LMArena Long queries leaderboard
LMArena’s text votes on long prompts. Gemini 4 Argon leads with a rating of 1538.
- Models
- 330
- Leader
- Gemini 4 Argon
- 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 | Gemini 4 Argon | 1538 | 1528–1548 | 4.3K | $2 / $10 | |
| 2 | Claude Opus 5.5 | Anthropic | 1533 | 1523–1543 | 4.4K | $4 / $20 |
| 3 | Claude Fable 5.1 | Anthropic | 1524 | 1516–1532 | 6.8K | $10 / $50 |
| 4 | Claude Opus 5 | Anthropic | 1517 | 1511–1524 | 16.2K | $5 / $25 |
| 5 | Claude Opus 4.6 | Anthropic | 1517 | 1513–1522 | 35.4K | $5 / $25 |
| 8 | Claude Fable 5 | Anthropic | 1510 | 1505–1516 | 20.5K | $10 / $50 |
| 9 | Gemini 3.8 Flash | 1507 | 1501–1513 | 20.2K | $0.82 / $4.13 | |
| 10 | Claude Opus 4.7 | Anthropic | 1505 | 1500–1510 | 30.1K | $5 / $25 |
| 11 | MiMo-V2.6-Pro | Xiaomi | 1501 | 1486–1515 | 1.7K | $0.43 / $0.87 |
| 13 | Claude Sonnet 5.5 | Anthropic | 1495 | 1484–1505 | 3.8K | $2 / $10 |
| 14 | Gemini 3.7 Flash | 1494 | 1488–1501 | 14.1K | $0.75 / $3.75 | |
| 15 | Kimi K3 | Moonshot AI | 1493 | 1487–1499 | 15.3K | $0.24 / $11 |
| 16 | Muse Wonder | Meta | 1492 | 1480–1504 | 2.6K | $4 / $20 |
| 17 | Muse Spark 1.3 | Meta | 1489 | 1482–1496 | 9.2K | $1.25 / $4.25 |
| 18 | Qwen3.8-Max | Alibaba | 1489 | 1483–1495 | 13.5K | $2 / $6 |
| 19 | GPT-5.5 | OpenAI | 1484 | 1479–1489 | 32K | $5 / $30 |
| 20 | Claude Opus 4.8 | Anthropic | 1484 | 1478–1489 | 30.2K | $5 / $25 |
| 21 | GLM-5.3 | Z.ai | 1483 | 1476–1490 | 11.4K | $0.079 / $1.40 |
| 23 | Gemini 3.5 Flash | 1482 | 1477–1488 | 22.8K | $1.50 / $9 | |
| 24 | Gemini 3.1 Pro Preview | 1482 | 1478–1487 | 57.8K | $2 / $12 | |
| 25 | GLM-5.3-Flash | Z.ai | 1482 | 1476–1488 | 16.9K | $0.15 / $0.50 |
| 26 | Qwen3.7-Max-Preview | Alibaba | 1482 | 1467–1497 | 1.7K | $1.48 / $4.42 |
| 27 | MiMo-V2.5-Pro | Xiaomi | 1481 | 1476–1486 | 34.5K | $0.30 / $0.61 |
| 28 | GPT-5.6 Sol | OpenAI | 1481 | 1475–1487 | 19.7K | $4 / $20 |
| 30 | GLM-5.2 | Z.ai | 1480 | 1474–1485 | 23.8K | $0.034 / $7 |
| 31 | Claude Opus 4.5 | Anthropic | 1479 | 1474–1484 | 24.2K | $5 / $25 |
| 32 | Claude Sonnet 4.6 | Anthropic | 1479 | 1474–1484 | 31.1K | $3 / $15 |
| 35 | Qwen3.5-Max-Preview | Alibaba | 1477 | 1469–1484 | 9K | — |
| 36 | Claude Sonnet 4.5 | Anthropic | 1475 | 1471–1480 | 26.5K | $3 / $15 |
| 38 | Gemini 3.6 Flash | 1475 | 1469–1481 | 17.1K | $0.75 / $3.75 | |
| 39 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 1474 | 1465–1482 | 6K | $0.15 / $0.60 |
| 40 | GPT-5.4 | OpenAI | 1474 | 1468–1479 | 28.4K | $2.50 / $15 |
| 41 | Muse Spark 1.2 | Meta | 1473 | 1463–1482 | 4.6K | $1.25 / $4.25 |
| 42 | Gemini 3 Pro | 1471 | 1465–1478 | 11.2K | — | |
| 43 | Kimi K2.6 | Moonshot AI | 1468 | 1462–1474 | 17K | $0.65 / $3.41 |
| 44 | GLM-5.1 | Z.ai | 1467 | 1462–1472 | 29.4K | $1.40 / $4.40 |
| 46 | Claude Sonnet 5 | Anthropic | 1462 | 1457–1468 | 23.9K | $2 / $10 |
| 47 | Grok 4.5 | xAI | 1462 | 1456–1468 | 19.3K | $2 / $6 |
