LMArena German leaderboard
LMArena’s text votes on german prompts. Claude Opus 5 leads with a rating of 1530.
- Models
- 261
- Leader
- Claude Opus 5
- Source
- LMArena
- As of
- Oct 22, 2026
Open weightsProprietaryBest for the price
Full leaderboard
| Rank | Model | Lab | Rating | 95% interval | Votes | Price in / out |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5 | Anthropic | 1530 | 1504–1556 | 584 | $5 / $25 |
| 2 | Gemini 3 Pro | 1515 | 1494–1537 | 811 | — | |
| 3 | Muse Spark 1.3 | Meta | 1513 | 1479–1547 | 301 | $1.25 / $4.25 |
| 4 | Gemini 3.7 Flash | 1509 | 1482–1537 | 461 | $0.75 / $3.75 | |
| 5 | Gemini 3.8 Flash | 1509 | 1486–1532 | 684 | $0.82 / $4.13 | |
| 7 | Claude Opus 4.6 | Anthropic | 1502 | 1485–1519 | 1.3K | $5 / $25 |
| 8 | Claude Fable 5.1 | Anthropic | 1498 | 1464–1532 | 304 | $10 / $50 |
| 9 | Muse Spark | Meta | 1498 | 1459–1537 | 237 | — |
| 10 | Gemini 3 Flash | 1497 | 1472–1522 | 572 | $0.50 / $3 | |
| 11 | Claude Opus 4.7 | Anthropic | 1495 | 1476–1514 | 1K | $5 / $25 |
| 12 | Gemini 3.5 Flash | 1494 | 1471–1516 | 759 | $1.50 / $9 | |
| 14 | Kimi K3 | Moonshot AI | 1492 | 1468–1515 | 686 | $0.24 / $11 |
| 15 | Gemini 3.1 Pro Preview | 1490 | 1476–1504 | 2.2K | $2 / $12 | |
| 17 | Qwen3.5-Max-Preview | Alibaba | 1487 | 1457–1517 | 383 | — |
| 18 | Gemini 2.5 Pro | 1487 | 1475–1500 | 2.7K | $1.25 / $10 | |
| 19 | GLM-5.3 | Z.ai | 1486 | 1457–1515 | 402 | $0.079 / $1.40 |
| 21 | Claude Fable 5 | Anthropic | 1485 | 1462–1508 | 679 | $10 / $50 |
| 22 | Gemini 3.6 Flash | 1481 | 1456–1505 | 593 | $0.75 / $3.75 | |
| 23 | GPT-5.5 | OpenAI | 1480 | 1461–1499 | 1.1K | $5 / $30 |
| 24 | Qwen3.8-Max | Alibaba | 1476 | 1450–1502 | 478 | $2 / $6 |
| 25 | GPT-5.6 Sol | OpenAI | 1475 | 1452–1498 | 674 | $4 / $20 |
| 26 | NVIDIA-Nemotron-3-Ultra-550B-A55B | NVIDIA | 1474 | 1435–1513 | 211 | — |
| 27 | Claude Opus 4.8 | Anthropic | 1473 | 1454–1492 | 1.1K | $5 / $25 |
| 28 | GPT-5.4 | OpenAI | 1473 | 1454–1491 | 1.1K | $2.50 / $15 |
| 29 | GLM-5.2 | Z.ai | 1471 | 1451–1491 | 935 | $0.034 / $7 |
| 30 | Qwen3.7-Plus | Alibaba | 1471 | 1449–1493 | 762 | $0.32 / $1.28 |
| 31 | ERNIE 5.1 | Baidu | 1470 | 1448–1492 | 748 | — |
| 32 | Muse Spark 1.1 | Meta | 1469 | 1447–1491 | 825 | $1.25 / $4.25 |
| 33 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 1468 | 1433–1504 | 246 | $0.15 / $0.60 |
