순위표
종합 랭킹
다섯 리더보드의 가중 혼합인 Podium Score.
종합700코딩399수학53추론413에이전트55지식412멀티모달382코딩 에이전트55과학 추론82다국어12글쓰기61채팅 어시스턴트61리서치85도구 호출32긴 컨텍스트82속도402가성비401오픈 웨이트170
700개 모델
| # | 모델명 | Podium Score | 아레나 Elo |
|---|---|---|---|
| 01 | Claude Mythos Preview Anthropic · reasoning · preview | 97.4 | — |
| 02 | Claude Fable 5 Anthropic · reasoning | 93.4 | 1509 |
| 03 | Claude Fable 5.1 Anthropic · reasoning | 88.4 | — |
| 4 | GPT-6 Astra OpenAI · reasoning | 86.2 | 1498 |
| 5 | Kimi K3 Moonshot AI · 오픈소스 · reasoning | 83.3 | 1485 |
| 6 | Claude Opus 5 Anthropic | 81.4 | 1492 |
| 7 | GPT-5.6 Sol OpenAI | 80.8 | 1483 |
| 8 | Qwen3.8 Max Alibaba | 79.8 | 1496 |
| 9 | Claude Opus 4.8 Anthropic | 76.0 | 1484 |
| 10 | Claude Opus 4 6 Thinking Anthropic · reasoning | 75.0 | — |
| 11 | Claude Opus 4 7 Thinking Anthropic · reasoning | 75.0 | — |
| 12 | Claude Opus 5 Max Anthropic | 75.0 | — |
| 13 | Gemini 3.1 Pro Preview Google | 74.0 | — |
| 14 | Kimi K3 Max Moonshot AI · reasoning | 74.0 | — |
| 15 | Claude Opus 4 8 Thinking Anthropic · reasoning | 74.0 | — |
| 16 | GPT 5.6 Sol Xhigh OpenAI | 74.0 | — |
| 17 | GPT 5.5 High OpenAI | 74.0 | — |
| 18 | GPT 5.4 High OpenAI | 74.0 | — |
| 19 | Gemini 3.5 Flash High Google | 74.0 | — |
| 20 | 74.0 | — | |
| 21 | Qwen3.7 Max Preview Alibaba | 74.0 | — |
| 22 | 74.0 | — | |
| 23 | Gemini 3.5 Flash Medium Google | 74.0 | — |
| 24 | GPT 5.5 Instant OpenAI | 74.0 | — |
| 25 | Claude Opus 4 5 20251101 Thinking 32k Anthropic · reasoning | 74.0 | — |
| 26 | Grok 4.20 Beta 0309 Reasoning xAI · reasoning | 74.0 | — |
| 27 | 74.0 | — | |
| 28 | Glm 5.2 Max Z.ai | 73.0 | — |
| 29 | Claude Opus 4 5 20251101 Anthropic | 73.0 | — |
| 30 | GPT 5.6 Terra Xhigh OpenAI | 73.0 | — |
| 31 | Grok 4.1 Thinking xAI · reasoning | 73.0 | — |
| 32 | Qwen3.5 Max Preview Alibaba | 73.0 | — |
| 33 | Qwen3.6 Max Preview Alibaba | 73.0 | — |
| 34 | Grok 4.1 xAI | 73.0 | — |
| 35 | Dola Seed 2.0 Pro Unknown | 73.0 | — |
| 36 | Claude Sonnet 4 5 20250929 Thinking 32k Anthropic · reasoning | 73.0 | — |
| 37 | Claude Sonnet 4 5 20250929 Anthropic | 73.0 | — |
| 38 | GPT 5.1 High OpenAI | 73.0 | — |
| 39 | Deepseek V4 Pro High Preview DeepSeek | 73.0 | — |
| 40 | GPT 5.6 Luna Xhigh OpenAI | 73.0 | — |
| 41 | Kimi K2.5 Thinking Moonshot AI · reasoning | 73.0 | — |
| 42 | Claude Opus 4 1 20250805 Thinking 16k Anthropic · reasoning | 72.0 | — |
| 43 | 72.0 | — | |
| 44 | GPT 5.3 Chat Latest OpenAI | 72.0 | — |
| 45 | GPT 5.4 Mini High OpenAI | 72.0 | — |
| 46 | Mimo V2 Pro Unknown | 72.0 | — |
| 47 | Claude Opus 4 1 20250805 Anthropic | 72.0 | — |
| 48 | Ernie 5.0 0110 Baidu | 72.0 | — |
| 49 | 72.0 | — | |
| 50 | 72.0 | — | |
| 51 | Glm 4.7 Z.ai | 72.0 | — |
| 52 | Qwen3.5 397b A17b Alibaba | 72.0 | — |
| 53 | Deepseek V4 Flash High Preview DeepSeek | 72.0 | — |
| 54 | GPT 5.2 High OpenAI | 72.0 | — |
| 55 | Longcat Flash Chat 2602 Exp LongCat | 72.0 | — |
| 56 | GPT 5 High OpenAI | 72.0 | — |
| 57 | Mimo V2.5 Unknown | 72.0 | — |
| 58 | Glm 5v Turbo Z.ai | 72.0 | — |
| 59 | 72.0 | — | |
| 60 | Kimi K2.5 Instant Moonshot AI | 72.0 | — |
| 61 | Grok 4 1 Fast Reasoning xAI · reasoning | 72.0 | — |
| 62 | O3 2025 04 16 OpenAI · reasoning | 72.0 | — |
| 63 | Mimo V2 Omni Unknown | 72.0 | — |
| 64 | Kimi K2 Thinking Turbo Moonshot AI · reasoning | 72.0 | — |
| 65 | GPT 5 Chat OpenAI | 71.0 | — |
| 66 | 71.0 | — | |
| 67 | 71.0 | — | |
| 68 | Glm 4.6 Z.ai | 71.0 | — |
| 69 | Deepseek V3.2 Exp Thinking DeepSeek · reasoning | 71.0 | — |
| 70 | Claude Opus 4 20250514 Thinking 16k Anthropic · reasoning | 71.0 | — |
| 71 | Qwen3 Max 2025 09 23 Alibaba | 71.0 | — |
| 72 | Deepseek V3.2 Thinking DeepSeek · reasoning | 71.0 | — |
| 73 | Deepseek V3.2 Exp DeepSeek | 71.0 | — |
| 74 | Deepseek R1 0528 DeepSeek · reasoning | 71.0 | — |
| 75 | 71.0 | — | |
| 76 | 71.0 | — | |
| 77 | Kimi K2 0905 Preview Moonshot AI | 71.0 | — |
| 78 | Kimi K2 0711 Preview Moonshot AI | 71.0 | — |
| 79 | Deepseek V3.1 DeepSeek | 71.0 | — |
| 80 | Deepseek V3.1 Terminus Thinking DeepSeek · reasoning | 71.0 | — |
| 81 | Deepseek V3.1 Thinking DeepSeek · reasoning | 71.0 | — |
| 82 | Qwen3.5 122b A10b Alibaba | 71.0 | — |
| 83 | 71.0 | — | |
| 84 | Deepseek V3.1 Terminus DeepSeek | 71.0 | — |
| 85 | GPT 4.1 2025 04 14 OpenAI | 71.0 | — |
| 86 | Claude Opus 4 20250514 Anthropic | 71.0 | — |
