Daten aktualisiert vor 36 MinutenQuellen:Text Arena
Live Benchmarks / Allgemeiner Chat
Allgemeine Chat-Benchmarks
Open-Ended Chat-Präferenz-Rankings aus echten Nutzervotes.
Text Arena
Originalquelle ansehen →| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 ThinkingAnthropic | 1504Elo |
| 2 | Claude Opus 4.6Anthropic | 1496Elo |
| 3 | Muse SparkMeta | 1493Elo |
| 4 | Gemini 3.1 ProGoogle | 1492Elo |
| 5 | Gemini 3 ProGoogle | 1486Elo |
| 6 | Grok 4.20xAI | 1486Elo |
| 7 | GPT-5.4OpenAI | 1484Elo |
| 8 | 1478Elo | |
| 9 | 1477Elo | |
| 10 | 1476Elo | |
| 11 | Gemini 3 FlashGoogle | 1474Elo |
| 12 | Claude Opus 4.5 ThinkingAnthropic | 1473Elo |
| 13 | Glm 5.1Z.ai | 1471Elo |
| 14 | 1471Elo | |
| 15 | Claude Opus 4.5Anthropic | 1468Elo |
| 16 | Qwen3.5 Max PreviewAlibaba | 1466Elo |
| 17 | Gpt 5.4OpenAI | 1466Elo |
| 18 | 1463Elo | |
| 19 | Claude Sonnet 4.6Anthropic | 1462Elo |
| 20 | Dola Seed 2.0 ProBytedance | 1461Elo |
| 21 | Grok 4.1xAI | 1460Elo |
| 22 | GPT-5.4 MiniOpenAI | 1459Elo |
| 23 | Gpt 5.3 Chat LatestOpenAI | 1456Elo |
| 24 | GLM-5Z.ai | 1456Elo |
| 25 | Gpt 5.1 HighOpenAI | 1454Elo |
| 26 | Claude Sonnet 4.5 ThinkingAnthropic | 1452Elo |
| 27 | Kimi K2.5 ThinkingMoonshot | 1452Elo |
| 28 | Claude Sonnet 4.5Anthropic | 1451Elo |
| 29 | Gemma 4 31bGoogle | 1451Elo |
| 30 | Ernie 5.0 0110Baidu | 1450Elo |
| 31 | 1449Elo | |
| 32 | 1448Elo | |
| 33 | Gemini 2.5 ProGoogle | 1448Elo |
| 34 | Qwen 3.5 397BAlibaba | 1447Elo |
| 35 | Claude Opus 4.1Anthropic | 1447Elo |
| 36 | MiMo V2 ProXiaomi | 1446Elo |
| 37 | 1444Elo | |
| 38 | 1443Elo | |
| 39 | GLM-4.7Z.ai | 1443Elo |
| 40 | Gpt 5.2 HighOpenAI | 1442Elo |
| 41 | Longcat Flash Chat 2602 ExpMeituan | 1440Elo |
| 42 | GPT-5.2OpenAI | 1439Elo |
| 43 | GPT-5.1OpenAI | 1439Elo |
| 44 | Gemma 4 26b A4bGoogle | 1438Elo |
| 45 | Gemini 3.1 Flash LiteGoogle | 1435Elo |
| 46 | Qwen3 Max PreviewAlibaba | 1435Elo |
| 47 | Gpt 5 HighOpenAI | 1433Elo |
| 48 | Kimi K2.5 InstantMoonshot | 1433Elo |
| 49 | 1432Elo | |
| 50 | O3 2025 04 16OpenAI | 1431Elo |
| 51 | Kimi K2 TurboMoonshot | 1430Elo |
| 52 | 1428Elo | |
| 53 | Gpt 5 ChatOpenAI | 1426Elo |
| 54 | GLM-4.6Z.ai | 1426Elo |
| 55 | Deepseek v3.2 Exp ThinkingDeepSeek | 1425Elo |
| 56 | Qwen3 Max 2025 09 23Alibaba | 1424Elo |
| 57 | DeepSeek V3.2DeepSeek | 1424Elo |
| 58 | Claude Opus 4 20250514 Thinking 16kAnthropic | 1424Elo |
| 59 | 1423Elo | |
| 60 | Deepseek v3.2 ExpDeepSeek | 1423Elo |