| 48 | GPT-6 Astra | OpenAI | 1462 | 1454–1471 | 5.9K | $10 / $50 |
| 49 | ERNIE 5.1 | Baidu | 1462 | 1456–1468 | 16.7K | — |
| 50 | Muse Spark 1.1 | Meta | 1461 | 1456–1467 | 21.2K | $1.25 / $4.25 |
| 51 | GPT-6.1 Sol | OpenAI | 1461 | 1450–1472 | 3.4K | $2 / $10 |
| 52 | MiMo-V2.6-Flash | Xiaomi | 1459 | 1450–1468 | 5.6K | $0.14 / $0.28 |
| 53 | Qwen3.6-Max-Preview | Alibaba | 1458 | 1445–1471 | 2.3K | — |
| 54 | DeepSeek-V4-Pro | DeepSeek | 1458 | 1452–1463 | 25.9K | $0.66 / $1.98 |
| 56 | Grok 4.6 | xAI | 1457 | 1451–1463 | 14.8K | $2 / $6 |
| 57 | MiMo-V2-Pro | Xiaomi | 1455 | 1449–1462 | 10K | — |
| 58 | Claude Opus 4.1 | Anthropic | 1455 | 1449–1461 | 11.5K | $15 / $75 |
| 59 | Qwen3.7-Plus | Alibaba | 1454 | 1449–1460 | 19.5K | $0.32 / $1.28 |
| 60 | GPT-5.6 Terra | OpenAI | 1453 | 1448–1459 | 21.5K | $2 / $12 |
| 61 | Gemini 3 Flash | 1452 | 1445–1459 | 8.5K | $0.50 / $3 | |
| 62 | Muse Spark | Meta | 1451 | 1442–1459 | 5.6K | — |
| 63 | Step 5 Preview | StepFun | 1450 | 1441–1460 | 4.1K | $1 / $2.70 |
| 64 | Gemini 2.5 Pro | 1449 | 1445–1453 | 34K | $1.25 / $10 | |
| 65 | Qwen3.8-27B | Alibaba | 1449 | 1442–1456 | 11.6K | $0.20 / $2.50 |
| 66 | GPT-5.1 | OpenAI | 1448 | 1441–1454 | 10.9K | $1.25 / $10 |
| 67 | Gemma 4 31B | 1446 | 1433–1460 | 1.8K | $0.20 / $0.40 | |
| 69 | GLM-5 | Z.ai | 1446 | 1439–1452 | 11.1K | $1 / $3.20 |
| 70 | MiMo-V2.5 | Xiaomi | 1445 | 1439–1451 | 21.3K | $0.12 / $0.24 |
| 71 | MiniMax-M3 | MiniMax | 1445 | 1440–1450 | 30.2K | $0.30 / $1.20 |
| 72 | Kimi K2.5 | Moonshot AI | 1444 | 1440–1449 | 29.8K | $0.50 / $2.50 |
| 74 | Hy3 | Tencent | 1442 | 1434–1451 | 6K | $0.083 / $0.33 |
| 75 | amazon-nova-experimental-chat | Amazon | 1442 | 1424–1460 | 1K | — |
| 76 | Qwen3.5-397B-A17B | Alibaba | 1441 | 1437–1446 | 42.4K | $0.50 / $3.60 |
| 77 | MiMo-V2-Omni | Xiaomi | 1441 | 1434–1449 | 9.2K | — |
| 78 | Qwen3.6-Plus | Alibaba | 1439 | 1434–1445 | 21.2K | $0.33 / $1.95 |
| 79 | Grok 3 Preview | xAI | 1439 | 1430–1448 | 4.9K | — |
| 80 | GLM-5V-Turbo | Z.ai | 1439 | 1430–1448 | 4.9K | $1.20 / $4 |
| 81 | Qwen3-Max-Preview | Alibaba | 1438 | 1430–1446 | 6.2K | — |
| 82 | NVIDIA-Nemotron-3-Ultra-550B-A55B | NVIDIA | 1437 | 1428–1446 | 5.3K | — |
| 83 | Grok 4.20 Beta | xAI | 1437 | 1431–1442 | 29.1K | — |
| 84 | GPT-5.6 Luna | OpenAI | 1436 | 1431–1442 | 19.5K | $0.20 / $1.20 |
| 86 | IInkling | Thinky | 1435 | 1430–1441 | 20.4K | $1 / $4.05 |
| 87 | Gemini 3.5 Flash-Lite | 1435 | 1429–1441 | 17.1K | $0.30 / $2.50 | |
| 88 | DeepSeek-V4-Flash | DeepSeek | 1434 | 1429–1440 | 23.4K | $0.042 / $0.18 |
| 89 | GLM-4.7 | Z.ai | 1432 | 1422–1442 | 3.3K | $0.54 / $1.98 |
| 90 | Grok 4.20 Multi-Agent Beta | xAI | 1431 | 1426–1436 | 28K | — |
| 92 | BBeam 1.0 501B A23B | Reflection AI | 1429 | 1415–1444 | 1.9K | $0.25 / $1 |
| 94 | Mistral Large 4 | Mistral AI | 1429 | 1419–1438 | 4.4K | $1.36 / $4.18 |