| 87 | Claude Haiku 4 5 20251001 Anthropic | 71.0 | — |
| 88 | Hunyuan Hy3 Preview Tencent | 71.0 | — |
| 89 | 71.0 | — | |
| 90 | Glm 4.5 Z.ai | 71.0 | — |
| 91 | Grok 4 0709 xAI | 70.0 | — |
| 92 | Mistral Medium 2508 Mistral | 70.0 | — |
| 93 | Qwen3.5 27b Alibaba | 70.0 | — |
| 94 | 70.0 | — | |
| 95 | Qwen3 235b A22b No Thinking Alibaba · reasoning | 70.0 | — |
| 96 | GPT 5.4 Nano High OpenAI | 70.0 | — |
| 97 | O1 2024 12 17 OpenAI · reasoning | 70.0 | — |
| 98 | Longcat Flash Chat LongCat | 70.0 | — |
| 99 | Claude Sonnet 4 20250514 Thinking 32k Anthropic · reasoning | 70.0 | — |
| 100 | Qwen3 235b A22b Thinking 2507 Alibaba · reasoning | 70.0 | — |
| 101 | Qwen3.5 Flash Alibaba | 70.0 | — |
| 102 | Qwen3.5 35b A3b Alibaba | 70.0 | — |
| 103 | Qwen3 VL 235b A22b Thinking Alibaba · reasoning | 70.0 | — |
| 104 | Hunyuan Vision 1.5 Thinking Tencent · reasoning | 70.0 | — |
| 105 | Step 3.5 Flash StepFun | 70.0 | — |
| 106 | 70.0 | — | |
| 107 | GPT 5 Mini High OpenAI | 70.0 | — |
| 108 | O4 Mini 2025 04 16 OpenAI · reasoning | 70.0 | — |
| 109 | Minimax M2.5 MiniMax | 70.0 | — |
| 110 | Muse Spark 1.1 Meta | 69.9 | 1490 |
| 111 | Claude Sonnet 4 20250514 Anthropic | 69.0 | — |
| 112 | Claude 3 7 Sonnet 20250219 Thinking 32k Anthropic · reasoning | 69.0 | — |
| 113 | Mistral Medium 2505 Mistral | 69.0 | — |
| 114 | Hunyuan T1 20250711 Tencent | 69.0 | — |
| 115 | Minimax M2.1 Preview MiniMax | 69.0 | — |
| 116 | Qwen3 30b A3b Instruct 2507 Alibaba | 69.0 | — |
| 117 | GPT 4.1 Mini 2025 04 14 OpenAI | 69.0 | — |
| 118 | Hunyuan Turbos 20250416 Tencent | 69.0 | — |
| 119 | Gemini 2.5 Flash Lite Preview 09 2025 No Thinking Google · reasoning | 69.0 | — |
| 120 | Glm 4.6v Z.ai | 69.0 | — |
| 121 | Qwen3 235b A22b Alibaba | 69.0 | — |
| 122 | Gemini 2.5 Flash Lite Preview 06 17 Thinking Google · reasoning | 69.0 | — |
| 123 | Qwen2.5 Max Alibaba | 69.0 | — |
| 124 | Claude 3 5 Sonnet 20241022 Anthropic | 69.0 | — |
| 125 | Glm 4.5 Air Z.ai | 69.0 | — |
| 126 | Claude 3 7 Sonnet 20250219 Anthropic | 69.0 | — |
| 127 | Gemini 3.8 Flash Google · reasoning | 68.5 | — |
| 128 | Qwen3 Next 80b A3b Thinking Alibaba · reasoning | 68.0 | — |
| 129 | Glm 4.7 Flash Z.ai | 68.0 | — |
| 130 | Gemma 3 27b It Google | 68.0 | — |
| 131 | 68.0 | — | |
| 132 | Minimax M1 MiniMax | 68.0 | — |
| 133 | 68.0 | — | |
| 134 | Gemini 2.0 Flash 001 Google | 68.0 | — |
| 135 | Mistral Small 2506 Mistral | 68.0 | — |
| 136 | 68.0 | — | |
| 137 | Command A 03 2025 Cohere | 68.0 | — |
| 138 | 68.0 | — | |
| 139 | Glm 4.5v Z.ai | 68.0 | — |
| 140 | Gemini 1.5 Pro 002 Google | 68.0 | — |
| 141 | 67.0 | — | |
| 142 | Hunyuan Turbos 20250226 Tencent | 67.0 | — |
| 143 | Step 3 StepFun | 67.0 | — |
| 144 | 67.0 | — | |
| 145 | 67.0 | — | |
| 146 | Qwen3 32b Alibaba | 67.0 | — |
| 147 | Qwen Plus 0125 Alibaba | 67.0 | — |
| 148 | Ling Flash 2.0 Ling | 67.0 | — |
| 149 | 67.0 | — | |
| 150 | Glm 4 Plus 0111 Z.ai | 67.0 | — |
| 151 | Claude 3 5 Sonnet 20240620 Anthropic | 67.0 | — |
| 152 | Gemma 3 12b It Google | 67.0 | — |
| 153 | Hunyuan Turbo 0110 Tencent | 67.0 | — |
| 154 | GPT 5 Nano High OpenAI | 67.0 | — |
| 155 | O1 Mini OpenAI · reasoning | 67.0 | — |
| 156 | Nova 2 Lite Amazon | 67.0 | — |
| 157 | 67.0 | — | |
| 158 | Gemini Advanced 0514 Google | 67.0 | — |
| 159 | 67.0 | — | |
| 160 | Step 2 16k Exp 202412 StepFun | 67.0 | — |
| 161 | 67.0 | — | |
| 162 | 67.0 | — | |
| 163 | Qwen3.8 Flash Next Alibaba · 오픈소스 | 66.8 | 1460 |
| 164 | GPT-5.6 Terra OpenAI | 66.4 | 1468 |
| 165 | Molmo 2 8b AI2 | 66.0 | — |
| 166 | 66.0 | — | |
| 167 | Qwen3 30b A3b Alibaba | 66.0 | — |
| 168 | 66.0 | — | |
| 169 | Hunyuan Large 2025 02 10 Tencent | 66.0 | — |
| 170 | GPT 4 Turbo 2024 04 09 OpenAI | 66.0 | — |
| 171 | Claude 3 5 Haiku 20241022 Anthropic | 66.0 | — |
| 172 | Gemini 1.5 Pro 001 Google | 66.0 | — |
| 173 | Deepseek V2.5 1210 DeepSeek | 66.0 | — |
| 174 | 66.0 | — | |
| 175 | GPT 4.1 Nano 2025 04 14 OpenAI | 66.0 | — |
| 176 | Claude 3 Opus 20240229 Anthropic | 66.0 | — |
| 177 | Ring Flash 2.0 Unknown | 66.0 | — |
| 178 | Step 1o Turbo 202506 StepFun | 66.0 | — |
| 179 | Glm 4 Plus Z.ai | 66.0 | — |
| 180 | 66.0 | — | |
| 181 | Gemma 3n E4b It Google | 66.0 | — |
| 182 | Qwen Max 0919 Alibaba | 66.0 | — |
| 183 | GPT 4o Mini 2024 07 18 OpenAI | 66.0 | — |
| 184 | 66.0 | — | |
| 185 | Qwen2.5 Plus 1127 Alibaba | 66.0 | — |