| 61 | DeepSeek V3.2 ThinkingDeepSeek | 1423Elo |
| 62 | Deepseek R1 0528DeepSeek | 1422Elo |
| 63 | 1421Elo | |
| 64 | 1419Elo | |
| 65 | Deepseek v3.1DeepSeek | 1418Elo |
| 66 | Kimi K2 0905 PreviewMoonshot | 1418Elo |
| 67 | Qwen 3.5 122BAlibaba | 1418Elo |
| 68 | Kimi K2 0711 PreviewMoonshot | 1417Elo |
| 69 | Deepseek v3.1 ThinkingDeepSeek | 1417Elo |
| 70 | Deepseek v3.1 Terminus ThinkingDeepSeek | 1416Elo |
| 71 | Deepseek v3.1 TerminusDeepSeek | 1416Elo |
| 72 | Qwen3 Vl 235b A22b InstructAlibaba | 1416Elo |
| 73 | 1415Elo | |
| 74 | Mistral Large 3Mistral | 1415Elo |
| 75 | Gpt 4.1 2025 04 14OpenAI | 1413Elo |
| 76 | Claude Opus 4 20250514Anthropic | 1412Elo |
| 77 | 1412Elo | |
| 78 | Gemini 2.5 FlashGoogle | 1411Elo |
| 79 | Glm 4.5Z.ai | 1411Elo |
| 80 | Grok 4 0709xAI | 1410Elo |
| 81 | Mistral Medium 2508Mistral | 1410Elo |
| 82 | Claude Haiku 4.5Anthropic | 1408Elo |
| 83 | 1405Elo | |
| 84 | 1404Elo | |
| 85 | MiniMax M2.7MiniMax | 1404Elo |
| 86 | MiniMax M2.5MiniMax | 1403Elo |
| 87 | Qwen3 235b A22b No ThinkingAlibaba | 1403Elo |
| 88 | Qwen 3.5 27BAlibaba | 1402Elo |
| 89 | Gpt 5.4 Nano HighOpenAI | 1402Elo |
| 90 | Qwen3 Next 80b A3b InstructAlibaba | 1402Elo |
| 91 | O1 2024 12 17OpenAI | 1402Elo |
| 92 | Longcat Flash ChatMeituan | 1401Elo |
| 93 | Qwen3.5 FlashAlibaba | 1400Elo |
| 94 | 1400Elo | |
| 95 | 1399Elo | |
| 96 | Deepseek R1DeepSeek | 1398Elo |
| 97 | Hunyuan Vision 1.5 ThinkingTencent | 1397Elo |
| 98 | Qwen3.5 35b A3bAlibaba | 1396Elo |
| 99 | Qwen3 Vl 235b A22b ThinkingAlibaba | 1395Elo |
| 100 | 1395Elo | |
| 101 | Deepseek v3 0324DeepSeek | 1395Elo |
| 102 | Mai 1 PreviewMicrosoft AI | 1393Elo |
| 103 | 1392Elo | |
| 104 | Step 3.5 FlashStepfun | 1392Elo |
| 105 | O4 Mini 2025 04 16OpenAI | 1390Elo |
| 106 | Gpt 5 Mini HighOpenAI | 1389Elo |
| 107 | Claude Sonnet 4 20250514Anthropic | 1389Elo |
| 108 | O1 PreviewOpenAI | 1388Elo |
| 109 | Qwen 3 CoderAlibaba | 1387Elo |
| 110 | Hunyuan T1 20250711Tencent | 1387Elo |
| 111 | mimo-v2-flash (thinking)Xiaomi | 1387Elo |
| 112 | 1386Elo | |
| 113 | Mistral Medium 2505Mistral | 1386Elo |
| 114 | MiniMax M2.1MiniMax | 1386Elo |
| 115 | Qwen3 30b A3b Instruct 2507Alibaba | 1383Elo |
| 116 | Hunyuan Turbos 20250416Tencent | 1383Elo |
| 117 | Gpt 4.1 Mini 2025 04 14OpenAI | 1382Elo |
| 118 | 1380Elo | |
| 119 | Glm 4.6vZ.ai | 1378Elo |
| 120 | Qwen3 235b A22bAlibaba | 1374Elo |
| 121 | 1374Elo | |
| 122 | Trinity LargeArcee AI | 1374Elo |
| 123 | Qwen2.5 MaxAlibaba | 1374Elo |