| 95 | DeepSeek-V3.2-Exp | DeepSeek | 1428 | 1422–1434 | 13.7K | $0.28 / $0.42 |
| 96 | Dola Seed 2.0 Pro | ByteDance | 1428 | 1423–1432 | 32.7K | — |
| 97 | GPT-5.2 Chat | OpenAI | 1428 | 1422–1434 | 14K | $1.75 / $14 |
| 98 | Gemma 4 26B A4B | 1427 | 1413–1441 | 1.7K | $0.068 / $0.23 | |
| 99 | Claude Haiku 4.5 | Anthropic | 1427 | 1423–1431 | 57.9K | $1 / $5 |
| 100 | Grok 4.20 Beta 1 | xAI | 1427 | 1420–1433 | 10.5K | — |
| 101 | Qwen3-235B-A22B-Instruct | Alibaba | 1426 | 1422–1430 | 27.1K | $0.09 / $0.55 |
| 103 | LongCat-Flash-Chat Exp | Meituan | 1425 | 1419–1432 | 11.5K | — |
| 105 | DeepSeek-V3.1-Terminus | DeepSeek | 1423 | 1401–1445 | 676 | $0.27 / $1 |
| 106 | GLM-4.6 | Z.ai | 1422 | 1416–1429 | 9.1K | $0.55 / $2.20 |
| 107 | GPT-5.5 Instant | OpenAI | 1422 | 1415–1429 | 12.6K | — |
| 108 | Claude Opus 4 | Anthropic | 1422 | 1414–1430 | 7K | — |
| 109 | ERNIE 5.0 | Baidu | 1422 | 1416–1428 | 11.9K | — |
| 110 | DeepSeek-V3.1 | DeepSeek | 1422 | 1410–1434 | 2.4K | $0.25 / $0.95 |
| 111 | Qwen3-VL-235B-A22B-Instruct | Alibaba | 1420 | 1407–1433 | 2.2K | $0.21 / $1.90 |
| 112 | Gemini 2.5 Flash | 1419 | 1415–1423 | 33.3K | $0.30 / $2.50 | |
| 113 | MiniMax-M2.7 | MiniMax | 1419 | 1414–1423 | 37.3K | $0.30 / $1.20 |
| 115 | Grok 4.1 | xAI | 1416 | 1411–1421 | 21.2K | — |
| 116 | Grok 4.7 | xAI | 1416 | 1407–1424 | 6.1K | $2 / $6 |
| 117 | GPT-6 Sol | OpenAI | 1416 | 1407–1424 | 6.2K | $2 / $10 |
| 118 | MiniMax-M2.1 Preview | MiniMax | 1416 | 1407–1424 | 4.5K | $0.30 / $1.20 |
| 119 | Mistral Medium 3.5 | Mistral AI | 1415 | 1406–1424 | 5.1K | $1.50 / $7.50 |
| 120 | Kimi K2 Thinking Turbo | Moonshot AI | 1415 | 1410–1420 | 19.9K | — |
| 121 | Mistral Large 3 | Mistral AI | 1415 | 1410–1419 | 33.2K | $0.50 / $1.50 |
| 122 | Grok 4 Fast | xAI | 1414 | 1398–1430 | 1.4K | — |
| 123 | Qwen3.5-27B | Alibaba | 1413 | 1407–1420 | 11K | $0.27 / $2.16 |
| 124 | GPT-5.2 | OpenAI | 1413 | 1408–1417 | 34.1K | $1.75 / $14 |
| 125 | GLM-4.5 | Z.ai | 1413 | 1404–1421 | 5.1K | $0.60 / $2.20 |
| 126 | ChatGPT-4o Latest | OpenAI | 1412 | 1407–1417 | 17.8K | — |
| 129 | Qwen3.5-122B-A10B | Alibaba | 1411 | 1404–1417 | 11.7K | $0.40 / $3.20 |
| 132 | MiMo-V2-Flash | Xiaomi | 1409 | 1404–1415 | 16.5K | — |
| 134 | Grok 4 | xAI | 1408 | 1402–1415 | 8.9K | — |
| 135 | GPT-5.4 mini | OpenAI | 1407 | 1402–1413 | 27.8K | $0.75 / $4.50 |
| 136 | GPT-6 Luna | OpenAI | 1407 | 1402–1413 | 31.1K | $0.10 / $0.50 |
| 139 | Mistral Medium 3.1 | Mistral AI | 1406 | 1402–1410 | 27.8K | $0.40 / $2 |
| 140 | GPT-4.5 Preview | OpenAI | 1406 | 1392–1419 | 1.8K | — |
| 142 | Hunyuan Vision 1.5 Thinking | Tencent | 1405 | 1381–1430 | 510 | — |
| 143 | Qwen3-Next-80B-A3B-Instruct | Alibaba | 1402 | 1394–1411 | 5.4K | $0.09 / $1.10 |
| 144 | IInkling-Small | Thinky | 1402 | 1396–1408 | 16.6K | $0.45 / $1.20 |
| 146 | Step-3.5-Flash | StepFun | 1402 | 1397–1407 | 22.8K | $0.10 / $0.30 |