| 186 | GPT 4 0125 Preview OpenAI | 66.0 | — |
| 187 | GPT 4 1106 Preview OpenAI | 66.0 | — |
| 188 | Hunyuan Standard 2025 02 10 Tencent | 66.0 | — |
| 189 | Gemini 3.6 Flash Google | 65.9 | 1483 |
| 190 | Gemini 3.8 Flash (Medium Reasoning) Google · reasoning | 65.2 | — |
| 191 | Gemini 1.5 Flash 002 Google | 65.0 | — |
| 192 | 65.0 | — | |
| 193 | Deepseek V2.5 DeepSeek | 65.0 | — |
| 194 | 65.0 | — | |
| 195 | Mercury Inception | 65.0 | — |
| 196 | 65.0 | — | |
| 197 | Mistral Large 2411 Mistral | 65.0 | — |
| 198 | Magistral Medium 2506 Mistral | 65.0 | — |
| 199 | Gemma 3 4b It Google | 65.0 | — |
| 200 | 65.0 | — | |
| 201 | Qwen2.5 72b Instruct Alibaba | 65.0 | — |
| 202 | 65.0 | — | |
| 203 | Hunyuan Large Vision Tencent | 65.0 | — |
| 204 | 65.0 | — | |
| 205 | Amazon Nova Pro V1.0 Amazon | 65.0 | — |
| 206 | DeepSeek V4 Flash Vision DeepSeek | 65.0 | — |
| 207 | G9v3-39A5B AI9Stars · 오픈소스 | 65.0 | — |
| 208 | G9v3-3B AI9Stars · 오픈소스 | 65.0 | — |
| 209 | GLM-5.3 Zhipu AI | 65.0 | — |
| 210 | 65.0 | — | |
| 211 | 65.0 | — | |
| 212 | 65.0 | — | |
| 213 | HyperNova 60B Multiverse · 오픈소스 | 65.0 | — |
| 214 | KAT-Coder-Pro V2 Kwai | 65.0 | — |
| 215 | LFM2.5-2.6B Liquid AI · 오픈소스 | 65.0 | — |
| 216 | LFM2.5-8B-A1B Liquid AI · 오픈소스 | 65.0 | — |
| 217 | LFM2.5-VL-1.6B Liquid AI · 오픈소스 | 65.0 | — |
| 218 | LongCat 2.0 LongCat · 오픈소스 | 65.0 | — |
| 219 | Magistral Small 1.2 Mistral · 오픈소스 | 65.0 | — |
| 220 | Qwen3.8 27B (xhigh) Alibaba · 오픈소스 | 65.0 | — |
| 221 | Qwen3.8 27B (low) Alibaba · 오픈소스 | 65.0 | — |
| 222 | Qwen3.8 27B (medium) Alibaba · 오픈소스 | 65.0 | — |
| 223 | Qwen3.8 27B (Non-reasoning) Alibaba · 오픈소스 · reasoning | 65.0 | — |
| 224 | GLM-5.3 Flash Z.ai · 오픈소스 | 64.2 | 1445 |
| 225 | Gemma 2 27b It Google | 64.0 | — |
| 226 | Ibm Granite H Small Unknown | 64.0 | — |
| 227 | GPT 4 0314 OpenAI | 64.0 | — |
| 228 | Gemini 1.5 Flash 001 Google | 64.0 | — |
| 229 | 64.0 | — | |
| 230 | 64.0 | — | |
| 231 | 64.0 | — | |
| 232 | Claude 3 Sonnet 20240229 Anthropic | 64.0 | — |
| 233 | Nemotron 4 340b Instruct NVIDIA | 64.0 | — |
| 234 | 64.0 | — | |
| 235 | Command R Plus 08 2024 Cohere | 64.0 | — |
| 236 | GPT 4 0613 OpenAI | 64.0 | — |
| 237 | 64.0 | — | |
| 238 | Glm 4 0520 Z.ai | 64.0 | — |
| 239 | Qwen2.5 Coder 32b Instruct Alibaba | 64.0 | — |
| 240 | C4ai Aya Expanse 32b Cohere | 63.0 | — |
| 241 | Gemma 2 9b It Google | 63.0 | — |
| 242 | Deepseek Coder V2 DeepSeek | 63.0 | — |
| 243 | Qwen2 72b Instruct Alibaba | 63.0 | — |
| 244 | Command R Plus Cohere | 63.0 | — |
| 245 | Claude 3 Haiku 20240307 Anthropic | 63.0 | — |
| 246 | Amazon Nova Lite V1.0 Amazon | 63.0 | — |
| 247 | Gemini 1.5 Flash 8b 001 Google | 63.0 | — |
| 248 | 63.0 | — | |
| 249 | Command R 08 2024 Cohere | 63.0 | — |
| 250 | Claude Opus 5 Xhigh Anthropic | 62.5 | — |
| 251 | Mistral Large 2402 Mistral | 62.0 | — |
| 252 | Amazon Nova Micro V1.0 Amazon | 62.0 | — |
| 253 | Ministral 8b 2410 Mistral | 62.0 | — |
| 254 | Gemini Pro Dev API Google | 62.0 | — |
| 255 | Qwen1.5 110b Chat Alibaba | 62.0 | — |
| 256 | Hunyuan Standard 256k Tencent | 62.0 | — |
| 257 | Qwen1.5 72b Chat Alibaba | 62.0 | — |
| 258 | Gemini 3.8 Flash (Low Reasoning) Google · reasoning | 62.0 | — |
| 259 | Claude Opus 5 High Anthropic | 61.5 | — |
| 260 | Grok 4.5 xAI | 61.3 | 1469 |
| 261 | Claude Opus 4.6 Anthropic | 61.2 | 1505 |
| 262 | Mixtral 8x22b Instruct V0.1 Mistral | 61.0 | — |
| 263 | Command R Cohere | 61.0 | — |
| 264 | GPT 3.5 Turbo 0125 OpenAI | 61.0 | — |
| 265 | 61.0 | — | |
| 266 | C4ai Aya Expanse 8b Cohere | 61.0 | — |
| 267 | Gemini Pro Google | 61.0 | — |
| 268 | 61.0 | — | |
| 269 | 61.0 | — | |
| 270 | Grok 4 xAI | 60.9 | — |
| 271 | Grok 4 6 xAI | 60.9 | — |
| 272 | Gemini 3.1 Pro Google | 60.6 | 1485 |
| 273 | 60.0 | — | |
| 274 | Qwen1.5 32b Chat Alibaba | 60.0 | — |
| 275 | GPT 3.5 Turbo 1106 OpenAI | 60.0 | — |
| 276 | Gemma 2 2b It Google | 60.0 | — |
| 277 | Phi 3 Medium 4k Instruct Microsoft | 60.0 | — |
| 278 | Mixtral 8x7b Instruct V0.1 Mistral | 60.0 | — |
| 279 | Qwen1.5 14b Chat Alibaba | 60.0 | — |
| 280 | GLM-5.2 Z.ai · 오픈소스 | 59.1 | 1469 |
| 281 | Deepseek LLM 67b Chat DeepSeek | 59.0 | — |
| 282 | Wizardlm 70b Microsoft | 59.0 | — |
| 283 | 59.0 | — | |
| 284 | Gemma 1.1 7b It Google | 59.0 | — |
| 285 | 59.0 | — | |