| 124 | Glm 4.5 AirZ.ai | 1373Elo |
| 125 | Claude 3 5 Sonnet 20241022Anthropic | 1372Elo |
| 126 | Claude 3 7 Sonnet 20250219Anthropic | 1370Elo |
| 127 | Qwen3 Next 80b A3b ThinkingAlibaba | 1369Elo |
| 128 | Glm 4.7 FlashZ.ai | 1368Elo |
| 129 | 1367Elo | |
| 130 | Gemma 3 27b ItGoogle | 1365Elo |
| 131 | Minimax M1MiniMax | 1363Elo |
| 132 | O3 Mini HighOpenAI | 1363Elo |
| 133 | 1363Elo | |
| 134 | 1361Elo | |
| 135 | Gemini 2.0 Flash 001Google | 1360Elo |
| 136 | Deepseek v3DeepSeek | 1358Elo |
| 137 | 1357Elo | |
| 138 | Mistral Small 2506Mistral | 1357Elo |
| 139 | Intellect 3Prime Intellect | 1356Elo |
| 140 | Gpt Oss 120bOpenAI | 1354Elo |
| 141 | Command A 03 2025Cohere | 1353Elo |
| 142 | Glm 4.5vZ.ai | 1353Elo |
| 143 | 1353Elo | |
| 144 | Gemini 1.5 Pro 002Google | 1351Elo |
| 145 | 1350Elo | |
| 146 | Hunyuan Turbos 20250226Tencent | 1348Elo |
| 147 | Step 3Stepfun | 1348Elo |
| 148 | O3 MiniOpenAI | 1347Elo |
| 149 | 1347Elo | |
| 150 | Qwen3 32bAlibaba | 1347Elo |
| 151 | Mercury 2Inception AI | 1347Elo |
| 152 | 1347Elo | |
| 153 | MiniMax M2MiniMax | 1346Elo |
| 154 | Ling Flash 2.0Ant Group | 1346Elo |
| 155 | Qwen Plus 0125Alibaba | 1346Elo |
| 156 | Gpt 4o 2024 05 13OpenAI | 1345Elo |
| 157 | 1343Elo | |
| 158 | Glm 4 Plus 0111Zhipu | 1343Elo |
| 159 | Gemma 3 12b ItGoogle | 1341Elo |
| 160 | Claude 3 5 Sonnet 20240620Anthropic | 1341Elo |
| 161 | Hunyuan Turbo 0110Tencent | 1340Elo |
| 162 | Nova 2 LiteAmazon | 1337Elo |
| 163 | O1 MiniOpenAI | 1337Elo |
| 164 | Gpt 5 Nano HighOpenAI | 1337Elo |
| 165 | Qwq 32bAlibaba | 1336Elo |
| 166 | 1335Elo | |
| 167 | Gpt 4o 2024 08 06OpenAI | 1334Elo |
| 168 | 1334Elo | |
| 169 | Gemini Advanced 0514Google | 1334Elo |
| 170 | Step 2 16k Exp 202412Stepfun | 1334Elo |
| 171 | 1332Elo | |
| 172 | 1331Elo | |
| 173 | Yi Lightning01.AI | 1328Elo |
| 174 | 1327Elo | |
| 175 | Qwen3 30b A3bAlibaba | 1327Elo |
| 176 | Molmo 2 8bAi2 | 1327Elo |
| 177 | 1327Elo | |
| 178 | Hunyuan Large 2025 02 10Tencent | 1326Elo |
| 179 | Gpt 4 Turbo 2024 04 09OpenAI | 1323Elo |
| 180 | Deepseek v2.5 1210DeepSeek | 1323Elo |
| 181 | Gemini 1.5 Pro 001Google | 1323Elo |
| 182 | Claude 3 5 Haiku 20241022Anthropic | 1323Elo |
| 183 | 1322Elo | |
| 184 | Gpt 4.1 Nano 2025 04 14OpenAI | 1321Elo |
| 185 | Ring Flash 2.0Ant Group | 1321Elo |
| 186 | Claude 3 Opus 20240229Anthropic | 1321Elo |
| 187 | Step 1o Turbo 202506Stepfun | 1320Elo |
| 188 | Glm 4 PlusZhipu AI | 1319Elo |