| 34 | GLM-5.1 | Z.ai | 1467 | 1448–1486 | 1.1K | $1.40 / $4.40 |
| 36 | Grok 4.20 Beta 1 | xAI | 1464 | 1437–1492 | 444 | — |
| 37 | Qwen3-Max-Preview | Alibaba | 1462 | 1437–1487 | 596 | — |
| 38 | GPT-5.6 Terra | OpenAI | 1461 | 1438–1483 | 732 | $2 / $12 |
| 39 | ERNIE 5.0 | Baidu | 1460 | 1419–1501 | 222 | — |
| 41 | MiMo-V2.5-Pro | Xiaomi | 1459 | 1442–1477 | 1.3K | $0.30 / $0.61 |
| 42 | DeepSeek-V4-Pro | DeepSeek | 1458 | 1439–1477 | 997 | $0.66 / $1.98 |
| 43 | GLM-5.3-Flash | Z.ai | 1457 | 1433–1481 | 654 | $0.15 / $0.50 |
| 44 | GPT-4.5 Preview | OpenAI | 1457 | 1424–1489 | 319 | — |
| 45 | Grok 4.20 Multi-Agent Beta | xAI | 1457 | 1437–1476 | 1.1K | — |
| 46 | GPT-5.6 Luna | OpenAI | 1455 | 1433–1478 | 711 | $0.20 / $1.20 |
| 47 | Mistral Medium 3.5 | Mistral AI | 1455 | 1412–1499 | 173 | $1.50 / $7.50 |
| 48 | MiMo-V2.6-Flash | Xiaomi | 1455 | 1416–1495 | 230 | $0.14 / $0.28 |
| 49 | GPT-6 Astra | OpenAI | 1455 | 1415–1495 | 213 | $10 / $50 |
| 50 | Gemini 3.5 Flash-Lite | 1454 | 1431–1477 | 656 | $0.30 / $2.50 | |
| 51 | Qwen3.6-Plus | Alibaba | 1452 | 1430–1473 | 794 | $0.33 / $1.95 |
| 52 | Step 5 Preview | StepFun | 1451 | 1409–1493 | 162 | $1 / $2.70 |
| 53 | Kimi K2.6 | Moonshot AI | 1451 | 1430–1472 | 744 | $0.65 / $3.41 |
| 54 | Claude Opus 4.5 | Anthropic | 1450 | 1432–1468 | 1.1K | $5 / $25 |
| 56 | Grok 4.5 | xAI | 1448 | 1425–1471 | 685 | $2 / $6 |
| 58 | GPT-5.2 Chat | OpenAI | 1448 | 1422–1473 | 563 | $1.75 / $14 |
| 59 | GLM-4.6 | Z.ai | 1447 | 1425–1469 | 681 | $0.55 / $2.20 |
| 60 | GLM-5 | Z.ai | 1447 | 1421–1473 | 511 | $1 / $3.20 |
| 61 | Grok 4.1 | xAI | 1446 | 1429–1464 | 1.2K | — |
| 62 | IInkling | Thinky | 1445 | 1422–1468 | 667 | $1 / $4.05 |
| 63 | GPT-5.2 | OpenAI | 1444 | 1423–1465 | 834 | $1.75 / $14 |
| 64 | Qwen3.5-397B-A17B | Alibaba | 1444 | 1427–1460 | 1.5K | $0.50 / $3.60 |
| 65 | Hy3 | Tencent | 1444 | 1407–1480 | 233 | $0.083 / $0.33 |
| 66 | Dola Seed 2.0 Pro | ByteDance | 1442 | 1425–1460 | 1.3K | — |
| 67 | Claude Sonnet 5 | Anthropic | 1442 | 1421–1464 | 827 | $2 / $10 |
| 68 | Qwen3.8-27B | Alibaba | 1442 | 1413–1471 | 420 | $0.20 / $2.50 |
| 70 | Kimi K2.5 | Moonshot AI | 1441 | 1424–1458 | 1.3K | $0.50 / $2.50 |
| 71 | Grok 4.20 Beta | xAI | 1441 | 1422–1460 | 1K | — |