| 286 | Phi 3 Small 8k Instruct Microsoft | 59.0 | — |
| 287 | Llama 2 70b Chat Meta | 59.0 | — |
| 288 | Claude Opus 5 Medium Anthropic | 58.6 | — |
| 289 | Granite 4.2 30B Instruct IBM · 오픈소스 | 58.6 | 1380 |
| 290 | 58.0 | — | |
| 291 | 58.0 | — | |
| 292 | Qwq 32b Preview Alibaba · reasoning | 58.0 | — |
| 293 | 58.0 | — | |
| 294 | Qwen3 8 2 4t A95b Alibaba · 오픈소스 | 57.7 | — |
| 295 | Gpt 5 6 Sol High OpenAI | 57.3 | — |
| 296 | Wizardlm 13b Microsoft | 57.0 | — |
| 297 | Mistral 7b Instruct V0.2 Mistral | 57.0 | — |
| 298 | Qwen1.5 7b Chat Alibaba | 57.0 | — |
| 299 | Phi 3 Mini 4k Instruct June 2024 Microsoft | 57.0 | — |
| 300 | Llama 2 13b Chat Meta | 57.0 | — |
| 301 | Qwen 14b Chat Alibaba | 57.0 | — |
| 302 | Palm 2 Google | 57.0 | — |
| 303 | Gemma 7b It Google | 57.0 | — |
| 304 | Codellama 34b Instruct Unknown | 57.0 | — |
| 305 | Muse Spark 1 2 Meta | 56.8 | — |
| 306 | Gemini 3 7 Flash Google | 56.0 | — |
| 307 | Phi 3 Mini 128k Instruct Microsoft | 56.0 | — |
| 308 | Phi 3 Mini 4k Instruct Microsoft | 56.0 | — |
| 309 | Codellama 70b Instruct Unknown | 56.0 | — |
| 310 | Gemma 1.1 2b It Google | 56.0 | — |
| 311 | 56.0 | — | |
| 312 | Gpt 5 6 Sol Medium OpenAI | 55.6 | — |
| 313 | Llama 2 7b Chat Meta | 55.0 | — |
| 314 | Gemma 2b It Google | 55.0 | — |
| 315 | Qwen1.5 4b Chat Alibaba | 55.0 | — |
| 316 | Grok 4 Heavy xAI · preview | 54.5 | — |
| 317 | DeepSeek V4.1 Flash DeepSeek · 오픈소스 · reasoning | 54.5 | 1450 |
| 318 | GPT-5.5 OpenAI | 54.0 | 1482 |
| 319 | 54.0 | — | |
| 320 | Gemini 3 7 Flash Medium Google | 53.4 | — |
| 321 | Glm 5 Z.ai · 오픈소스 | 52.6 | — |
| 322 | Claude Opus 5 Low Anthropic | 52.5 | — |
| 323 | GPT-5.3 Codex OpenAI | 52.4 | — |
| 324 | Claude Opus 4.5 Anthropic | 52.1 | 1473 |
| 325 | Claude Opus 4.7 Anthropic | 52.0 | 1502 |
| 326 | Phi-4 Multimodal Microsoft | 52.0 | — |
| 327 | Gemini 3 Pro Google | 51.9 | 1486 |
| 328 | Gpt 5 5 Medium OpenAI | 51.4 | — |
| 329 | GPT-5.4 OpenAI | 51.0 | 1477 |
| 330 | Qwen3.7 Max Alibaba | 51.0 | 1475 |
| 331 | Gemini 3 7 Flash Low Google | 50.9 | — |
| 332 | Gpt 5 6 Sol Low OpenAI | 50.7 | — |
| 333 | Gpt 5 6 Terra High OpenAI | 50.1 | — |
| 334 | Gemini 3.5 Flash Google | 50.0 | 1476 |
| 335 | Sarvam 105B Sarvam AI · 오픈소스 | 50.0 | — |
| 336 | Sarvam 30B Sarvam AI · 오픈소스 | 50.0 | — |
| 337 | GPT-5.2 OpenAI | 49.2 | 1476 |
| 338 | Granite 4.2 8B Instruct IBM · 오픈소스 | 49.2 | 1315 |
| 339 | GPT-5.6 Luna OpenAI | 49.1 | 1450 |
| 340 | ERNIE 5.1 Baidu | 49.1 | 1468 |
| 341 | Kimi K2.6 Moonshot AI · 오픈소스 | 49.0 | 1461 |
| 342 | Sarvam M Reasoning Sarvam AI · 오픈소스 · reasoning | 49.0 | — |
| 343 | Kimi K3 Low Moonshot AI · reasoning | 48.3 | — |
| 344 | Agnes 3.0 Flash Agnes · reasoning | 48.2 | 1390 |
| 345 | Grok 4.3 xAI | 48.0 | 1442 |
| 346 | MiMo V2.5 Pro Xiaomi · 오픈소스 | 48.0 | 1466 |
| 347 | Muse Spark Meta | 47.0 | 1488 |
| 348 | Claude Sonnet 4 6 Adaptive Anthropic | 47.0 | — |
| 349 | Gpt 5 6 Luna High OpenAI | 47.0 | — |
| 350 | Gpt 5 6 Terra Medium OpenAI | 46.8 | — |
| 351 | DeepSeek V4 Pro DeepSeek · 오픈소스 | 46.0 | 1458 |
| 352 | GLM-5.1 Z.ai · 오픈소스 | 46.0 | — |
| 353 | Claude Sonnet 5 Anthropic | 45.4 | 1462 |
| 354 | Deepseek V4 Pro 0424 DeepSeek · 오픈소스 | 45.3 | — |
| 355 | MiniMax-M2.7 MiniMax | 45.0 | — |
| 356 | Claude Opus 4 6 Adaptive Anthropic | 44.9 | — |
| 357 | Gpt 5 5 Low OpenAI | 44.5 | — |
| 358 | Nex N2 Pro Nex AGI | 44.4 | — |
| 359 | Gpt 5 4 Mini OpenAI | 44.0 | — |
| 360 | Claude Opus 4 7 Non Reasoning Anthropic · reasoning | 43.9 | — |
| 361 | Deepseek V4 Pro 0424 High DeepSeek · 오픈소스 | 43.7 | — |
| 362 | Claude Sonnet 5 Non Reasoning Anthropic · reasoning | 42.6 | — |
| 363 | Agnes 2.5 Pro Beta Agnes | 42.5 | — |
| 364 | Claude Sonnet 4.5 Anthropic | 42.4 | 1456 |
| 365 | Gemini 3 Flash Google | 42.4 | 1473 |
| 366 | GPT-5.1 OpenAI | 42.3 | 1455 |
| 367 | Qwen3.7 Plus Alibaba | 42.2 | 1459 |
| 368 | Deepseek V4 Flash 0420 DeepSeek · 오픈소스 | 42.1 | — |
| 369 | DeepSeek V4 Flash DeepSeek · 오픈소스 | 42.0 | 1438 |
| 370 | Granite 4.2 3B Instruct IBM · 오픈소스 | 42.0 | 1260 |
| 371 | Claude Opus 4 5 Thinking Anthropic · reasoning | 41.9 | — |
| 372 | Gpt 5 6 Sol Non Reasoning OpenAI · reasoning | 41.9 | — |
| 373 | Kimi K2.7 Code Moonshot AI · 오픈소스 | 41.8 | — |
| 374 | Inkling Small Thinking Machines | 41.7 | — |
| 375 | Solar Pro4 Upstage · reasoning | 41.6 | — |