| 189 | Gemma 3n E4b ItGoogle | 1318Elo |
| 190 | 1318Elo | |
| 191 | Gpt Oss 20bOpenAI | 1318Elo |
| 192 | 1317Elo | |
| 193 | Qwen Max 0919Alibaba | 1317Elo |
| 194 | Gpt 4o Mini 2024 07 18OpenAI | 1317Elo |
| 195 | Qwen2.5 Plus 1127Alibaba | 1315Elo |
| 196 | Athene v2 ChatNexusFlow | 1314Elo |
| 197 | Mistral Large 2407Mistral | 1313Elo |
| 198 | Gpt 4 0125 PreviewOpenAI | 1312Elo |
| 199 | Gpt 4 1106 PreviewOpenAI | 1312Elo |
| 200 | Hunyuan Standard 2025 02 10Tencent | 1311Elo |
| 201 | Gemini 1.5 Flash 002Google | 1309Elo |
| 202 | 1308Elo | |
| 203 | Deepseek v2.5DeepSeek | 1307Elo |
| 204 | MercuryInception AI | 1306Elo |
| 205 | Athene 70b 0725NexusFlow | 1306Elo |
| 206 | 1305Elo | |
| 207 | Mistral Large 2411Mistral | 1305Elo |
| 208 | Magistral Medium 2506Mistral | 1303Elo |
| 209 | Gemma 3 4b ItGoogle | 1303Elo |
| 210 | 1303Elo | |
| 211 | Qwen2.5 72b InstructAlibaba | 1302Elo |
| 212 | 1298Elo | |
| 213 | Hunyuan Large VisionTencent | 1294Elo |
| 214 | 1293Elo | |
| 215 | Amazon Nova Pro v1.0Amazon | 1290Elo |
| 216 | Jamba 1.5 LargeAI21 Labs | 1288Elo |
| 217 | Gemma 2 27b ItGoogle | 1288Elo |
| 218 | Reka Core 20240904Reka AI | 1287Elo |
| 219 | 1287Elo | |
| 220 | Gpt 4 0314OpenAI | 1286Elo |
| 221 | 1286Elo | |
| 222 | 1285Elo | |
| 223 | 1285Elo | |
| 224 | Gemini 1.5 Flash 001Google | 1285Elo |
| 225 | Claude 3 Sonnet 20240229Anthropic | 1280Elo |
| 226 | Gemma 2 9b It SimpoPrinceton | 1279Elo |
| 227 | Nemotron 4 340b InstructNvidia | 1276Elo |
| 228 | Command R Plus 08 2024Cohere | 1276Elo |
| 229 | 1275Elo | |
| 230 | Gpt 4 0613OpenAI | 1274Elo |
| 231 | 1273Elo | |
| 232 | Glm 4 0520Zhipu AI | 1273Elo |
| 233 | Reka Flash 20240904Reka AI | 1271Elo |
| 234 | Qwen2.5 Coder 32b InstructAlibaba | 1270Elo |
| 235 | C4ai Aya Expanse 32bCohere | 1266Elo |
| 236 | Gemma 2 9b ItGoogle | 1265Elo |
| 237 | Deepseek Coder v2DeepSeek | 1263Elo |
| 238 | Command R PlusCohere | 1261Elo |
| 239 | Qwen2 72b InstructAlibaba | 1261Elo |
| 240 | Amazon Nova Lite v1.0Amazon | 1260Elo |
| 241 | Claude 3 Haiku 20240307Anthropic | 1260Elo |
| 242 | Gemini 1.5 Flash 8b 001Google | 1258Elo |
| 243 | Phi 4Microsoft | 1255Elo |
| 244 | 1251Elo | |
| 245 | Command R 08 2024Cohere | 1249Elo |
| 246 | Mistral Large 2402Mistral | 1241Elo |
| 247 | Amazon Nova Micro v1.0Amazon | 1240Elo |
| 248 | Jamba 1.5 MiniAI21 Labs | 1238Elo |
| 249 | Ministral 8b 2410Mistral | 1237Elo |
| 250 | Gemini Pro Dev ApiGoogle | 1234Elo |