| 150 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | NVIDIA | 1399 | 1385–1414 | 1.8K | — |
| 151 | Qwen3-235B-A22B-Thinking | Alibaba | 1399 | 1385–1413 | 1.6K | $0.45 / $3.50 |
| 152 | Claude Haiku 5.5 | Anthropic | 1399 | 1387–1411 | 2.7K | $0.10 / $0.50 |
| 153 | GPT-5 Chat | OpenAI | 1399 | 1391–1406 | 6.8K | — |
| 154 | Claude Sonnet 4 | Anthropic | 1397 | 1390–1405 | 6.7K | — |
| 156 | GPT-5.3 Chat | OpenAI | 1395 | 1389–1401 | 13.4K | — |
| 158 | Gemini 3.1 Flash-Lite Preview | 1394 | 1389–1400 | 27.2K | $0.25 / $1.50 | |
| 160 | Grok 4.3 | xAI | 1393 | 1388–1398 | 33.2K | $1.25 / $2.50 |
| 161 | Qwen3.5-Flash | Alibaba | 1392 | 1387–1397 | 25.7K | $0.065 / $0.26 |
| 163 | Qwen3-VL-235B-A22B-Thinking | Alibaba | 1391 | 1377–1405 | 1.8K | — |
| 164 | DeepSeek-R1 | DeepSeek | 1391 | 1380–1402 | 3.1K | $0.50 / $2.15 |
| 165 | Grok 4.1 Fast | xAI | 1390 | 1385–1395 | 18.6K | — |
| 167 | Qwen3.5-35B-A3B | Alibaba | 1389 | 1383–1396 | 11.9K | $0.14 / $1 |
| 168 | Qwen3-235B-A22B | Alibaba | 1389 | 1381–1396 | 7.2K | $0.09 / $0.55 |
| 169 | GPT-5 | OpenAI | 1387 | 1380–1395 | 7K | $1.25 / $10 |
| 170 | Hunyuan T1 | Tencent | 1385 | 1366–1404 | 897 | — |
| 171 | GPT-4.1 | OpenAI | 1385 | 1378–1391 | 10K | $2 / $8 |
| 172 | Muse Glimmer | Meta | 1382 | 1367–1396 | 1.8K | — |
| 173 | Solar Pro 4 | Upstage | 1382 | 1375–1388 | 11.2K | $0.15 / $0.60 |
| 175 | Qwen3-30B-A3B-Instruct | Alibaba | 1378 | 1370–1387 | 4.9K | $0.09 / $0.30 |
| 176 | Qwen3-Coder-480B-A35B-Instruct | Alibaba | 1378 | 1369–1387 | 4.9K | — |
| 177 | o1 | OpenAI | 1378 | 1368–1387 | 3.6K | $15 / $60 |
| 178 | Gemini 2.5 Flash-Lite Preview | 1373 | 1365–1381 | 6.4K | $0.10 / $0.40 | |
| 180 | Claude 3.7 Sonnet | Anthropic | 1373 | 1365–1381 | 6.1K | — |
| 181 | Grok 3 Mini | xAI | 1372 | 1361–1382 | 3.2K | — |
| 182 | o3 | OpenAI | 1372 | 1366–1378 | 11.5K | $2 / $8 |
| 184 | GLM-4.5-Air | Z.ai | 1366 | 1359–1373 | 6.8K | $0.13 / $0.85 |
| 185 | Hunyuan TurboS | Tencent | 1366 | 1351–1381 | 1.5K | — |
| 186 | MiniMax-M2.5 | MiniMax | 1366 | 1360–1372 | 16.3K | $0.30 / $1.20 |
| 187 | GPT-5.4 nano | OpenAI | 1366 | 1360–1371 | 27.7K | $0.20 / $1.25 |
| 188 | NVIDIA-Nemotron-3-Super-120B-A12B | NVIDIA | 1362 | 1350–1374 | 2.3K | — |
| 189 | Mistral Medium 3 | Mistral AI | 1360 | 1352–1368 | 5.9K | $0.40 / $2 |
| 190 | Granite 4.2 30B | IBM | 1358 | 1342–1375 | 1.4K | — |
| 191 | Qwen2.5-Max | Alibaba | 1358 | 1349–1366 | 4.5K | — |
| 192 | GLM-4.6V | Z.ai | 1357 | 1335–1379 | 703 | $0.30 / $0.90 |
| 193 | Grok 3 Mini Beta | xAI | 1357 | 1348–1366 | 4K | — |
| 194 | GPT-5 mini | OpenAI | 1355 | 1347–1363 | 5.9K | $0.25 / $2 |
| 197 | Trinity Large Preview | Arcee | 1354 | 1348–1361 | 11.6K | — |
| 198 | Kimi K2 Preview | Moonshot AI | 1353 | 1342–1365 | 2.6K | $0.60 / $2.50 |
| 199 | Qwen3-Next-80B-A3B-Thinking | Alibaba | 1353 | 1342–1364 | 2.9K | $0.15 / $1.20 |
| 200 | DeepSeek-V3 | DeepSeek | 1352 | 1345–1359 | 8.5K | $0.29 / $1.14 |