| 376 | Gpt 5 6 Terra Low OpenAI | 41.3 | — |
| 377 | Gpt 5 2 Codex OpenAI | 41.2 | — |
| 378 | Qwen3 6 Max Alibaba · 오픈소스 | 41.1 | — |
| 379 | 40.7 | — | |
| 380 | Gpt 5 4 Low OpenAI | 40.2 | — |
| 381 | Seed 2.0 Pro ByteDance | 40.0 | 1456 |
| 382 | Agnes 2 5 Pro Alpha Agnes | 39.7 | — |
| 383 | Gpt 5 4 Nano OpenAI | 39.7 | — |
| 384 | MiniMax M3 MiniMax | 39.6 | 1445 |
| 385 | Deepseek V4 Flash 0420 High DeepSeek · 오픈소스 | 39.0 | — |
| 386 | Hunyuan Hy3 Tencent | 38.9 | 1456 |
| 387 | Gpt 5 2 Medium OpenAI | 38.9 | — |
| 388 | Gpt 5 6 Luna Medium OpenAI | 38.9 | — |
| 389 | Gemini 3.5 Flash-Lite Google | 38.8 | 1457 |
| 390 | Gemini 3 Flash Reasoning Google · reasoning | 38.7 | — |
| 391 | 38.3 | — | |
| 392 | Claude Sonnet 4.6 Anthropic | 38.1 | 1472 |
| 393 | Deepseek V3 2 Reasoning DeepSeek · 오픈소스 · reasoning | 38.0 | — |
| 394 | Grok 4 20 xAI | 38.0 | — |
| 395 | Mimo V2 5 0424 Xiaomi · 오픈소스 | 38.0 | — |
| 396 | Ling 3 0 Flash Ling | 37.8 | — |
| 397 | Qwen3 6 27b Alibaba · 오픈소스 | 37.7 | — |
| 398 | Claude 4 5 Sonnet Thinking Anthropic · reasoning | 37.4 | — |
| 399 | 37.4 | — | |
| 400 | Gpt 5 Codex OpenAI | 37.0 | — |
| 401 | 36.9 | — | |
| 402 | Glm 5 1 Non Reasoning Z.ai · 오픈소스 · reasoning | 36.3 | — |
| 403 | Grok 4 3 Low xAI | 36.3 | — |
| 404 | Kimi K2 5 Moonshot AI | 36.0 | — |
| 405 | Gemini 3 5 Flash Minimal Google | 35.8 | — |
| 406 | Gpt 5 5 Non Reasoning OpenAI · reasoning | 35.8 | — |
| 407 | Gpt 5 1 Codex OpenAI | 35.6 | — |
| 408 | Kimi K2 6 Non Reasoning Moonshot AI · reasoning | 35.4 | — |
| 409 | Claude Sonnet 4 6 Non Reasoning Low Effort Anthropic · reasoning | 35.1 | — |
| 410 | Muse Glimmer Meta | 35.1 | — |
| 411 | Gemma 4 31B Google · 오픈소스 | 35.0 | 1451 |
| 412 | Mistral Medium 3.5 Mistral | 35.0 | — |
| 413 | Glm 5 2 Non Reasoning Z.ai · 오픈소스 · reasoning | 34.8 | — |
| 414 | Gpt 5 6 Terra Non Reasoning OpenAI · reasoning | 34.6 | — |
| 415 | Gpt 5 Medium OpenAI | 34.6 | — |
| 416 | Claude 4 1 Opus Thinking Anthropic · reasoning | 34.5 | — |
| 417 | Hy3 Preview Tencent | 34.4 | — |
| 418 | Gpt 5 5 Instant 05 26 OpenAI | 34.3 | — |
| 419 | Gemini 3 Pro Low Google | 33.9 | — |
| 420 | Gpt 5 6 Luna Low OpenAI | 33.9 | — |
| 421 | Kimi K2 Thinking Moonshot AI · reasoning | 33.5 | — |
| 422 | O3 Pro OpenAI · reasoning | 33.3 | — |
| 423 | Glm 5 Non Reasoning Z.ai · 오픈소스 · reasoning | 33.2 | — |
| 424 | Claude 4 5 Haiku Reasoning Anthropic · reasoning | 33.0 | — |
| 425 | Qwen3 5 397b A17b Non Reasoning Alibaba · 오픈소스 · reasoning | 32.7 | — |
| 426 | Qwen3.6 Plus Alibaba | 32.4 | 1444 |
| 427 | Minimax M2 1 MiniMax · 오픈소스 | 32.1 | — |
| 428 | Qwen3 6 35b A3b Alibaba · 오픈소스 | 32.1 | — |
| 429 | o3 OpenAI · reasoning | 32.0 | 1431 |
| 430 | Nova 2 0 Pro Reasoning Medium Amazon · reasoning | 32.0 | — |
| 431 | 32.0 | — | |
| 432 | Deepseek V4 Pro 0424 Non Reasoning DeepSeek · 오픈소스 · reasoning | 31.9 | — |
| 433 | Gpt 5 Low OpenAI | 31.9 | — |
| 434 | Mimo V2 Flash Reasoning Xiaomi · 오픈소스 · reasoning | 31.9 | — |
| 435 | Inkling Thinking Machines | 31.7 | 1441 |
| 436 | Claude 4 Opus Thinking Anthropic · reasoning | 31.7 | — |
| 437 | Gpt 5 Mini Medium OpenAI | 31.6 | — |
| 438 | Gpt 5 1 Codex Mini OpenAI | 31.3 | — |
| 439 | Qwen3 5 Omni Plus Alibaba · 오픈소스 | 31.3 | — |
| 440 | Qwen3 6 27b Non Reasoning Alibaba · 오픈소스 · reasoning | 31.3 | — |
| 441 | Ring 2 6 1t WeRide | 31.3 | — |
| 442 | Deepseek V3 1 Terminus Reasoning DeepSeek · 오픈소스 · reasoning | 31.1 | — |
| 443 | Step 3 7 Flash StepFun | 30.9 | — |
| 444 | Gpt 5 4 Nano Medium OpenAI | 30.8 | — |
| 445 | Gpt 5 4 Mini Medium OpenAI | 30.5 | — |
| 446 | Kimi K2 5 Non Reasoning Moonshot AI · reasoning | 30.1 | — |
| 447 | GPT-oss-120B OpenAI · 오픈소스 | 30.0 | — |
| 448 | Qwen3 5 27b Non Reasoning Alibaba · 오픈소스 · reasoning | 30.0 | — |
| 449 | Claude 4 5 Sonnet Anthropic | 29.9 | — |
| 450 | Claude 4 Sonnet Thinking Anthropic · reasoning | 29.8 | — |
| 451 | Deepseek V4 Flash Non Reasoning DeepSeek · 오픈소스 · reasoning | 29.3 | — |
| 452 | Glm 4 6 Reasoning Z.ai · 오픈소스 · reasoning | 29.3 | — |
| 453 | Gpt 5 5 Instant 06 26 OpenAI | 29.2 | — |
| 454 | Minimax M2 MiniMax · 오픈소스 | 28.9 | — |
| 455 | Claude 4 1 Opus Anthropic | 28.8 | — |
| 456 | Mimo V2 5 Pro Non Reasoning Xiaomi · 오픈소스 · reasoning | 28.4 | — |
| 457 | Gpt 5 4 Non Reasoning OpenAI · reasoning | 28.3 | — |