| 251 | Qwen1.5 110b ChatAlibaba | 1233Elo |
| 252 | Hunyuan Standard 256kTencent | 1233Elo |
| 253 | 1232Elo | |
| 254 | Qwen1.5 72b ChatAlibaba | 1232Elo |
| 255 | Mixtral 8x22b Instruct v0.1Mistral | 1228Elo |
| 256 | Command RCohere | 1226Elo |
| 257 | Reka Flash 21b 20240226Reka AI | 1225Elo |
| 258 | Gpt 3.5 Turbo 0125OpenAI | 1223Elo |
| 259 | C4ai Aya Expanse 8bCohere | 1222Elo |
| 260 | 1222Elo | |
| 261 | Mistral MediumMistral | 1222Elo |
| 262 | Gemini ProGoogle | 1221Elo |
| 263 | 1220Elo | |
| 264 | Yi 1.5 34b Chat01.AI | 1212Elo |
| 265 | Zephyr Orpo 141b A35b v0.1HuggingFace | 1212Elo |
| 266 | 1211Elo | |
| 267 | 1207Elo | |
| 268 | Qwen1.5 32b ChatAlibaba | 1203Elo |
| 269 | Gpt 3.5 Turbo 1106OpenAI | 1201Elo |
| 270 | Gemma 2 2b ItGoogle | 1199Elo |
| 271 | Phi 3 Medium 4k InstructMicrosoft | 1197Elo |
| 272 | Mixtral 8x7b Instruct v0.1Mistral | 1196Elo |
| 273 | Dbrx Instruct PreviewDatabricks | 1194Elo |
| 274 | Internlm2 5 20b ChatInternLM | 1190Elo |
| 275 | Qwen1.5 14b ChatAlibaba | 1190Elo |
| 276 | Wizardlm 70bMicrosoft | 1183Elo |
| 277 | Deepseek Llm 67b ChatDeepSeek | 1183Elo |
| 278 | Yi 34b Chat01.AI | 1183Elo |
| 279 | Openchat 3.5 0106OpenChat | 1181Elo |
| 280 | Openchat 3.5OpenChat | 1181Elo |
| 281 | 1181Elo | |
| 282 | Gemma 1.1 7b ItGoogle | 1180Elo |
| 283 | Snowflake Arctic InstructSnowflake | 1178Elo |
| 284 | 1178Elo | |
| 285 | Tulu 2 Dpo 70bAllenAI/UW | 1177Elo |
| 286 | Openhermes 2.5 Mistral 7bNousResearch | 1174Elo |
| 287 | Vicuna 33bLMSYS | 1172Elo |
| 288 | Starling Lm 7b BetaNexusflow | 1170Elo |
| 289 | Phi 3 Small 8k InstructMicrosoft | 1170Elo |
| 290 | Llama 2 70b ChatMeta | 1170Elo |
| 291 | Starling Lm 7b AlphaUC Berkeley | 1166Elo |
| 292 | 1166Elo | |
| 293 | Nous Hermes 2 Mixtral 8x7b DpoNousResearch | 1164Elo |
| 294 | Qwq 32b PreviewAlibaba | 1156Elo |
| 295 | 1155Elo | |
| 296 | Llama2 70b Steerlm ChatNvidia | 1154Elo |
| 297 | Solar 10.7b Instruct v1.0Upstage AI | 1151Elo |
| 298 | Dolphin 2.2.1 Mistral 7bCognitive Computations | 1151Elo |
| 299 | Mpt 30b ChatMosaicML | 1149Elo |
| 300 | Mistral 7b Instruct v0.2Mistral | 1148Elo |
| 301 | Wizardlm 13bMicrosoft | 1148Elo |
| 302 | 1146Elo | |
| 303 | Qwen1.5 7b ChatAlibaba | 1143Elo |
| 304 | Phi 3 Mini 4k Instruct June 2024Microsoft | 1142Elo |
| 305 | Llama 2 13b ChatMeta | 1140Elo |
| 306 | Vicuna 13bLMSYS | 1140Elo |
| 307 | Qwen 14b ChatAlibaba | 1137Elo |
| 308 | Palm 2Google | 1136Elo |