| 202 | Step-1o Turbo | StepFun | 1348 | 1332–1365 | 1.3K | — |
| 203 | GLM-4.7-Flash | Z.ai | 1345 | 1334–1355 | 3.4K | $0.06 / $0.40 |
| 204 | Gemini 2.0 Flash | 1344 | 1337–1352 | 6.5K | — | |
| 205 | GPT-4.1 mini | OpenAI | 1344 | 1336–1351 | 7.1K | $0.40 / $1.60 |
| 208 | o3-mini | OpenAI | 1343 | 1331–1355 | 2.2K | $1.10 / $4.40 |
| 209 | Hunyuan Large | Tencent | 1341 | 1313–1369 | 371 | — |
| 210 | Amazon Nova 2 Lite | Amazon | 1336 | 1325–1346 | 3.1K | — |
| 211 | Command A | Cohere | 1334 | 1328–1340 | 10.7K | $0.30 / $1.50 |
| 212 | Gemma 3 27B IT | 1333 | 1326–1340 | 6.7K | $0.08 / $0.35 | |
| 214 | MiniMax-M2 | MiniMax | 1331 | 1317–1346 | 1.7K | $0.26 / $1.02 |
| 215 | IINTELLECT-3 | — | 1331 | 1315–1347 | 1.4K | — |
| 216 | Mercury 2 | Inception | 1330 | 1311–1349 | 918 | $0.25 / $0.75 |
| 218 | Qwen3-32B | Alibaba | 1327 | 1303–1351 | 504 | $0.08 / $0.28 |
| 219 | MiniMax-M1 | MiniMax | 1326 | 1319–1334 | 7K | $0.55 / $2.20 |
| 220 | Mistral Small 3.2 | Mistral AI | 1326 | 1316–1336 | 3.4K | — |
| 222 | Step-3 | StepFun | 1325 | 1309–1342 | 1.3K | — |
| 223 | LLing-flash-2.0 | Ant Group | 1324 | 1308–1340 | 1.3K | — |
| 224 | Qwen-Plus | Alibaba | 1324 | 1303–1345 | 690 | $0.26 / $0.78 |
| 225 | Granite 4.2 8B | IBM | 1324 | 1307–1341 | 1.4K | $0.06 / $0.25 |
| 226 | RRing-flash-2.0 | Ant Group | 1321 | 1305–1337 | 1.4K | — |
| 227 | Gemini 2.0 Flash-Lite Preview | 1320 | 1310–1331 | 2.9K | — | |
| 228 | o1-mini | OpenAI | 1320 | 1313–1328 | 7.9K | — |
| 230 | gpt-oss-120b | OpenAI | 1319 | 1311–1327 | 6.6K | $0.15 / $0.60 |
| 231 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B | NVIDIA | 1318 | 1311–1326 | 9.8K | — |
| 232 | Trinity Large Thinking | Arcee | 1318 | 1311–1325 | 13.1K | $0.25 / $0.80 |
| 233 | Gemma 3 12B IT | 1317 | 1289–1345 | 371 | $0.05 / $0.15 | |
| 234 | GLM-4-Plus | Z.ai | 1316 | 1295–1336 | 765 | — |
| 235 | Llama 3.3 Nemotron Super 49B v1.5 | NVIDIA | 1315 | 1293–1336 | 653 | — |
| 236 | o4-mini | OpenAI | 1315 | 1308–1321 | 8.6K | $1.10 / $4.40 |
| 237 | Olmo 3.1 32B Instruct | Ai2 | 1313 | 1302–1324 | 3K | — |
| 238 | GPT-5 nano | OpenAI | 1312 | 1298–1327 | 1.6K | $0.05 / $0.40 |
| 239 | Qwen3-30B-A3B | Alibaba | 1312 | 1303–1320 | 4.5K | $0.12 / $0.50 |
| 240 | Claude 3.5 Sonnet | Anthropic | 1311 | 1305–1317 | 13.8K | — |
| 241 | Hunyuan Turbo | Tencent | 1309 | 1280–1338 | 313 | — |
| 242 | QwQ-32B | Alibaba | 1308 | 1299–1317 | 4.1K | — |
| 243 | Gemini 1.5 Pro | 1308 | 1300–1315 | 8.4K | — | |
| 244 | Step-2 16K Exp | StepFun | 1306 | 1285–1327 | 693 | — |
| 245 | GLM-4.5V | Z.ai | 1305 | 1287–1322 | 1.1K | $0.60 / $1.80 |
| 246 | Hunyuan Standard | Tencent | 1301 | 1274–1327 | 432 | — |
| 247 | DeepSeek-V2.5 | DeepSeek | 1300 | 1283–1318 | 1K | — |
| 248 | NVIDIA-Nemotron-3-Nano-30B-A3B | NVIDIA | 1300 | 1291–1310 | 4.1K | — |
| 249 | Llama 3.3 Nemotron Super 49B v1 | NVIDIA | 1299 | 1269–1329 | 317 | — |