| 73 | DeepSeek-V3.2-Exp | DeepSeek | 1440 | 1403–1477 | 227 | $0.28 / $0.42 |
| 75 | Mistral Large 3 | Mistral AI | 1439 | 1422–1456 | 1.4K | $0.50 / $1.50 |
| 76 | GPT-5.1 | OpenAI | 1438 | 1416–1460 | 718 | $1.25 / $10 |
| 80 | Qwen3-235B-A22B-Instruct | Alibaba | 1432 | 1418–1447 | 1.8K | $0.09 / $0.55 |
| 81 | Mistral Medium 3.1 | Mistral AI | 1432 | 1418–1447 | 1.7K | $0.40 / $2 |
| 82 | Grok 3 Preview | xAI | 1431 | 1409–1452 | 786 | — |
| 83 | Gemini 3.1 Flash-Lite Preview | 1430 | 1411–1449 | 1K | $0.25 / $1.50 | |
| 84 | MiniMax-M3 | MiniMax | 1430 | 1411–1448 | 1.1K | $0.30 / $1.20 |
| 86 | Grok 4 | xAI | 1429 | 1409–1449 | 905 | — |
| 87 | Claude Sonnet 4.6 | Anthropic | 1428 | 1410–1446 | 1.2K | $3 / $15 |
| 88 | Claude Sonnet 4.5 | Anthropic | 1427 | 1411–1444 | 1.4K | $3 / $15 |
| 89 | GLM-4.7 | Z.ai | 1426 | 1389–1464 | 223 | $0.54 / $1.98 |
| 90 | Qwen3.5-122B-A10B | Alibaba | 1425 | 1398–1453 | 427 | $0.40 / $3.20 |
| 91 | Grok 4.6 | xAI | 1424 | 1398–1451 | 541 | $2 / $6 |
| 92 | Qwen3-VL-235B-A22B-Instruct | Alibaba | 1424 | 1389–1460 | 279 | $0.21 / $1.90 |
| 93 | ChatGPT-4o Latest | OpenAI | 1423 | 1409–1438 | 1.8K | — |
| 94 | GLM-5V-Turbo | Z.ai | 1422 | 1380–1465 | 182 | $1.20 / $4 |
| 95 | MiMo-V2.5 | Xiaomi | 1422 | 1400–1443 | 797 | $0.12 / $0.24 |
| 97 | o3 | OpenAI | 1420 | 1404–1436 | 1.5K | $2 / $8 |
| 98 | DeepSeek-V4-Flash | DeepSeek | 1419 | 1398–1440 | 839 | $0.042 / $0.18 |
| 99 | Gemini 2.5 Flash | 1418 | 1395–1441 | 657 | $0.30 / $2.50 | |
| 101 | MiMo-V2-Pro | Xiaomi | 1417 | 1390–1445 | 434 | — |
| 102 | Qwen3-VL-235B-A22B-Thinking | Alibaba | 1417 | 1374–1460 | 179 | — |
| 104 | Qwen3-Next-80B-A3B-Instruct | Alibaba | 1417 | 1391–1443 | 491 | $0.09 / $1.10 |
| 105 | GPT-5 | OpenAI | 1416 | 1394–1438 | 747 | $1.25 / $10 |
| 108 | Claude Opus 4.1 | Anthropic | 1413 | 1394–1432 | 1K | $15 / $75 |
| 110 | GPT-5.5 Instant | OpenAI | 1411 | 1382–1440 | 430 | — |
| 111 | DeepSeek-V3.1 | DeepSeek | 1411 | 1382–1440 | 397 | $0.25 / $0.95 |
| 112 | GPT-5.4 mini | OpenAI | 1409 | 1389–1429 | 933 | $0.75 / $4.50 |
| 113 | IInkling-Small | Thinky | 1409 | 1384–1434 | 586 | $0.45 / $1.20 |
| 116 | Qwen3-235B-A22B-Thinking | Alibaba | 1408 | 1369–1448 | 211 | $0.45 / $3.50 |
| 117 | LongCat-Flash-Chat Exp | Meituan | 1408 | 1373–1442 | 298 | — |