| 458 | Qwen3 5 122b A10b Non Reasoning Alibaba · 오픈소스 · reasoning | 28.2 | — |
| 459 | Grok 4 Fast Reasoning xAI · reasoning | 27.9 | — |
| 460 | Glm 4 7 Non Reasoning Z.ai · 오픈소스 · reasoning | 27.1 | — |
| 461 | Gpt 5 6 Luna Non Reasoning OpenAI · reasoning | 26.8 | — |
| 462 | Hy3 Non Reasoning Tencent · reasoning | 26.6 | — |
| 463 | Ling 2 6 1t Ling | 26.6 | — |
| 464 | Gpt 5 2 Non Reasoning OpenAI · reasoning | 26.5 | — |
| 465 | Gemma 4 26b A4b Google · 오픈소스 | 26.1 | — |
| 466 | Claude 4 Opus Anthropic | 26.0 | — |
| 467 | Claude 4 Sonnet Anthropic | 26.0 | — |
| 468 | Step 3 5 Flash 0202 StepFun | 26.0 | — |
| 469 | Deepseek V3 2 Reasoning 0925 DeepSeek · 오픈소스 · reasoning | 25.9 | — |
| 470 | Gpt 5 Mini OpenAI | 25.8 | — |
| 471 | Qwen3 Max Thinking Preview Alibaba · 오픈소스 · reasoning | 25.5 | — |
| 472 | Grok 4 3 Non Reasoning xAI · reasoning | 25.0 | — |
| 473 | Qwen3 6 35b A3b Non Reasoning Alibaba · 오픈소스 · reasoning | 24.6 | — |
| 474 | Ling 3 0 Tiny Ling | 24.5 | — |
| 475 | Qwen3 5 35b A3b Non Reasoning Alibaba · 오픈소스 · reasoning | 24.3 | — |
| 476 | Claude 4.5 Haiku Anthropic | 24.1 | — |
| 477 | Kimi K2 0905 Moonshot AI | 24.0 | — |
| 478 | Qwen3.5 397B-A17B Alibaba · 오픈소스 | 23.9 | 1442 |
| 479 | Claude 3 7 Sonnet Anthropic | 23.9 | — |
| 480 | O1 OpenAI · reasoning | 23.9 | — |
| 481 | Nemotron 3 5 Lightning NVIDIA | 23.6 | — |
| 482 | GPT-5 OpenAI | 23.0 | 1434 |
| 483 | Solar Pro 3 Upstage | 23.0 | — |
| 484 | Grok 3 Mini Reasoning xAI · reasoning | 22.9 | — |
| 485 | Grok 4 20 0309 Non Reasoning xAI · reasoning | 22.9 | — |
| 486 | Command A Plus Cohere | 22.8 | — |
| 487 | Gemini 2 5 Pro 05 06 Google | 22.7 | — |
| 488 | Gemma 4 31b Non Reasoning Google · 오픈소스 · reasoning | 22.3 | — |
| 489 | Gemma 4 12b Google · 오픈소스 | 22.2 | — |
| 490 | Grok 4 20 Non Reasoning xAI · reasoning | 22.2 | — |
| 491 | Qwen3.5 122B-A10B Alibaba · 오픈소스 | 22.0 | 1417 |
| 492 | GPT-oss-20B OpenAI · 오픈소스 | 22.0 | — |
| 493 | 22.0 | — | |
| 494 | Mercury 2 Inception | 21.9 | — |
| 495 | Qwen3 5 9b Alibaba · 오픈소스 | 21.8 | — |
| 496 | Claude Opus 4.1 Anthropic | 21.7 | 1449 |
| 497 | Deepseek V3 2 0925 DeepSeek · 오픈소스 | 21.7 | — |
| 498 | Apriel V1 5 15b Thinker ServiceNow | 21.6 | — |
| 499 | Nova 2 0 Omni Reasoning Medium Amazon · reasoning | 21.3 | — |
| 500 | Qwen3 Coder Next Alibaba · 오픈소스 | 21.3 | — |
| 501 | Deepseek V3 1 Reasoning DeepSeek · 오픈소스 · reasoning | 21.0 | — |
| 502 | Qwen3 Vl 235b A22b Reasoning Alibaba · 오픈소스 · reasoning | 20.9 | — |
| 503 | Apriel V1 6 15b Thinker ServiceNow | 20.8 | — |
| 504 | Nova 2 0 Lite Reasoning Amazon · reasoning | 20.8 | — |
| 505 | Gpt 5 1 Non Reasoning OpenAI · reasoning | 20.7 | — |
| 506 | Qwen3 5 9b Non Reasoning Alibaba · 오픈소스 · reasoning | 20.6 | — |
| 507 | Gemma 4 26b A4b Non Reasoning Google · 오픈소스 · reasoning | 20.4 | — |
| 508 | Qwen3 5 4b Alibaba · 오픈소스 | 20.4 | — |
| 509 | Gemini 2 5 Flash Reasoning Google · reasoning | 20.3 | — |
| 510 | North Mini Code North | 20.2 | — |
| 511 | Gpt 5 Nano OpenAI | 20.1 | — |
| 512 | Qwen3 235b A22b Instruct 2507 Reasoning Alibaba · 오픈소스 · reasoning | 19.9 | — |
| 513 | Nova 2 0 Pro Reasoning Low Amazon · reasoning | 19.8 | — |
| 514 | Kimi K2 Moonshot AI | 19.7 | — |
| 515 | Mistral Small 4 Mistral · 오픈소스 | 19.7 | — |
| 516 | Qwen3 Max Alibaba · 오픈소스 | 19.6 | 1435 |
| 517 | Gpt 4 1 OpenAI | 19.6 | — |
| 518 | Qwen3 Max Preview Alibaba · 오픈소스 | 19.4 | — |
| 519 | Devstral 2 Mistral | 19.2 | — |
| 520 | Gpt 5 Nano Medium OpenAI | 19.2 | — |
| 521 | Nova 2 0 Lite Reasoning Medium Amazon · reasoning | 19.2 | — |
| 522 | O3 Mini OpenAI · reasoning | 19.2 | — |
| 523 | Qwen3 5 Omni Flash Alibaba · 오픈소스 | 19.2 | — |
| 524 | O1 Pro OpenAI · reasoning | 19.1 | — |
| 525 | Nemotron 3 Ultra 550B NVIDIA · 오픈소스 | 19.0 | 1426 |
| 526 | Deepseek R1 0120 DeepSeek · 오픈소스 · reasoning | 18.6 | — |
| 527 | Seed Oss 36b Instruct ByteDance | 18.5 | — |
| 528 | Qwen3 235b A22b Instruct 2507 Alibaba · 오픈소스 | 18.4 | — |
| 529 | Trinity Large Thinking Trinity · reasoning | 18.4 | — |
| 530 | Qwen3 Coder 480b A35b Instruct Alibaba · 오픈소스 | 18.2 | — |
| 531 | Qwen3 Vl 32b Reasoning Alibaba · 오픈소스 · reasoning | 18.1 | — |
| 532 | Nova 2 0 Lite Reasoning Low Amazon · reasoning | 18.0 | — |
| 533 | Minimax M1 80k MiniMax · 오픈소스 | 17.9 | — |
| 534 | Gpt 5 4 Nano Non Reasoning OpenAI · reasoning | 17.8 | — |
