35
|
—
|
—
|
1541.05
|
| Phi-4 Mini Instruct |  Microsoft |
6.33
|
—
|
—
|
45.67
|
| EXAONE 4.0 32B (Non-reasoning) | LG AI Research |
6.33
|
—
|
—
|
—
|
| Qwen3.5 2B (Non-reasoning) | Alibaba |
6.19
|
—
|
—
|
—
|
| Qwen3.5 0.8B (Reasoning) | Alibaba |
6.13
|
—
|
—
|
—
|
| DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | Nous Research |
6.07
|
—
|
—
|
—
|
| Jamba 1.7 Large |  AI21 Labs |
6.07
|
—
|
—
|
—
|
| Granite 4.0 H Small | IBM |
6.05
|
—
|
—
|
24.06
|
| Ministral 3 14B | Mistral |
6.04
|
—
|
—
|
89.13
|
| Qwen3 Omni 30B A3B Instruct | Alibaba |
6.01
|
—
|
—
|
94.59
|
| LFM2 24B A2B | Liquid AI |
5.95
|
—
|
—
|
—
|
| Phi-4 | Microsoft |
5.92
|
—
|
—
|
29.97
|
| Nova Micro | Amazon |
5.88
|
—
|
—
|
252.21
|
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | NVIDIA |
5.82
|
—
|
—
|
194.31
|
| Phi-4 Multimodal Instruct | Microsoft |
5.81
|
—
|
—
|
17.07
|
| MiniCPM-V 4.6 1.3B | OpenBMB |
5.69
|
—
|
—
|
—
|
| Jamba Reasoning 3B | AI21 Labs |
5.67
|
—
|
—
|
—
|
| Reka Flash 3 |  Reka AI |
5.65
|
—
|
—
|
—
|
| Olmo 3 7B Think | Allen Institute for AI |
5.62
|
—
|
—
|
—
|
| Molmo 7B-D | Allen Institute for AI |
5.56
|
—
|
—
|
—
|
| Ministral 3 8B | Mistral |
5.48
|
—
|
—
|
80.46
|
| Llama 3.2 Instruct 11B (Vision) | Meta |
5.41
|
—
|
—
|
17.82
|
| Qwen3.5 0.8B (Non-reasoning) | Alibaba |
5.40
|
—
|
—
|
—
|
| Exaone 4.0 1.2B (Reasoning) | LG AI Research |
5.27
|
—
|
—
|
—
|
| Olmo 3 7B Instruct | Allen Institute for AI |
5.24
|
—
|
—
|
—
|
| Exaone 4.0 1.2B (Non-reasoning) | LG AI Research |
5.23
|
—
|
—
|
—
|
| LFM2.5-1.2B-Thinking | Liquid AI |
5.22
|
—
|
—
|
—
|
| Jamba 1.7 Mini | AI21 Labs |
5.22
|
—
|
—
|
—
|
| LFM2.5-1.2B-Instruct | Liquid AI |
5.21
|
—
|
—
|
—
|
| Granite 4.0 H 1B | IBM |
5.19
|
—
|
—
|
—
|
| Gemma 3 270M | Google |
5.12
|
—
|
—
|
—
|
| Apertus 70B Instruct |  Swiss AI Initiative |
5.11
|
—
|
—
|
—
|
| Granite 4.0 Micro | IBM |
5.11
|
—
|
—
|
—
|
| DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | Nous Research |
5.08
|
—
|
—
|
—
|
| Molmo2-8B | Allen Institute for AI |
5.00
|
—
|
—
|
—
|
| Ministral 3 3B | Mistral |
4.84
|
—
|
—
|
224.52
|
| Apertus 8B Instruct | Swiss AI Initiative |
4.83
|
—
|
—
|
—
|
| Granite 4.0 350M | IBM |
4.83
|
—
|
—
|
—
|
| Granite 4.0 H 350M | IBM |
4.83
|
—
|
—
|
—
|
| LFM2.5-VL-1.6B | Liquid AI |
4.83
|
—
|
—
|
—
|
| Tiny Aya Global | Cohere |
4.83
|
—
|
—
|
—
|
| K2 Horizon 0.9B | MBZUAI Institute of Foundation Models |
3.05
|
—
|
—
|
—
|
| K2 Horizon 0.9B | Institute of Foundation Models |
3.05
|
—
|
—
|
—
|
| Cogito v2.1 (Reasoning) |  Deep Cogito |
—
|
—
|
—
|
—
|
| EXAONE 4.5 33B (Non-reasoning) | LG AI Research |
—
|
—
|
—
|
—
|
| GPT-5.5 Pro (xhigh) | OpenAI |
—
|
—
|
—
|
—
|
| Gemini 3 Deep Think | Google |
—
|
—
|
—
|
—
|