| 118 | GLM-4.5 | Z.ai | 1407 | 1381–1432 | 539 | $0.60 / $2.20 |
| 120 | Step-3.5-Flash | StepFun | 1405 | 1387–1424 | 1.1K | $0.10 / $0.30 |
| 121 | GPT-5 Chat | OpenAI | 1404 | 1382–1427 | 702 | — |
| 122 | DeepSeek-R1 | DeepSeek | 1404 | 1380–1429 | 597 | $0.50 / $2.15 |
| 123 | Grok 4.1 Fast | xAI | 1403 | 1384–1423 | 931 | — |
| 124 | MiMo-V2-Omni | Xiaomi | 1399 | 1368–1430 | 351 | — |
| 125 | MiniMax-M2.7 | MiniMax | 1398 | 1381–1414 | 1.5K | $0.30 / $1.20 |
| 126 | amazon-nova-experimental-chat | Amazon | 1396 | 1369–1422 | 482 | — |
| 127 | MiMo-V2-Flash | Xiaomi | 1395 | 1358–1432 | 261 | — |
| 128 | Grok 4.3 | xAI | 1395 | 1375–1414 | 1K | $1.25 / $2.50 |
| 129 | Qwen3.5-27B | Alibaba | 1393 | 1365–1420 | 451 | $0.27 / $2.16 |
| 131 | Claude Opus 4 | Anthropic | 1391 | 1371–1410 | 957 | — |
| 132 | Qwen3.5-Flash | Alibaba | 1391 | 1372–1409 | 1.1K | $0.065 / $0.26 |
| 133 | Kimi K2 Thinking Turbo | Moonshot AI | 1390 | 1372–1407 | 1.1K | — |
| 134 | Gemini 2.5 Flash-Lite Preview | 1389 | 1368–1409 | 845 | $0.10 / $0.40 | |
| 135 | Qwen3-235B-A22B | Alibaba | 1387 | 1366–1409 | 762 | $0.09 / $0.55 |
| 136 | Kimi K2 Preview | Moonshot AI | 1387 | 1352–1422 | 278 | $0.60 / $2.50 |
| 139 | GPT-5.3 Chat | OpenAI | 1384 | 1358–1409 | 522 | — |
| 140 | Grok 4 Fast | xAI | 1383 | 1353–1413 | 364 | — |
| 142 | MiniMax-M2.1 Preview | MiniMax | 1381 | 1346–1416 | 297 | $0.30 / $1.20 |
| 143 | GPT-4.1 | OpenAI | 1381 | 1365–1398 | 1.3K | $2 / $8 |
| 144 | Qwen3-30B-A3B-Instruct | Alibaba | 1379 | 1354–1405 | 522 | $0.09 / $0.30 |
| 145 | Mistral Medium 3 | Mistral AI | 1378 | 1359–1396 | 998 | $0.40 / $2 |
| 146 | GLM-4.5-Air | Z.ai | 1378 | 1356–1399 | 744 | $0.13 / $0.85 |
| 147 | GPT-6 Luna | OpenAI | 1376 | 1356–1397 | 1K | $0.10 / $0.50 |
| 149 | DeepSeek-V3 | DeepSeek | 1374 | 1356–1391 | 1.2K | $0.29 / $1.14 |
| 150 | Claude Haiku 4.5 | Anthropic | 1374 | 1361–1387 | 2.5K | $1 / $5 |
| 152 | GPT-6 Sol | OpenAI | 1373 | 1335–1411 | 247 | $2 / $10 |
| 153 | Grok 4.7 | xAI | 1372 | 1334–1411 | 230 | $2 / $6 |
| 155 | Step-3 | StepFun | 1371 | 1325–1417 | 153 | — |
| 156 | Gemma 3 12B IT | 1370 | 1328–1413 | 166 | $0.05 / $0.15 | |
| 157 | GPT-5.4 nano | OpenAI | 1368 | 1347–1388 | 935 | $0.20 / $1.25 |
| 158 | Qwen3.5-35B-A3B | Alibaba | 1367 | 1342–1393 | 488 | $0.14 / $1 |