| 535 | Devstral Small 2 Mistral | 17.7 | — |
| 536 | Gpt 5 Minimal OpenAI | 17.3 | — |
| 537 | O1 Preview OpenAI · reasoning | 17.2 | — |
| 538 | Glm 4 6v Reasoning Z.ai · 오픈소스 · reasoning | 16.9 | — |
| 539 | Qwen3 Next 80b A3b Reasoning Alibaba · 오픈소스 · reasoning | 16.9 | — |
| 540 | Gpt 5 4 Mini Non Reasoning OpenAI · reasoning | 16.8 | — |
| 541 | Nova 2 0 Omni Reasoning Low Amazon · reasoning | 16.7 | — |
| 542 | Grok 4 Fast xAI | 16.6 | — |
| 543 | Qwen3 5 4b Non Reasoning Alibaba · 오픈소스 · reasoning | 16.1 | — |
| 544 | Mistral Large 3 Mistral · 오픈소스 | 15.9 | — |
| 545 | O3 Mini High OpenAI · reasoning | 15.7 | — |
| 546 | Glm 4 7 Flash Non Reasoning Z.ai · 오픈소스 · reasoning | 15.6 | — |
| 547 | Deepseek V3 0324 DeepSeek · 오픈소스 | 15.2 | — |
| 548 | Gemini 2 5 Flash Lite Preview 09 2025 Reasoning Google · reasoning | 15.2 | — |
| 549 | 15.0 | — | |
| 550 | Gpt Oss 120b Low OpenAI | 14.9 | — |
| 551 | Mistral Small 3 1 Mistral · 오픈소스 | 14.9 | — |
| 552 | Gpt 4 1 Mini OpenAI | 14.8 | — |
| 553 | Mistral Medium 3 1 Mistral · 오픈소스 | 14.7 | — |
| 554 | Qwen3 30b A3b 2507 Reasoning Alibaba · 오픈소스 · reasoning | 14.6 | — |
| 555 | Nvidia Nemotron 3 Nano 30b A3b Reasoning NVIDIA · reasoning | 14.5 | — |
| 556 | Nova 2.0 Pro Preview Amazon · preview | 14.4 | — |
| 557 | Gpt Oss 20b Low OpenAI | 14.4 | — |
| 558 | Qwen3 Vl 235b A22b Instruct Alibaba · 오픈소스 | 14.4 | — |
| 559 | Gpt 5 Mini Minimal OpenAI | 14.3 | — |
| 560 | Ling 2 6 Flash Ling | 14.2 | — |
| 561 | Qwen3 Next 80b A3b Instruct Alibaba · 오픈소스 | 13.8 | — |
| 562 | Qwen3 Coder 30b A3b Instruct Alibaba · 오픈소스 | 13.6 | — |
| 563 | Qwen3 235b A22b Instruct Reasoning Alibaba · 오픈소스 · reasoning | 13.5 | — |
| 564 | Qwen3 Vl 30b A3b Reasoning Alibaba · 오픈소스 · reasoning | 13.4 | — |
| 565 | Qwq 32b Alibaba · reasoning | 13.4 | — |
| 566 | Gemma 4 12b Non Reasoning Google · 오픈소스 · reasoning | 13.2 | — |
| 567 | 13.1 | — | |
| 568 | DeepSeek V3.2 DeepSeek · 오픈소스 | 12.9 | 1425 |
| 569 | Nova Premier Amazon | 12.7 | — |
| 570 | Mistral Medium 3 Mistral · 오픈소스 | 12.5 | — |
| 571 | Celeris 1 Celeris | 12.4 | — |
| 572 | Llama Nemotron Super 49b V1 5 Reasoning Meta · 오픈소스 · reasoning | 12.4 | — |
| 573 | Mistral Small 4 Non Reasoning Mistral · 오픈소스 · reasoning | 12.3 | — |
| 574 | Gemma 4 E4b Google · 오픈소스 | 12.2 | — |
| 575 | Claude 3 Opus Anthropic | 11.8 | — |
| 576 | Nova 2 0 Lite Amazon | 11.8 | — |
| 577 | Gemini 2 5 Flash Lite Reasoning Google · reasoning | 11.4 | — |
| 578 | Qwen3 32b Instruct Reasoning Alibaba · 오픈소스 · reasoning | 11.4 | — |
| 579 | Ministral 3 14b Mistral | 11.2 | — |
| 580 | Qwen3 Vl 32b Instruct Alibaba · 오픈소스 | 11.0 | — |
| 581 | Qwen3 235b A22b Instruct Alibaba · 오픈소스 | 10.8 | — |
| 582 | Mistral Small 3 2 Mistral · 오픈소스 | 10.7 | — |
| 583 | 10.6 | — | |
| 584 | Qwen3 Vl 8b Reasoning Alibaba · 오픈소스 · reasoning | 10.5 | — |
| 585 | Nova 2 0 Omni Amazon | 10.4 | — |
| 586 | Qwen3 14b Instruct Reasoning Alibaba · 오픈소스 · reasoning | 10.4 | — |
| 587 | Llama 4 Scout Meta · 오픈소스 | 10.3 | — |
| 588 | Hermes 4 Llama 3 1 70b Reasoning Meta · 오픈소스 · reasoning | 9.9 | — |
| 589 | Qwen3 Vl 30b A3b Instruct Alibaba · 오픈소스 | 9.9 | — |
| 590 | Claude 35 Sonnet Anthropic | 9.8 | — |
| 591 | Deepseek R1 Distill Llama 70b DeepSeek · 오픈소스 · reasoning | 9.8 | — |
| 592 | Gpt 4 1 Nano OpenAI | 9.6 | — |
| 593 | Qwen3 Omni 30b A3b Reasoning Alibaba · 오픈소스 · reasoning | 9.5 | — |
| 594 | Gpt 4o 2024 08 06 OpenAI | 9.4 | — |
| 595 | Llama 3 3 Instruct 70b Meta · 오픈소스 | 9.3 | — |
| 596 | Qwen3 30b A3b Instruct Reasoning Alibaba · 오픈소스 · reasoning | 9.2 | — |
| 597 | Glm 4 5v Reasoning Z.ai · 오픈소스 · reasoning | 9.0 | — |
| 598 | Ministral 3 8b Mistral | 9.0 | — |
| 599 | Ernie 4 5 300b A47b Baidu | 8.9 | — |
| 600 | Llama 3 1 Nemotron Ultra 253b V1 Reasoning Meta · 오픈소스 · reasoning | 8.9 | — |
| 601 | Qwen3 30b A3b 2507 Alibaba · 오픈소스 | 8.9 | — |
| 602 | Hermes 4 Llama 3 1 405b Reasoning Meta · 오픈소스 · reasoning | 8.8 | — |
| 603 | Nvidia Nemotron Nano 12b V2 Vl Reasoning NVIDIA · reasoning | 8.8 | — |
| 604 | Gemma 4 E4b Non Reasoning Google · 오픈소스 · reasoning | 8.7 | — |
| 605 | Nvidia Nemotron Nano 9b V2 Reasoning NVIDIA · reasoning | 8.7 | — |
| 606 | Hermes 4 Llama 3 1 405b Meta · 오픈소스 | 8.6 | — |
| 607 | Llama Nemotron Super 49b V1 5 Meta · 오픈소스 | 8.5 | — |
| 608 | Qwen3 32b Instruct Alibaba · 오픈소스 | 8.5 | — |