| 250 | Llama 3.1 Nemotron Ultra 253B v1 | NVIDIA | 1299 | 1269–1328 | 321 | — |
| 251 | Mistral Small 3.1 24B Instruct | Mistral AI | 1298 | 1291–1306 | 6.3K | $0.35 / $0.56 |
| 252 | Yi Lightning | 01.AI | 1297 | 1286–1307 | 3.6K | — |
| 253 | Olmo 3 32B Think | Ai2 | 1295 | 1279–1312 | 1.4K | — |
| 254 | Magistral Medium | Mistral AI | 1294 | 1282–1307 | 2.4K | — |
| 255 | Granite 4.2 3B | IBM | 1292 | 1274–1310 | 1.4K | — |
| 256 | Qwen2.5-Plus | Alibaba | 1292 | 1277–1306 | 1.6K | — |
| 258 | AAthene V2 Chat | — | 1289 | 1280–1299 | 3.7K | — |
| 259 | GPT-4o mini | OpenAI | 1289 | 1282–1296 | 9K | $0.15 / $0.60 |
| 260 | GPT-4o | OpenAI | 1288 | 1281–1295 | 14.9K | $2.50 / $10 |
| 261 | Qwen-Max | Alibaba | 1288 | 1276–1300 | 2.4K | — |
| 263 | Gemini 1.5 Flash | 1284 | 1275–1292 | 5.5K | — | |
| 265 | GPT-4.1 nano | OpenAI | 1282 | 1263–1302 | 730 | $0.10 / $0.40 |
| 266 | Qwen2.5-72B-Instruct | Alibaba | 1281 | 1273–1289 | 6K | $0.36 / $0.40 |
| 267 | Llama 4 Maverick 17B 128E Instruct | Meta | 1279 | 1272–1287 | 7.1K | — |
| 268 | Hunyuan Large Vision | Tencent | 1279 | 1260–1299 | 875 | — |
| 269 | Grok 2 | xAI | 1276 | 1269–1283 | 8.9K | — |
| 270 | Gemma 3n E4B IT | 1276 | 1265–1287 | 2.9K | — | |
| 271 | Granite 4.1 8B | IBM | 1275 | 1258–1291 | 1.6K | — |
| 273 | Gemma 3 4B IT | 1273 | 1246–1300 | 444 | $0.04 / $0.05 | |
| 275 | Olmo 3.1 32B Think | Ai2 | 1271 | 1258–1284 | 2K | — |
| 276 | Grok 2 mini | xAI | 1266 | 1258–1274 | 7K | — |
| 277 | Llama 3.1 405B Instruct | Meta | 1265 | 1257–1273 | 5.5K | — |
| 278 | Llama 4 Scout 17B 16E Instruct | Meta | 1265 | 1257–1273 | 5.8K | — |
| 279 | Mercury | Inception | 1264 | 1239–1290 | 521 | — |
| 280 | Mistral Large | Mistral AI | 1261 | 1252–1271 | 3.6K | $0.50 / $1.50 |
| 281 | Claude 3.5 Haiku | Anthropic | 1260 | 1254–1266 | 11K | — |
| 283 | Claude 3 Opus | Anthropic | 1259 | 1252–1265 | 23.4K | — |
| 284 | Mistral Large 2 | Mistral AI | 1257 | 1249–1266 | 5.9K | — |
| 285 | Llama 3.3 70B Instruct | Meta | 1255 | 1249–1262 | 8.3K | $0.10 / $0.32 |
| 286 | Amazon Nova Pro 1.0 | Amazon | 1255 | 1245–1264 | 3.4K | — |
| 287 | GPT-4 Turbo | OpenAI | 1254 | 1246–1261 | 11.6K | $10 / $30 |
| 288 | Gemini Advanced | 1253 | 1243–1264 | 5.5K | — | |
| 290 | Qwen2.5-Coder-32B-Instruct | Alibaba | 1250 | 1232–1269 | 804 | $0.66 / $1 |
| 291 | gpt-oss-20b | OpenAI | 1250 | 1237–1264 | 2.1K | $0.018 / $0.09 |
| 292 | Mistral Small 24B Instruct | Mistral AI | 1246 | 1232–1259 | 1.8K | $0.05 / $0.08 |
| 294 | Granite-4.0-H-Small | IBM | 1242 | 1225–1259 | 1.3K | — |
| 295 | Llama 3.1 70B Instruct | Meta | 1241 | 1233–1248 | 7.6K | $0.40 / $0.40 |
| 296 | Llama 3.1 Nemotron 70B Instruct | NVIDIA | 1238 | 1221–1256 | 1K | — |
| 298 | Amazon Nova Lite 1.0 | Amazon | 1233 | 1223–1244 | 2.8K | — |
| 299 | AAthene 70B | — | 1232 | 1220–1244 | 2.1K | — |