| 159 | GPT-5 mini | OpenAI | 1366 | 1342–1390 | 592 | $0.25 / $2 |
| 161 | Gemma 3 27B IT | 1362 | 1345–1379 | 1.2K | $0.08 / $0.35 | |
| 162 | MiniMax-M2.5 | MiniMax | 1361 | 1337–1385 | 644 | $0.30 / $1.20 |
| 163 | Solar Pro 4 | Upstage | 1357 | 1327–1388 | 401 | $0.15 / $0.60 |
| 164 | Trinity Large Thinking | Arcee | 1357 | 1328–1385 | 409 | $0.25 / $0.80 |
| 165 | Qwen3-Next-80B-A3B-Thinking | Alibaba | 1356 | 1323–1389 | 296 | $0.15 / $1.20 |
| 166 | Hunyuan TurboS | Tencent | 1355 | 1323–1388 | 329 | — |
| 167 | MiniMax-M2 | MiniMax | 1354 | 1302–1407 | 132 | $0.26 / $1.02 |
| 168 | Gemini 2.0 Flash | 1353 | 1336–1371 | 1.1K | — | |
| 169 | gpt-oss-120b | OpenAI | 1353 | 1330–1375 | 673 | $0.15 / $0.60 |
| 170 | GPT-4.1 mini | OpenAI | 1351 | 1332–1369 | 1.1K | $0.40 / $1.60 |
| 171 | MiniMax-M1 | MiniMax | 1350 | 1330–1370 | 881 | $0.55 / $2.20 |
| 172 | Qwen2.5-Max | Alibaba | 1350 | 1329–1371 | 782 | — |
| 173 | Grok 3 Mini | xAI | 1350 | 1321–1379 | 416 | — |
| 174 | NVIDIA-Nemotron-3-Nano-30B-A3B | NVIDIA | 1348 | 1314–1383 | 293 | — |
| 175 | Grok 3 Mini Beta | xAI | 1347 | 1322–1372 | 538 | — |
| 176 | Amazon Nova 2 Lite | Amazon | 1343 | 1308–1379 | 283 | — |
| 177 | Command A | Cohere | 1341 | 1325–1358 | 1.4K | $0.30 / $1.50 |
| 178 | Qwen3-32B | Alibaba | 1341 | 1301–1382 | 172 | $0.08 / $0.28 |
| 179 | NVIDIA-Nemotron-3-Super-120B-A12B | NVIDIA | 1341 | 1300–1382 | 200 | — |
| 180 | GLM-4-Plus | Z.ai | 1341 | 1302–1380 | 207 | — |
| 181 | Mistral Small 3.2 | Mistral AI | 1340 | 1311–1370 | 427 | — |
| 182 | o1 | OpenAI | 1337 | 1313–1361 | 556 | $15 / $60 |
| 183 | GLM-4.7-Flash | Z.ai | 1336 | 1297–1376 | 228 | $0.06 / $0.40 |
| 184 | o4-mini | OpenAI | 1336 | 1319–1354 | 1.2K | $1.10 / $4.40 |
| 185 | Claude Sonnet 4 | Anthropic | 1331 | 1312–1350 | 1.1K | — |
| 186 | GPT-5 nano | OpenAI | 1327 | 1286–1368 | 206 | $0.05 / $0.40 |
| 187 | Qwen3-Coder-480B-A35B-Instruct | Alibaba | 1325 | 1300–1350 | 591 | — |
| 190 | Step-1o Turbo | StepFun | 1314 | 1283–1346 | 345 | — |
| 191 | Trinity Large Preview | Arcee | 1314 | 1285–1342 | 466 | — |
| 192 | QwQ-32B | Alibaba | 1313 | 1290–1335 | 671 | — |
| 193 | Gemma 3n E4B IT | 1311 | 1290–1333 | 719 | — | |
| 195 | Qwen3-30B-A3B | Alibaba | 1307 | 1286–1328 | 767 | $0.12 / $0.50 |
| 196 | Gemini 2.0 Flash-Lite Preview | 1306 | 1283–1328 | 627 | — | |