| 309 | Gemma 7b ItGoogle | 1135Elo |
| 310 | 1135Elo | |
| 311 | Zephyr 7b BetaHuggingFace | 1130Elo |
| 312 | Phi 3 Mini 128k InstructMicrosoft | 1128Elo |
| 313 | Phi 3 Mini 4k InstructMicrosoft | 1127Elo |
| 314 | 1126Elo | |
| 315 | Zephyr 7b AlphaHuggingFace | 1126Elo |
| 316 | Stripedhyena Nous 7bTogether AI | 1120Elo |
| 317 | 1118Elo | |
| 318 | Gemma 1.1 2b ItGoogle | 1114Elo |
| 319 | Vicuna 7bLMSYS | 1113Elo |
| 320 | Smollm2 1.7b InstructHuggingFace | 1113Elo |
| 321 | 1110Elo | |
| 322 | Mistral 7b InstructMistral | 1108Elo |
| 323 | Llama 2 7b ChatMeta | 1107Elo |
| 324 | Gemma 2b ItGoogle | 1091Elo |
| 325 | Qwen1.5 4b ChatAlibaba | 1089Elo |
| 326 | 1073Elo | |
| 327 | Koala 13bUC Berkeley | 1069Elo |
| 328 | Alpaca 13bStanford | 1066Elo |
| 329 | Gpt4all 13b SnoozyNomic AI | 1065Elo |
| 330 | Mpt 7b ChatMosaicML | 1061Elo |
| 331 | Chatglm3 6bTsinghua | 1055Elo |
| 332 | RWKV 4 Raven 14BRWKV | 1040Elo |
| 333 | Chatglm2 6bTsinghua | 1023Elo |
| 334 | Oasst Pythia 12bOpenAssistant | 1021Elo |
| 335 | Chatglm 6bTsinghua | 994Elo |
| 336 | Fastchat T5 3bLMSYS | 990Elo |
| 337 | Dolly v2 12bDatabricks | 979Elo |
| 338 | Llama 13bMeta | 971Elo |
| 339 | Stablelm Tuned Alpha 7bStability | 951Elo |
Verwandte Diskussion
Community-Puls
90%+ fewer tokens per session by reading a pre-compiled wiki instead of exploring files cold. Built from Karpathy's workflow.
Reduced Claude context from 47,450 tokens → 360 tokens. **“This week, Andrej Karpathy shared his ‘LLM Knowledge Bases’ setup and closed by saying, ‘I think there is room here for an incredible new product instead of a hacky collection of sc
OpenAI launch $100 ChatGPT plan
We gave 12 LLMs a startup to run for a year. GLM-5 nearly matched Claude Opus 4.6 at 11× lower cost.
So, this week claude wiped agentic AI startups with a new update. Also, as they have mythos now, they will ship things very fast without any trouble
How I use Cursor 10+ hours a day without torching my Claude Opus 4.6 limits
Anyone else here doing full-stack Next.js in Cursor and watching the Claude quota evaporate before lunch? I used to be in the same boat — massive context windows from all the components, pages, and DB logic would smoke the default limits fa
Brauchen Sie Hilfe bei der Auswahl des richtigen KI-Modells?
Benchmarks sind ein Ausgangspunkt, keine Antwort. Das richtige Modell hängt von Ihrem Workload, Budget und Ihren Integrations-Anforderungen ab – lassen Sie es uns gemeinsam herausfinden.