| 300 | Gemma 2 27B IT | 1230 | 1223–1237 | 9.9K | $0.65 / $0.65 | |
| 301 | Command R+ | Cohere | 1230 | 1215–1245 | 1.4K | $0.15 / $0.60 |
| 302 | Aya Expanse 32B | Cohere | 1227 | 1218–1237 | 4.2K | — |
| 303 | Gemma 2 9B IT SimPO | 1226 | 1207–1245 | 841 | — | |
| 304 | Nemotron-4 340B Instruct | NVIDIA | 1224 | 1211–1238 | 2.1K | — |
| 305 | Hunyuan Standard 256K | Tencent | 1224 | 1198–1250 | 414 | — |
| 306 | Llama 3.1 Tulu 3 70B | Ai2 | 1224 | 1199–1249 | 463 | — |
| 307 | Reka Core | Reka | 1220 | 1202–1238 | 951 | — |
| 308 | DeepSeek-Coder-V2 | DeepSeek | 1219 | 1205–1233 | 1.8K | — |
| 309 | Gemini 1.5 Flash-8B | 1218 | 1210–1227 | 5.6K | — | |
| 310 | Phi-4 | Microsoft | 1217 | 1206–1228 | 2.9K | $0.07 / $0.14 |
| 311 | Ministral 8B | Mistral AI | 1212 | 1192–1232 | 720 | $0.15 / $0.15 |
| 312 | Claude 3 Sonnet | Anthropic | 1211 | 1202–1219 | 11.9K | — |
| 313 | GLM-4 | Z.ai | 1206 | 1190–1223 | 1.2K | — |
| 314 | Jamba 1.5 Large | AI21 Labs | 1206 | 1189–1223 | 1K | — |
| 315 | Amazon Nova Micro 1.0 | Amazon | 1205 | 1194–1217 | 2.6K | — |
| 316 | Llama 3.1 Nemotron 51B Instruct | NVIDIA | 1205 | 1182–1228 | 587 | — |
| 319 | Gemma 2 9B IT | 1196 | 1189–1204 | 6.9K | — | |
| 320 | OLMo 2 32B Instruct | Ai2 | 1194 | 1160–1228 | 261 | — |
| 321 | Qwen2-72B-Instruct | Alibaba | 1192 | 1182–1202 | 4.6K | — |
| 322 | Reka Flash | Reka | 1191 | 1174–1209 | 992 | — |
| 323 | Aya Expanse 8B | Cohere | 1191 | 1176–1206 | 1.5K | — |
| 324 | Claude 3 Haiku | Anthropic | 1190 | 1182–1198 | 14K | — |
| 325 | GPT-4 | OpenAI | 1190 | 1178–1201 | 4.3K | $30 / $60 |
| 327 | Llama 3.1 8B Instruct | Meta | 1181 | 1173–1189 | 6.7K | $0.05 / $0.08 |
| 328 | Llama 3.1 Tulu 3 8B | Ai2 | 1180 | 1155–1206 | 454 | — |
| 329 | Llama 3 70B Instruct | Meta | 1174 | 1166–1181 | 17.5K | — |
| 332 | Granite 3.1 8B Instruct | IBM | 1162 | 1135–1188 | 461 | — |
| 334 | Qwen1.5-110B-Chat | Alibaba | 1157 | 1145–1169 | 3.3K | — |
| 335 | Qwen1.5-72B-Chat | Alibaba | 1157 | 1145–1168 | 3.5K | — |
| 336 | Jamba 1.5 Mini | AI21 Labs | 1156 | 1139–1174 | 1K | — |
| 337 | Granite 3.1 2B Instruct | IBM | 1155 | 1129–1181 | 489 | — |
| 338 | Mistral Medium | Mistral AI | 1153 | 1140–1166 | 2.7K | — |
| 339 | IInternLM2.5 20B Chat | — | 1149 | 1133–1165 | 1.3K | — |
| 340 | Qwen1.5-32B-Chat | Alibaba | 1146 | 1133–1158 | 2.6K | — |
| 341 | Mixtral 8x22B Instruct v0.1 | Mistral AI | 1143 | 1134–1153 | 5.9K | — |
| 342 | Yi 1.5 34B Chat | 01.AI | 1143 | 1130–1157 | 2.1K | — |
| 343 | Reka Flash 21B | Reka | 1141 | 1128–1153 | 2.7K | — |
| 345 | Gemini Pro | 1131 | 1114–1149 | 1.4K | $2 / $10 | |
| 346 | Gemma 2 2B IT | 1130 | 1121–1138 | 5.9K | — | |
| 347 | Llama 3 8B Instruct | Meta | 1127 | 1119–1136 | 11.2K | — |
| 348 | Granite 3.0 8B Instruct | IBM | 1122 | 1098–1145 | 603 | — |
| 349 | GPT-3.5 Turbo | OpenAI | 1121 | 1111–1130 | 6.7K | $1 / $2 |
| 350 | Phi-3 Medium 4K Instruct | Microsoft | 1120 | 1107–1133 | 2.2K | — |
| 351 | Qwen1.5-14B-Chat | Alibaba | 1113 | 1098–1127 | 2.1K | — |
| 352 | DDBRX Instruct Preview | — | 1111 | 1099–1124 | 3.5K | — |
| 353 | TTulu 2 DPO 70B | — | 1106 | 1073–1138 | 280 | — |
| 354 | ZZephyr ORPO 141B A35B v0.1 | — | 1105 | 1077–1132 | 448 | — |
| 355 | SStarling LM 7B Beta | — | 1104 | 1089–1119 | 1.7K | — |
| 356 | Mixtral 8x7B Instruct v0.1 | Mistral AI | 1103 | 1093–1112 | 6.6K | — |
| 357 | Llama 3.2 3B Instruct | Meta | 1100 | 1082–1118 | 1K | $0.051 / $0.34 |
| 358 | WizardLM 70B | Microsoft | 1097 | 1066–1128 | 355 | — |
| 359 | Yi 34B Chat | 01.AI | 1093 | 1076–1111 | 1.1K | — |
| 360 | OOpenChat 3.5 | — | 1093 | 1065–1121 | 414 | — |
| 361 | DeepSeek LLM 67B Chat | DeepSeek | 1092 | 1056–1128 | 243 | — |
| 362 | Qwen1.5-7B-Chat | Alibaba | 1090 | 1060–1120 | 372 | — |
| 363 | Phi-3 Small 8K Instruct | Microsoft | 1087 | 1074–1101 | 2.2K | — |
| 365 | SStarling LM 7B Alpha | — | 1081 | 1058–1103 | 666 | — |
| 366 | Granite 3.0 2B Instruct | IBM | 1070 | 1046–1094 | 647 | — |
| 368 | Llama 2 13B Chat | Meta | 1064 | 1047–1081 | 1.2K | — |
| 369 | Llama 2 70B Chat | Meta | 1062 | 1049–1074 | 2.8K | — |
| 370 | Mistral 7B Instruct v0.2 | Mistral AI | 1060 | 1045–1075 | 1.6K | — |
| 371 | SSmolLM2 1.7B Instruct | — | 1056 | 1024–1088 | 328 | — |
| 372 | Gemma 1.1 7B IT | 1055 | 1043–1068 | 2.6K | — | |
| 373 | OpenHermes 2.5 Mistral 7B | Mistral AI | 1054 | 1021–1087 | 270 | — |
| 374 | WizardLM 13B | Microsoft | 1053 | 1014–1093 | 203 | — |
| 375 | Llama 3.2 1B Instruct | Meta | 1050 | 1031–1068 | 1.1K | $0.027 / $0.20 |
| 376 | VVicuna 13B | — | 1047 | 1026–1068 | 756 | — |
| 377 | Nous Hermes 2 Mixtral 8x7B DPO | Nous Research | 1045 | 1011–1080 | 230 | — |
| 378 | Phi-3 Mini 4K Instruct | Microsoft | 1044 | 1029–1059 | 1.7K | — |
| 379 | ZZephyr 7B Beta | — | 1041 | 1015–1068 | 461 | — |
| 381 | VVicuna 7B | — | 1035 | 992–1078 | 162 | — |
| 382 | VVicuna 33B | — | 1028 | 1009–1047 | 1K | — |
| 383 | Qwen-14B-Chat | Alibaba | 1028 | 990–1066 | 214 | — |
| 384 | Gemma 7B IT | 1021 | 999–1044 | 676 | — | |
| 385 | Code Llama 34B Instruct | Meta | 1013 | 981–1046 | 320 | — |
| 386 | PaLM 2 | 1009 | 973–1046 | 251 | — | |
| 387 | Gemma 1.1 2B IT | 1002 | 985–1020 | 1.2K | — | |
| 388 | Mistral 7B Instruct | Mistral AI | 1000 | 974–1027 | 448 | — |
| 389 | Snowflake Arctic Instruct | Snowflake | 999 | 985–1013 | 2.8K | — |
| 390 | Llama 2 7B Chat | Meta | 999 | 979–1019 | 835 | — |
| 391 | Llama 2 70B SteerLM Chat | NVIDIA | 998 | 957–1038 | 208 | — |
| 392 | Phi-3 Mini 128K Instruct | Microsoft | 995 | 980–1011 | 2.1K | — |
| 393 | Qwen1.5-4B-Chat | Alibaba | 987 | 964–1011 | 692 | — |
| 394 | SStripedHyena Nous 7B | — | 982 | 951–1013 | 334 | — |
| 395 | Gemma 2B IT | 980 | 951–1010 | 377 | — | |
| 396 | CChatGLM3 6B | — | 952 | 912–991 | 205 | — |
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