| 197 | o3-mini | OpenAI | 1303 | 1274–1333 | 377 | $1.10 / $4.40 |
| 198 | Claude 3.7 Sonnet | Anthropic | 1301 | 1282–1320 | 1K | — |
| 200 | Claude 3.5 Sonnet | Anthropic | 1298 | 1284–1311 | 2K | — |
| 201 | Llama 4 Maverick 17B 128E Instruct | Meta | 1291 | 1272–1310 | 1K | — |
| 202 | Olmo 3 32B Think | Ai2 | 1290 | 1237–1344 | 136 | — |
| 203 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B | NVIDIA | 1290 | 1255–1325 | 360 | — |
| 204 | GPT-4.1 nano | OpenAI | 1288 | 1251–1325 | 222 | $0.10 / $0.40 |
| 205 | Grok 2 | xAI | 1287 | 1271–1303 | 1.6K | — |
| 206 | Gemini 1.5 Pro | 1286 | 1270–1303 | 1.3K | — | |
| 207 | GPT-4o | OpenAI | 1283 | 1269–1296 | 3.6K | $2.50 / $10 |
| 208 | Olmo 3.1 32B Instruct | Ai2 | 1282 | 1244–1319 | 245 | — |
| 210 | Gemma 3 4B IT | 1281 | 1239–1323 | 162 | $0.04 / $0.05 | |
| 212 | o1-mini | OpenAI | 1278 | 1260–1296 | 1.2K | — |
| 213 | Gemini Advanced | 1275 | 1257–1292 | 1.8K | — | |
| 214 | Grok 2 mini | xAI | 1273 | 1256–1290 | 1.3K | — |
| 215 | GPT-4o mini | OpenAI | 1272 | 1257–1287 | 1.6K | $0.15 / $0.60 |
| 216 | Llama 4 Scout 17B 16E Instruct | Meta | 1272 | 1250–1294 | 799 | — |
| 218 | Yi Lightning | 01.AI | 1267 | 1245–1289 | 700 | — |
| 219 | Mistral Small 3.1 24B Instruct | Mistral AI | 1267 | 1245–1288 | 876 | $0.35 / $0.56 |
| 220 | Olmo 3.1 32B Think | Ai2 | 1262 | 1213–1310 | 165 | — |
| 221 | Gemini 1.5 Flash | 1262 | 1240–1283 | 739 | — | |
| 222 | AAthene V2 Chat | — | 1261 | 1238–1283 | 626 | — |
| 223 | GPT-4 Turbo | OpenAI | 1260 | 1245–1274 | 3.4K | $10 / $30 |
| 224 | Claude 3 Opus | Anthropic | 1258 | 1246–1271 | 5.7K | — |
| 225 | DeepSeek-V2.5 | DeepSeek | 1258 | 1213–1304 | 140 | — |
| 227 | gpt-oss-20b | OpenAI | 1255 | 1215–1295 | 217 | $0.018 / $0.09 |
| 228 | Mistral Large 2 | Mistral AI | 1254 | 1236–1272 | 1.2K | — |
| 229 | Qwen-Max | Alibaba | 1254 | 1228–1280 | 438 | — |
| 230 | Llama 3.1 405B Instruct | Meta | 1252 | 1233–1272 | 894 | — |
| 231 | AAthene 70B | — | 1252 | 1228–1276 | 585 | — |
| 232 | Llama 3.3 70B Instruct | Meta | 1251 | 1234–1268 | 1.2K | $0.10 / $0.32 |
| 236 | Magistral Medium | Mistral AI | 1248 | 1215–1280 | 361 | — |
| 238 | Reka Core | Reka | 1243 | 1203–1284 | 183 | — |
| 239 | Amazon Nova Pro 1.0 | Amazon | 1243 | 1220–1267 | 553 | — |