| 609 | Gpt 4o 2024 05 13 OpenAI | 8.4 | — |
| 610 | Qwen3 8b Instruct Reasoning Alibaba · 오픈소스 · reasoning | 8.3 | — |
| 611 | Qwen3 Vl 8b Instruct Alibaba · 오픈소스 | 8.2 | — |
| 612 | Claude 35 Sonnet June 24 Anthropic | 8.1 | — |
| 613 | Gpt 5 Nano Minimal OpenAI | 7.8 | — |
| 614 | Gpt 4 Turbo OpenAI | 7.7 | — |
| 615 | Command A Cohere | 7.5 | — |
| 616 | Nova Pro Amazon | 7.5 | — |
| 617 | Gemma 3 27b Google · 오픈소스 | 7.4 | — |
| 618 | Llama 3 1 Instruct 8b Meta · 오픈소스 | 7.4 | — |
| 619 | Llama 3 1 Nemotron Instruct 70b Meta · 오픈소스 | 7.4 | — |
| 620 | 7.2 | — | |
| 621 | 7.2 | — | |
| 622 | Ministral 3 3b Mistral | 7.1 | — |
| 623 | Mistral Large 2407 Mistral · 오픈소스 | 7.0 | — |
| 624 | Gpt 4 OpenAI | 6.8 | — |
| 625 | Qwen3 14b Instruct Alibaba · 오픈소스 | 6.8 | — |
| 626 | Gemini 2 5 Flash Lite Google | 6.7 | — |
| 627 | Hermes 4 Llama 3 1 70b Meta · 오픈소스 | 6.7 | — |
| 628 | Mistral Small 3 Mistral · 오픈소스 | 6.7 | — |
| 629 | Nova Lite Amazon | 6.7 | — |
| 630 | Qwen3 30b A3b Instruct Alibaba · 오픈소스 | 6.6 | — |
| 631 | Llama 3 1 Instruct 70b Meta · 오픈소스 | 6.5 | — |
| 632 | Qwen Turbo Alibaba · 오픈소스 | 6.0 | — |
| 633 | Reka Flash Reka | 6.0 | — |
| 634 | Solar Mini Upstage | 6.0 | — |
| 635 | Phi 4 Mini Microsoft · 오픈소스 | 5.7 | — |
| 636 | Gemma 3 12b Google · 오픈소스 | 5.5 | — |
| 637 | DeepSeek R1 DeepSeek · 오픈소스 · reasoning | 5.4 | 1422 |
| 638 | Granite 4 0 H Small IBM · 오픈소스 | 4.9 | — |
| 639 | Hermes 3 Llama 3 1 70b Meta · 오픈소스 | 4.8 | — |
| 640 | Jamba 1 5 Large AI21 Labs | 4.8 | — |
| 641 | Qwen3 8b Instruct Alibaba · 오픈소스 | 4.8 | — |
| 642 | Qwen3 Omni 30b A3b Instruct Alibaba · 오픈소스 | 4.8 | — |
| 643 | Nova Micro Amazon | 4.4 | — |
| 644 | Mistral Small Mistral · 오픈소스 | 4.3 | — |
| 645 | 4.2 | — | |
| 646 | Mistral Large Mistral · 오픈소스 | 4.1 | — |
| 647 | Llama 2 Chat 7b Meta · 오픈소스 | 3.9 | — |
| 648 | Reka Flash 3 Reka | 3.7 | — |
| 649 | Claude 3 Haiku Anthropic | 3.5 | — |
| 650 | Gpt 35 Turbo OpenAI | 3.2 | — |
| 651 | Mistral Medium Mistral · 오픈소스 | 3.2 | — |
| 652 | Mistral Small 2402 Mistral · 오픈소스 | 3.2 | — |
| 653 | Llama 3 Instruct 70b Meta · 오픈소스 | 3.1 | — |
| 654 | Llama 3 2 Instruct 11b Vision Meta · 오픈소스 | 3.0 | — |
| 655 | Command R Plus 04 2024 Cohere | 2.6 | — |
| 656 | Olmo 3 7b Instruct AI2 · 오픈소스 | 2.4 | — |
| 657 | Jamba 1 5 Mini AI21 Labs | 2.3 | — |
| 658 | Apertus 70b Instruct Swiss AI | 2.0 | — |
| 659 | Mixtral 8x7b Instruct Mistral | 2.0 | — |
| 660 | Command R 03 2024 Cohere | 1.7 | — |
| 661 | Mistral 7b Instruct Mistral · 오픈소스 | 1.7 | — |
| 662 | Granite 3 3 8b Instruct IBM · 오픈소스 | 1.3 | — |
| 663 | Apertus 8b Instruct Swiss AI | 1.0 | — |
| 664 | Gemma 3 1b Google · 오픈소스 | 1.0 | — |
| 665 | Gemma 3 4b Google · 오픈소스 | 1.0 | — |
| 666 | Gemma 3n E2b Google · 오픈소스 | 1.0 | — |
| 667 | Gemma 3n E4b Google · 오픈소스 | 1.0 | — |
| 668 | Llama 3 Instruct 8b Meta · 오픈소스 | 1.0 | — |
| 669 | Tiny Aya Global Cohere | 1.0 | — |
| 670 | Claude Mythos 5 Anthropic · reasoning · preview | 0.0 | — |
| 671 | GPT-5.5 Pro OpenAI | 0.0 | — |
| 672 | Claude Sonnet 4.6 (max) Anthropic | 0.0 | — |
| 673 | Amazon Nova Amazon | 0.0 | — |
| 674 | Async Flash V1 5 Async | 0.0 | — |
| 675 | Async Pro V1 0 Async | 0.0 | — |
| 676 | Asyncflow V2 Async | 0.0 | — |
| 677 | Claude Sonnet 5 High Anthropic | 0.0 | — |
| 678 | Claude Sonnet 5 Low Anthropic | 0.0 | — |
| 679 | Claude Sonnet 5 Medium Anthropic | 0.0 | — |
| 680 | Claude Sonnet 5 Xhigh Anthropic | 0.0 | — |
| 681 | Cogito V2 1 Reasoning Cogito · reasoning | 0.0 | — |
| 682 | Falcon 2 TII · 오픈소스 | 0.0 | — |
| 683 | Gemini Google | 0.0 | — |
| 684 | 0.0 | — | |
| 685 | Gemini_nano Banana Pro Google | 0.0 | — |
| 686 | Gladia Solaria Upstage | 0.0 | — |
| 687 | Gpt 5 4 Pro OpenAI | 0.0 | — |
| 688 | Gpt Realtime 2 OpenAI | 0.0 | — |
| 689 | Grok Stt xAI | 0.0 | — |
| 690 | Hidream O1 Image OpenAI · reasoning | 0.0 | — |
| 691 | Minimax H3 MiniMax · 오픈소스 | 0.0 | — |
| 692 | Mistral Mistral · 오픈소스 | 0.0 | — |
| 693 | Nvidia NVIDIA | 0.0 | — |
| 694 | 0.0 | — | |
| 695 | Ocateve 2 Ocat | 0.0 | — |
| 696 | Qwen Image Alibaba · 오픈소스 | 0.0 | — |
| 697 | Qwen3 Asr Alibaba · 오픈소스 | 0.0 | — |
| 698 | Apodex 1.1 Independent · 오픈소스 | 0.0 | — |
| 699 | Muse Spark 1.3 (xhigh) Muse · reasoning | 0.0 | — |
| 700 | Quasar 438B Open Source · 오픈소스 · reasoning | 0.0 | — |
Podium Score는 5개 리더보드의 가중 평균입니다. 자세한 내용은 평가 방법을 참고하세요.