| 240 | Mistral Large | Mistral AI | 1242 | 1219–1265 | 648 | $0.50 / $1.50 |
| 241 | Claude 3.5 Haiku | Anthropic | 1237 | 1222–1252 | 1.7K | — |
| 242 | Qwen2.5-72B-Instruct | Alibaba | 1234 | 1214–1253 | 926 | $0.36 / $0.40 |
| 243 | Qwen2.5-Plus | Alibaba | 1231 | 1195–1267 | 257 | — |
| 244 | Amazon Nova Lite 1.0 | Amazon | 1229 | 1202–1255 | 490 | — |
| 246 | Phi-4 | Microsoft | 1222 | 1197–1248 | 523 | $0.07 / $0.14 |
| 247 | Llama 3.1 70B Instruct | Meta | 1222 | 1205–1239 | 1.4K | $0.40 / $0.40 |
| 248 | Gemma 2 9B IT SimPO | 1219 | 1187–1250 | 318 | — | |
| 250 | Command R+ | Cohere | 1216 | 1183–1249 | 267 | $0.15 / $0.60 |
| 251 | Mistral Small 24B Instruct | Mistral AI | 1211 | 1178–1245 | 301 | $0.05 / $0.08 |
| 252 | Gemma 2 27B IT | 1209 | 1194–1224 | 2K | $0.65 / $0.65 | |
| 253 | Gemini 1.5 Flash-8B | 1206 | 1185–1227 | 798 | — | |
| 254 | Claude 3 Sonnet | Anthropic | 1204 | 1189–1219 | 3.1K | — |
| 255 | Jamba 1.5 Large | AI21 Labs | 1200 | 1163–1237 | 234 | — |
| 256 | Aya Expanse 32B | Cohere | 1199 | 1175–1223 | 609 | — |
| 257 | GPT-4 | OpenAI | 1198 | 1179–1218 | 1.3K | $30 / $60 |
| 259 | Amazon Nova Micro 1.0 | Amazon | 1192 | 1165–1219 | 468 | — |
| 260 | Nemotron-4 340B Instruct | NVIDIA | 1192 | 1169–1215 | 703 | — |
| 261 | Aya Expanse 8B | Cohere | 1188 | 1150–1225 | 240 | — |
| 262 | Gemma 2 9B IT | 1186 | 1170–1202 | 1.6K | — | |
| 263 | GLM-4 | Z.ai | 1184 | 1154–1214 | 371 | — |
| 264 | Reka Flash | Reka | 1178 | 1140–1217 | 207 | — |
| 267 | Claude 3 Haiku | Anthropic | 1174 | 1160–1188 | 3.5K | — |
| 268 | Llama 3 70B Instruct | Meta | 1169 | 1155–1183 | 5K | — |
| 269 | DeepSeek-Coder-V2 | DeepSeek | 1164 | 1138–1191 | 516 | — |
| 270 | Jamba 1.5 Mini | AI21 Labs | 1162 | 1124–1200 | 248 | — |
| 272 | Mistral Medium | Mistral AI | 1155 | 1132–1177 | 852 | — |
| 273 | Reka Flash 21B | Reka | 1153 | 1131–1174 | 798 | — |
| 275 | Qwen2-72B-Instruct | Alibaba | 1151 | 1133–1169 | 1.3K | — |
| 276 | Llama 3.1 8B Instruct | Meta | 1144 | 1127–1162 | 1.3K | $0.05 / $0.08 |
| 277 | Mixtral 8x22B Instruct v0.1 | Mistral AI | 1141 | 1124–1159 | 1.7K | — |
| 279 | Gemini Pro | 1125 | 1095–1154 | 450 | $2 / $10 | |
| 280 | Qwen1.5-110B-Chat | Alibaba | 1123 | 1102–1144 | 928 | — |
| 281 | Gemma 2 2B IT | 1114 | 1095–1133 | 1.2K | — | |
| 282 | Mixtral 8x7B Instruct v0.1 | Mistral AI | 1114 | 1098–1131 | 2K | — |
| 283 | Yi 1.5 34B Chat | 01.AI | 1111 | 1090–1132 | 871 | — |
| 284 | Llama 3 8B Instruct | Meta | 1105 | 1090–1119 | 3.4K | — |
| 285 | Phi-3 Medium 4K Instruct | Microsoft | 1101 | 1079–1122 | 851 | — |
| 286 | GPT-3.5 Turbo | OpenAI | 1091 | 1073–1108 | 1.9K | $1 / $2 |
| 287 | Qwen1.5-72B-Chat | Alibaba | 1084 | 1064–1104 | 1.1K | — |
| 288 | WizardLM 70B | Microsoft | 1083 | 1038–1127 | 193 | — |
| 289 | SStarling LM 7B Beta | — | 1081 | 1050–1112 | 367 | — |
| 290 | Phi-3 Small 8K Instruct | Microsoft | 1080 | 1055–1104 | 620 | — |
| 291 | Snowflake Arctic Instruct | Snowflake | 1074 | 1051–1096 | 947 | — |
| 292 | IInternLM2.5 20B Chat | — | 1063 | 1026–1100 | 265 | — |
| 293 | OOpenChat 3.5 | — | 1060 | 1025–1095 | 268 | — |
| 294 | VVicuna 33B | — | 1059 | 1030–1089 | 428 | — |
| 295 | Qwen1.5-32B-Chat | Alibaba | 1058 | 1036–1081 | 777 | — |
| 296 | DDBRX Instruct Preview | — | 1057 | 1034–1081 | 742 | — |
| 297 | Llama 3.2 3B Instruct | Meta | 1056 | 1016–1097 | 232 | $0.051 / $0.34 |
| 299 | Gemma 1.1 7B IT | 1054 | 1032–1076 | 827 | — | |
| 300 | Phi-3 Mini 4K Instruct | Microsoft | 1044 | 1020–1068 | 699 | — |
| 301 | Qwen1.5-14B-Chat | Alibaba | 1043 | 1017–1069 | 540 | — |
| 302 | Yi 34B Chat | 01.AI | 1042 | 1010–1074 | 381 | — |
| 303 | Llama 2 70B Chat | Meta | 1041 | 1019–1064 | 878 | — |
| 305 | SStarling LM 7B Alpha | — | 1025 | 983–1068 | 199 | — |
| 306 | Llama 3.2 1B Instruct | Meta | 1014 | 974–1053 | 247 | $0.027 / $0.20 |
| 307 | Llama 2 13B Chat | Meta | 1009 | 979–1039 | 454 | — |
| 308 | Phi-3 Mini 128K Instruct | Microsoft | 1006 | 981–1031 | 727 | — |
| 309 | VVicuna 13B | — | 992 | 956–1029 | 283 | — |
| 310 | ZZephyr 7B Beta | — | 989 | 941–1037 | 152 | — |
| 311 | Mistral 7B Instruct v0.2 | Mistral AI | 987 | 960–1015 | 564 | — |
| 312 | Llama 2 7B Chat | Meta | 978 | 943–1012 | 327 | — |
| 313 | Gemma 1.1 2B IT | 944 | 909–979 | 365 | — | |
| 314 | Mistral 7B Instruct | Mistral AI | 931 | 886–977 | 174 | — |
| 315 | Qwen1.5-4B-Chat | Alibaba | 902 | 862–942 | 211 | — |
LMArena ranks overlap where confidence intervals do, so several models can share a rank. Where a model is rated at several effort levels, its best is shown.
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview











