LMArena Multi-turn leaderboard
LMArena’s text votes on conversations of more than one turn. Gemini 4 Argon leads with a rating of 1547.
- Models
- 349
- 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 | 1547 | 1530–1563 | 1.4K | $2 / $10 | |
| 2 | Claude Opus 4.6 | Anthropic | 1512 | 1506–1518 | 14.1K | $5 / $25 |
| 3 | Muse Wonder | Meta | 1507 | 1487–1528 | 858 | $4 / $20 |
| 5 | Claude Opus 4.7 | Anthropic | 1505 | 1499–1512 | 11.4K | $5 / $25 |
| 7 | Claude Fable 5 | Anthropic | 1504 | 1496–1512 | 7.2K | $10 / $50 |
| 8 | Claude Opus 5.5 | Anthropic | 1504 | 1487–1521 | 1.4K | $4 / $20 |
| 9 | Gemini 3.8 Flash | 1503 | 1495–1512 | 6.6K | $0.82 / $4.13 | |
| 10 | Claude Opus 5 | Anthropic | 1500 | 1491–1509 | 5.2K | $5 / $25 |
| 11 | Muse Spark 1.2 | Meta | 1500 | 1484–1515 | 1.5K | $1.25 / $4.25 |
| 12 | Claude Fable 5.1 | Anthropic | 1495 | 1481–1508 | 2.2K | $10 / $50 |
| 14 | Qwen3.8-Max | Alibaba | 1490 | 1481–1500 | 4.6K | $2 / $6 |
| 15 | Kimi K3 | Moonshot AI | 1489 | 1481–1498 | 5.4K | $0.24 / $11 |
| 16 | Muse Spark 1.3 | Meta | 1489 | 1478–1500 | 3.1K | $1.25 / $4.25 |
| 17 | Gemini 3.1 Pro Preview | 1487 | 1482–1492 | 22.1K | $2 / $12 | |
| 18 | Gemini 3.7 Flash | 1487 | 1477–1496 | 4.6K | $0.75 / $3.75 | |
| 19 | Gemini 3 Pro | 1484 | 1476–1492 | 6.9K | — | |
| 20 | Muse Spark 1.1 | Meta | 1484 | 1476–1492 | 7K | $1.25 / $4.25 |
| 21 | GPT-5.4 | OpenAI | 1482 | 1476–1489 | 12K | $2.50 / $15 |
| 22 | Gemini 3.6 Flash | 1481 | 1473–1490 | 5.8K | $0.75 / $3.75 | |
| 23 | Gemini 3.5 Flash | 1481 | 1474–1488 | 8.1K | $1.50 / $9 | |
| 24 | Qwen3.7-Max-Preview | Alibaba | 1480 | 1458–1503 | 700 | $1.48 / $4.42 |
| 25 | Qwen3.5-Max-Preview | Alibaba | 1478 | 1468–1488 | 3.8K | — |
| 26 | Muse Spark | Meta | 1478 | 1464–1491 | 2.3K | — |
| 28 | GPT-5.5 | OpenAI | 1476 | 1469–1483 | 11.8K | $5 / $30 |
| 29 | Claude Opus 4.8 | Anthropic | 1476 | 1469–1483 | 11.2K | $5 / $25 |
| 30 | MiMo-V2.5-Pro | Xiaomi | 1475 | 1469–1482 | 13.1K | $0.30 / $0.61 |
| 33 | GLM-5.1 | Z.ai | 1472 | 1465–1479 | 10.3K | $1.40 / $4.40 |
| 34 | Gemini 3 Flash | 1471 | 1463–1480 | 5.5K | $0.50 / $3 | |
| 35 | GLM-5.3-Flash | Z.ai | 1471 | 1463–1480 | 5.9K | $0.15 / $0.50 |
| 36 | ERNIE 5.1 | Baidu | 1470 | 1462–1479 | 6.8K | — |
| 37 | GLM-5.3 | Z.ai | 1470 | 1460–1480 | 3.7K | $0.079 / $1.40 |
| 38 | GLM-5.2 | Z.ai | 1469 | 1461–1476 | 8.3K | $0.034 / $7 |
| 39 | DeepSeek-V4-Pro | DeepSeek | 1468 | 1461–1475 | 10.4K | $0.66 / $1.98 |
| 40 | Claude Opus 4.5 | Anthropic | 1466 | 1460–1472 | 13K | $5 / $25 |
| 41 | Claude Sonnet 5.5 | Anthropic | 1465 | 1448–1482 | 1.3K | $2 / $10 |
| 42 | MiMo-V2.6-Pro | Xiaomi | 1465 | 1441–1489 | 582 | $0.43 / $0.87 |
| 43 | Claude Sonnet 4.5 | Anthropic | 1465 | 1459–1470 | 14.5K | $3 / $15 |
| 44 | Claude Sonnet 4.6 | Anthropic | 1464 | 1457–1470 | 12.7K | $3 / $15 |
| 46 | GPT-5.6 Sol | OpenAI | 1461 | 1453–1469 | 7K | $4 / $20 |
| 47 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 1460 | 1447–1474 | 2K | $0.15 / $0.60 |
| 49 | Qwen3.7-Plus | Alibaba | 1460 | 1452–1467 | 7K | $0.32 / $1.28 |
| 50 | GPT-5.2 Chat | OpenAI | 1458 | 1450–1466 | 6.8K | $1.75 / $14 |
| 51 | Grok 4.5 | xAI | 1456 | 1448–1464 | 6.6K | $2 / $6 |
| 52 | GLM-5 | Z.ai | 1456 | 1447–1465 | 4.7K | $1 / $3.20 |
| 53 | MiMo-V2-Pro | Xiaomi | 1456 | 1447–1465 | 4.6K | — |
| 54 | Grok 4.20 Beta | xAI | 1456 | 1449–1462 | 12.1K | — |
| 55 | Qwen3.6-Max-Preview | Alibaba | 1456 | 1436–1476 | 931 | — |
| 57 | ChatGPT-4o Latest | OpenAI | 1454 | 1449–1460 | 14.3K | — |
| 60 | Claude Sonnet 5 | Anthropic | 1454 | 1446–1461 | 8.7K | $2 / $10 |
| 61 | Kimi K2.6 | Moonshot AI | 1453 | 1445–1461 | 6.9K | $0.65 / $3.41 |
| 62 | GPT-5.6 Terra | OpenAI | 1453 | 1445–1460 | 7.4K | $2 / $12 |
| 63 | Gemini 2.5 Pro | 1453 | 1448–1457 | 21.2K | $1.25 / $10 | |
| 64 | Grok 4.20 Multi-Agent Beta | xAI | 1452 | 1445–1459 | 10.6K | — |
| 65 | Gemma 4 31B | 1452 | 1435–1469 | 1.1K | $0.20 / $0.40 | |
| 66 | Grok 4.20 Beta 1 | xAI | 1451 | 1441–1460 | 4.6K | — |
| 67 | GPT-5.1 | OpenAI | 1450 | 1442–1457 | 7.2K | $1.25 / $10 |
| 68 | GPT-6 Astra | OpenAI | 1449 | 1435–1463 | 1.9K | $10 / $50 |
| 69 | DeepSeek-V4-Flash | DeepSeek | 1448 | 1441–1456 | 9.3K | $0.042 / $0.18 |
| 70 | Qwen3.5-397B-A17B | Alibaba | 1447 | 1441–1452 | 15.5K | $0.50 / $3.60 |
| 71 | Qwen3-Max-Preview | Alibaba | 1446 | 1437–1455 | 4.5K | — |
| 72 | GLM-4.7 | Z.ai | 1446 | 1432–1459 | 1.9K | $0.54 / $1.98 |
| 73 | GPT-6.1 Sol | OpenAI | 1446 | 1428–1464 | 1.1K | $2 / $10 |
| 75 | Gemini 3.5 Flash-Lite | 1445 | 1437–1454 | 5.9K | $0.30 / $2.50 | |
| 76 | MiMo-V2-Omni | Xiaomi | 1445 | 1434–1456 | 3.5K | — |
| 77 | MiMo-V2.5 | Xiaomi | 1445 | 1437–1452 | 8.4K | $0.12 / $0.24 |
| 78 | Claude Opus 4.1 | Anthropic | 1444 | 1437–1451 | 8.5K | $15 / $75 |
| 79 | Kimi K2.5 | Moonshot AI | 1444 | 1438–1450 | 13.1K | $0.50 / $2.50 |
| 80 | GPT-4.5 Preview | OpenAI | 1444 | 1431–1457 | 2.1K | — |
| 81 | MiMo-V2.6-Flash | Xiaomi | 1444 | 1430–1457 | 2.1K | $0.14 / $0.28 |
| 83 | MiniMax-M3 | MiniMax | 1443 | 1436–1449 | 11.6K | $0.30 / $1.20 |
| 84 | amazon-nova-experimental-chat | Amazon | 1442 | 1418–1465 | 615 | — |
| 85 | Gemma 4 26B A4B | 1441 | 1424–1458 | 1.1K | $0.068 / $0.23 | |
| 86 | Dola Seed 2.0 Pro | ByteDance | 1441 | 1435–1447 | 13.8K | — |
| 87 | Mistral Large 4 | Mistral AI | 1441 | 1425–1456 | 1.5K | $1.36 / $4.18 |
| 88 | Qwen3.8-27B | Alibaba | 1440 | 1430–1450 | 4.1K | $0.20 / $2.50 |
| 89 | Step 5 Preview | StepFun | 1438 | 1422–1455 | 1.4K | $1 / $2.70 |
| 90 | Qwen3.6-Plus | Alibaba | 1438 | 1431–1446 | 8.4K | $0.33 / $1.95 |
| 91 | IInkling | Thinky | 1438 | 1430–1446 | 6.9K | $1 / $4.05 |
| 92 | Hy3 | Tencent | 1438 | 1424–1451 | 2.1K | $0.083 / $0.33 |
| 93 | Grok 4.1 | xAI | 1438 | 1431–1444 | 12.4K | — |
| 94 | GPT-5.6 Luna | OpenAI | 1435 | 1427–1443 | 6.7K | $0.20 / $1.20 |
| 96 | GPT-5.5 Instant | OpenAI | 1434 | 1425–1443 | 5.1K | — |
| 97 | ERNIE 5.0 | Baidu | 1433 | 1425–1441 | 5.9K | — |
| 99 | GLM-5V-Turbo | Z.ai | 1432 | 1417–1447 | 1.7K | $1.20 / $4 |
| 100 | Qwen3-235B-A22B-Instruct | Alibaba | 1432 | 1427–1437 | 17K | $0.09 / $0.55 |
| 103 | Mistral Large 3 | Mistral AI | 1430 | 1425–1436 | 14.6K | $0.50 / $1.50 |
| 104 | GPT-5.4 mini | OpenAI | 1429 | 1423–1436 | 11.9K | $0.75 / $4.50 |
| 105 | Qwen3-VL-235B-A22B-Instruct | Alibaba | 1428 | 1414–1442 | 1.9K | $0.21 / $1.90 |
| 107 | GLM-4.6 | Z.ai | 1427 | 1419–1435 | 5.6K | $0.55 / $2.20 |
| 108 | DeepSeek-V3.2-Exp | DeepSeek | 1427 | 1420–1434 | 8.3K | $0.28 / $0.42 |
| 109 | GPT-5 Chat | OpenAI | 1426 | 1418–1435 | 5.7K | — |
| 110 | Grok 4.6 | xAI | 1426 | 1417–1435 | 4.9K | $2 / $6 |
| 111 | Grok 3 Preview | xAI | 1424 | 1415–1433 | 4.6K | — |
| 113 | Mistral Medium 3.5 | Mistral AI | 1423 | 1409–1437 | 1.9K | $1.50 / $7.50 |
| 114 | Hunyuan Vision 1.5 Thinking | Tencent | 1423 | 1395–1451 | 426 | — |
| 116 | GPT-5.2 | OpenAI | 1419 | 1413–1426 | 9.2K | $1.75 / $14 |
| 119 | Mistral Medium 3.1 | Mistral AI | 1418 | 1413–1423 | 16.4K | $0.40 / $2 |
| 120 | LongCat-Flash-Chat Exp | Meituan | 1418 | 1409–1426 | 5.2K | — |
| 121 | Gemini 3.1 Flash-Lite Preview | 1417 | 1410–1423 | 11.6K | $0.25 / $1.50 | |
| 122 | Qwen3.5-122B-A10B | Alibaba | 1417 | 1408–1425 | 5.2K | $0.40 / $3.20 |
| 123 | Grok 4 | xAI | 1416 | 1408–1424 | 6.2K | — |
| 124 | BBeam 1.0 501B A23B | Reflection AI | 1416 | 1393–1439 | 677 | $0.25 / $1 |
| 125 | IInkling-Small | Thinky | 1416 | 1407–1425 | 5.4K | $0.45 / $1.20 |
| 126 | Qwen3-Next-80B-A3B-Instruct | Alibaba | 1416 | 1406–1425 | 4K | $0.09 / $1.10 |
| 127 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | NVIDIA | 1415 | 1392–1439 | 642 | — |
| 128 | GLM-4.5 | Z.ai | 1415 | 1405–1425 | 3.7K | $0.60 / $2.20 |
| 129 | Kimi K2 Thinking Turbo | Moonshot AI | 1414 | 1408–1420 | 11K | — |
| 130 | Grok 4 Fast | xAI | 1414 | 1396–1432 | 1.1K | — |
| 131 | GPT-6 Sol | OpenAI | 1413 | 1400–1426 | 2.3K | $2 / $10 |
| 133 | MiniMax-M2.7 | MiniMax | 1412 | 1406–1418 | 15K | $0.30 / $1.20 |
| 134 | GPT-5.3 Chat | OpenAI | 1412 | 1404–1420 | 6.5K | — |
| 135 | NVIDIA-Nemotron-3-Ultra-550B-A55B | NVIDIA | 1411 | 1397–1426 | 1.8K | — |
| 137 | DeepSeek-V3.1-Terminus | DeepSeek | 1411 | 1386–1435 | 571 | $0.27 / $1 |
| 138 | Qwen3.5-27B | Alibaba | 1410 | 1401–1419 | 4.9K | $0.27 / $2.16 |
| 140 | Claude Haiku 4.5 | Anthropic | 1409 | 1405–1414 | 26.4K | $1 / $5 |
| 142 | Gemini 2.5 Flash | 1408 | 1403–1413 | 21.7K | $0.30 / $2.50 | |
| 143 | DeepSeek-V3.1 | DeepSeek | 1408 | 1394–1422 | 1.8K | $0.25 / $0.95 |
| 144 | Qwen3-235B-A22B-Thinking | Alibaba | 1406 | 1391–1422 | 1.4K | $0.45 / $3.50 |
| 145 | Grok 4.3 | xAI | 1406 | 1399–1412 | 12.8K | $1.25 / $2.50 |
| 146 | o3 | OpenAI | 1405 | 1398–1412 | 9.7K | $2 / $8 |
| 147 | Step-3.5-Flash | StepFun | 1405 | 1398–1411 | 10.4K | $0.10 / $0.30 |
| 149 | DeepSeek-R1 | DeepSeek | 1404 | 1393–1415 | 2.8K | $0.50 / $2.15 |
| 150 | MiMo-V2-Flash | Xiaomi | 1404 | 1397–1411 | 8.5K | — |
| 153 | Muse Glimmer | Meta | 1399 | 1375–1424 | 616 | — |
| 154 | GPT-5 | OpenAI | 1399 | 1390–1408 | 5K | $1.25 / $10 |
| 155 | Qwen3-235B-A22B | Alibaba | 1398 | 1390–1406 | 6.5K | $0.09 / $0.55 |
| 156 | GPT-4.1 | OpenAI | 1398 | 1391–1405 | 8.7K | $2 / $8 |
| 157 | MiniMax-M2.1 Preview | MiniMax | 1397 | 1385–1408 | 2.8K | $0.30 / $1.20 |
| 159 | Claude Haiku 5.5 | Anthropic | 1396 | 1376–1416 | 927 | $0.10 / $0.50 |
| 160 | Claude Opus 4 | Anthropic | 1396 | 1388–1404 | 6K | — |
| 161 | Grok 4.7 | xAI | 1394 | 1380–1407 | 2.2K | $2 / $6 |
| 162 | Hunyuan T1 | Tencent | 1393 | 1371–1415 | 669 | — |
| 163 | GPT-6 Luna | OpenAI | 1393 | 1386–1400 | 10.5K | $0.10 / $0.50 |
| 164 | Qwen3.5-Flash | Alibaba | 1393 | 1386–1399 | 11K | $0.065 / $0.26 |
| 166 | Qwen3.5-35B-A3B | Alibaba | 1390 | 1382–1399 | 5.5K | $0.14 / $1 |
| 167 | Grok 4.1 Fast | xAI | 1389 | 1383–1396 | 10.3K | — |
| 168 | DeepSeek-V3 | DeepSeek | 1389 | 1381–1396 | 7.7K | $0.29 / $1.14 |
| 171 | Qwen3-VL-235B-A22B-Thinking | Alibaba | 1387 | 1371–1404 | 1.3K | — |
| 172 | Hunyuan TurboS | Tencent | 1387 | 1373–1402 | 1.7K | — |
| 173 | Solar Pro 4 | Upstage | 1387 | 1376–1397 | 3.6K | $0.15 / $0.60 |
| 174 | Mistral Medium 3 | Mistral AI | 1383 | 1375–1392 | 5.7K | $0.40 / $2 |
| 175 | GPT-5.4 nano | OpenAI | 1382 | 1375–1389 | 11.8K | $0.20 / $1.25 |
| 178 | Qwen3-30B-A3B-Instruct | Alibaba | 1379 | 1369–1388 | 3.9K | $0.09 / $0.30 |
| 180 | Claude Sonnet 4 | Anthropic | 1376 | 1368–1385 | 5.6K | — |
| 181 | GLM-4.5-Air | Z.ai | 1371 | 1362–1380 | 5K | $0.13 / $0.85 |
| 182 | Kimi K2 Preview | Moonshot AI | 1371 | 1362–1380 | 4.6K | $0.60 / $2.50 |
| 183 | NVIDIA-Nemotron-3-Super-120B-A12B | NVIDIA | 1369 | 1354–1385 | 1.4K | — |
| 184 | o1 | OpenAI | 1369 | 1359–1378 | 5.9K | $15 / $60 |
| 185 | Gemini 2.5 Flash-Lite Preview | 1366 | 1359–1373 | 8.1K | $0.10 / $0.40 | |
| 186 | Qwen3-Coder-480B-A35B-Instruct | Alibaba | 1365 | 1356–1375 | 4.3K | — |
| 189 | Qwen2.5-Max | Alibaba | 1364 | 1356–1373 | 4.8K | — |
| 191 | MiniMax-M2.5 | MiniMax | 1364 | 1356–1371 | 7.7K | $0.30 / $1.20 |
| 192 | GPT-5 mini | OpenAI | 1363 | 1354–1372 | 4.4K | $0.25 / $2 |
| 193 | MiniMax-M2 | MiniMax | 1361 | 1344–1379 | 1.1K | $0.26 / $1.02 |
| 196 | GLM-4.6V | Z.ai | 1359 | 1333–1385 | 488 | $0.30 / $0.90 |
| 197 | Mercury 2 | Inception | 1357 | 1332–1382 | 551 | $0.25 / $0.75 |
| 198 | Grok 3 Mini | xAI | 1355 | 1343–1367 | 2.5K | — |
| 201 | GPT-4.1 mini | OpenAI | 1354 | 1346–1362 | 7K | $0.40 / $1.60 |
| 202 | Grok 3 Mini Beta | xAI | 1351 | 1341–1361 | 3.4K | — |
| 203 | IINTELLECT-3 | — | 1350 | 1330–1370 | 794 | — |
| 204 | o4-mini | OpenAI | 1350 | 1343–1357 | 7.7K | $1.10 / $4.40 |
| 205 | Gemini 2.0 Flash | 1350 | 1342–1357 | 6.8K | — | |
| 207 | Qwen3-Next-80B-A3B-Thinking | Alibaba | 1346 | 1333–1359 | 2.2K | $0.15 / $1.20 |
| 208 | Gemma 3 27B IT | 1345 | 1337–1352 | 6.7K | $0.08 / $0.35 | |
| 209 | Mistral Small 3.2 | Mistral AI | 1343 | 1333–1354 | 3K | — |
| 210 | Trinity Large Preview | Arcee | 1342 | 1333–1351 | 5.6K | — |
| 211 | GLM-4.7-Flash | Z.ai | 1342 | 1329–1355 | 2.1K | $0.06 / $0.40 |
| 212 | Step-3 | StepFun | 1341 | 1322–1359 | 1K | — |
| 213 | Step-1o Turbo | StepFun | 1340 | 1324–1356 | 1.4K | — |
| 214 | Granite 4.2 30B | IBM | 1340 | 1313–1366 | 552 | — |
| 215 | gpt-oss-120b | OpenAI | 1340 | 1331–1348 | 4.9K | $0.15 / $0.60 |
| 216 | Claude 3.7 Sonnet | Anthropic | 1339 | 1332–1347 | 6.8K | — |
| 217 | Command A | Cohere | 1338 | 1332–1345 | 9.3K | $0.30 / $1.50 |
| 218 | Amazon Nova 2 Lite | Amazon | 1338 | 1325–1351 | 2.1K | — |
| 220 | Qwen-Plus | Alibaba | 1336 | 1317–1355 | 842 | $0.26 / $0.78 |
| 221 | MiniMax-M1 | MiniMax | 1335 | 1327–1343 | 5.4K | $0.55 / $2.20 |
| 222 | Gemma 3 12B IT | 1334 | 1308–1359 | 471 | $0.05 / $0.15 | |
| 223 | Llama 3.3 Nemotron Super 49B v1.5 | NVIDIA | 1334 | 1310–1358 | 560 | — |
| 224 | GLM-4.5V | Z.ai | 1333 | 1313–1353 | 850 | $0.60 / $1.80 |
| 225 | Qwen3-32B | Alibaba | 1331 | 1308–1354 | 590 | $0.08 / $0.28 |
| 226 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B | NVIDIA | 1329 | 1317–1341 | 3K | — |
| 227 | Claude 3.5 Sonnet | Anthropic | 1326 | 1320–1331 | 15.9K | — |
| 228 | GLM-4-Plus | Z.ai | 1324 | 1304–1343 | 851 | — |
| 229 | LLing-flash-2.0 | Ant Group | 1323 | 1306–1341 | 1.1K | — |
| 230 | o3-mini | OpenAI | 1320 | 1309–1332 | 2.5K | $1.10 / $4.40 |
| 231 | Trinity Large Thinking | Arcee | 1320 | 1311–1329 | 5.6K | $0.25 / $0.80 |
| 233 | NVIDIA-Nemotron-3-Nano-30B-A3B | NVIDIA | 1320 | 1308–1331 | 2.6K | — |
| 234 | Llama 3.1 Nemotron Ultra 253B v1 | NVIDIA | 1317 | 1287–1347 | 374 | — |
| 235 | Llama 3.3 Nemotron Super 49B v1 | NVIDIA | 1315 | 1283–1347 | 301 | — |
| 236 | o1-mini | OpenAI | 1314 | 1307–1321 | 9.3K | — |
| 237 | QwQ-32B | Alibaba | 1314 | 1304–1323 | 3.8K | — |
| 239 | GPT-5 nano | OpenAI | 1312 | 1296–1327 | 1.4K | $0.05 / $0.40 |
| 240 | Yi Lightning | 01.AI | 1311 | 1301–1321 | 4.7K | — |
| 241 | Olmo 3.1 32B Instruct | Ai2 | 1310 | 1297–1323 | 2.1K | — |
| 242 | Gemini 2.0 Flash-Lite Preview | 1307 | 1298–1317 | 3.6K | — | |
| 243 | Qwen3-30B-A3B | Alibaba | 1307 | 1298–1316 | 4.4K | $0.12 / $0.50 |
| 244 | Hunyuan Turbo | Tencent | 1303 | 1274–1332 | 323 | — |
| 245 | GPT-4o | OpenAI | 1302 | 1295–1308 | 20.4K | $2.50 / $10 |
| 246 | Granite 4.2 8B | IBM | 1300 | 1272–1328 | 524 | $0.06 / $0.25 |
| 247 | Qwen2.5-Plus | Alibaba | 1299 | 1286–1313 | 1.8K | — |
| 249 | Llama 3.1 405B Instruct | Meta | 1297 | 1289–1305 | 6.8K | — |
| 250 | DeepSeek-V2.5 | DeepSeek | 1297 | 1280–1313 | 1.2K | — |
| 251 | Gemini 1.5 Pro | 1296 | 1289–1303 | 10.1K | — | |
| 252 | Step-2 16K Exp | StepFun | 1292 | 1272–1312 | 805 | — |
| 253 | Granite 4.2 3B | IBM | 1292 | 1264–1321 | 530 | — |
| 254 | Grok 2 | xAI | 1290 | 1283–1297 | 10.7K | — |
| 255 | Olmo 3 32B Think | Ai2 | 1290 | 1268–1312 | 771 | — |
| 256 | Llama 4 Maverick 17B 128E Instruct | Meta | 1289 | 1282–1297 | 6.7K | — |
| 259 | RRing-flash-2.0 | Ant Group | 1287 | 1269–1305 | 1.1K | — |
| 260 | AAthene V2 Chat | — | 1286 | 1276–1295 | 4.3K | — |
| 261 | GPT-4o mini | OpenAI | 1285 | 1278–1292 | 12.3K | $0.15 / $0.60 |
| 262 | Hunyuan Large | Tencent | 1284 | 1259–1310 | 510 | — |
| 263 | Mercury | Inception | 1282 | 1250–1314 | 333 | — |
| 264 | Llama 4 Scout 17B 16E Instruct | Meta | 1280 | 1271–1289 | 5.2K | — |
| 265 | Llama 3.3 70B Instruct | Meta | 1280 | 1273–1286 | 9.1K | $0.10 / $0.32 |
| 267 | GPT-4.1 nano | OpenAI | 1277 | 1259–1295 | 1K | $0.10 / $0.40 |
| 268 | Qwen-Max | Alibaba | 1277 | 1266–1288 | 3.1K | — |
| 269 | Gemma 3n E4B IT | 1276 | 1266–1287 | 3.3K | — | |
| 270 | Llama 3.1 Nemotron 70B Instruct | NVIDIA | 1275 | 1259–1292 | 1.2K | — |
| 271 | Claude 3 Opus | Anthropic | 1275 | 1269–1281 | 31.1K | — |
| 272 | Hunyuan Standard | Tencent | 1275 | 1251–1299 | 570 | — |
| 273 | Magistral Medium | Mistral AI | 1275 | 1260–1290 | 1.6K | — |
| 274 | Qwen2.5-72B-Instruct | Alibaba | 1272 | 1264–1280 | 7.3K | $0.36 / $0.40 |
| 275 | Mistral Small 3.1 24B Instruct | Mistral AI | 1271 | 1262–1279 | 5.4K | $0.35 / $0.56 |
| 276 | Granite 4.1 8B | IBM | 1269 | 1244–1294 | 703 | — |
| 277 | Gemini Advanced | 1269 | 1259–1278 | 7.8K | — | |
| 279 | gpt-oss-20b | OpenAI | 1268 | 1253–1282 | 1.8K | $0.018 / $0.09 |
| 280 | GPT-4 Turbo | OpenAI | 1267 | 1260–1274 | 15.3K | $10 / $30 |
| 281 | Grok 2 mini | xAI | 1265 | 1258–1273 | 9.4K | — |
| 282 | Claude 3.5 Haiku | Anthropic | 1265 | 1259–1271 | 11.2K | — |
| 284 | Mistral Large | Mistral AI | 1260 | 1251–1269 | 4.4K | $0.50 / $1.50 |
| 285 | Mistral Large 2 | Mistral AI | 1257 | 1249–1265 | 8.3K | — |
| 286 | AAthene 70B | — | 1257 | 1246–1268 | 3.3K | — |
| 288 | Llama 3.1 70B Instruct | Meta | 1256 | 1249–1263 | 10.4K | $0.40 / $0.40 |
| 289 | Gemma 3 4B IT | 1255 | 1232–1279 | 565 | $0.04 / $0.05 | |
| 290 | Hunyuan Large Vision | Tencent | 1253 | 1233–1273 | 942 | — |
| 291 | Gemini 1.5 Flash | 1253 | 1244–1261 | 6.3K | — | |
| 292 | Llama 3.1 Tulu 3 70B | Ai2 | 1252 | 1228–1275 | 537 | — |
| 294 | Olmo 3.1 32B Think | Ai2 | 1250 | 1232–1268 | 1.2K | — |
| 295 | Amazon Nova Pro 1.0 | Amazon | 1246 | 1236–1255 | 4.1K | — |
| 296 | Granite-4.0-H-Small | IBM | 1243 | 1223–1263 | 944 | — |
| 298 | Llama 3.1 Nemotron 51B Instruct | NVIDIA | 1227 | 1207–1247 | 781 | — |
| 299 | Claude 3 Sonnet | Anthropic | 1227 | 1219–1235 | 17.1K | — |
| 300 | Reka Core | Reka | 1227 | 1210–1243 | 1.3K | — |
| 301 | Gemma 2 27B IT | 1224 | 1217–1230 | 13.6K | $0.65 / $0.65 | |
| 302 | Llama 3 70B Instruct | Meta | 1223 | 1216–1230 | 21.4K | — |
| 303 | Qwen2.5-Coder-32B-Instruct | Alibaba | 1222 | 1205–1240 | 1K | $0.66 / $1 |
| 304 | OLMo 2 32B Instruct | Ai2 | 1221 | 1192–1250 | 363 | — |
| 305 | Jamba 1.5 Large | AI21 Labs | 1220 | 1205–1234 | 1.6K | — |
| 306 | Gemma 2 9B IT SimPO | 1220 | 1205–1234 | 1.7K | — | |
| 307 | GLM-4 | Z.ai | 1218 | 1203–1233 | 1.6K | — |
| 308 | Mistral Small 24B Instruct | Mistral AI | 1217 | 1204–1230 | 2.2K | $0.05 / $0.08 |
| 309 | Nemotron-4 340B Instruct | NVIDIA | 1214 | 1202–1225 | 3.1K | — |
| 310 | Command R+ | Cohere | 1213 | 1199–1226 | 1.8K | $0.15 / $0.60 |
| 311 | GPT-4 | OpenAI | 1206 | 1196–1216 | 8K | $30 / $60 |
| 312 | Phi-4 | Microsoft | 1206 | 1196–1216 | 3.5K | $0.07 / $0.14 |
| 313 | Amazon Nova Lite 1.0 | Amazon | 1199 | 1188–1209 | 3.2K | — |
| 314 | Qwen2-72B-Instruct | Alibaba | 1196 | 1186–1205 | 6.7K | — |
| 315 | Gemma 2 9B IT | 1193 | 1186–1201 | 9.7K | — | |
| 317 | Aya Expanse 32B | Cohere | 1190 | 1181–1199 | 5.2K | — |
| 318 | Claude 3 Haiku | Anthropic | 1190 | 1183–1197 | 19.3K | — |
| 319 | Reka Flash | Reka | 1189 | 1173–1205 | 1.3K | — |
| 320 | Gemini 1.5 Flash-8B | 1185 | 1177–1194 | 6.7K | — | |
| 322 | Amazon Nova Micro 1.0 | Amazon | 1178 | 1167–1189 | 3.1K | — |
| 323 | DeepSeek-Coder-V2 | DeepSeek | 1177 | 1164–1189 | 2.7K | — |
| 324 | Hunyuan Standard 256K | Tencent | 1175 | 1150–1199 | 532 | — |
| 326 | Llama 3.1 8B Instruct | Meta | 1172 | 1164–1180 | 8.9K | $0.05 / $0.08 |
| 327 | Ministral 8B | Mistral AI | 1166 | 1148–1185 | 916 | $0.15 / $0.15 |
| 329 | Qwen1.5-72B-Chat | Alibaba | 1160 | 1150–1170 | 5.5K | — |
| 330 | Qwen1.5-110B-Chat | Alibaba | 1160 | 1148–1171 | 3.7K | — |
| 331 | Aya Expanse 8B | Cohere | 1160 | 1145–1174 | 1.7K | — |
| 332 | Jamba 1.5 Mini | AI21 Labs | 1157 | 1142–1171 | 1.6K | — |
| 333 | Llama 3.1 Tulu 3 8B | Ai2 | 1154 | 1129–1179 | 520 | — |
| 334 | Yi 1.5 34B Chat | 01.AI | 1153 | 1142–1164 | 3.4K | — |
| 335 | Llama 3 8B Instruct | Meta | 1152 | 1144–1161 | 14.8K | — |
| 336 | Reka Flash 21B | Reka | 1151 | 1136–1166 | 2K | — |
| 338 | Mistral Medium | Mistral AI | 1147 | 1136–1159 | 4.6K | — |
| 341 | Qwen1.5-32B-Chat | Alibaba | 1140 | 1127–1152 | 3.1K | — |
| 342 | Gemini Pro | 1139 | 1115–1164 | 641 | $2 / $10 | |
| 343 | IInternLM2.5 20B Chat | — | 1136 | 1121–1150 | 1.8K | — |
| 344 | Mixtral 8x22B Instruct v0.1 | Mistral AI | 1130 | 1121–1139 | 7.8K | — |
| 346 | Gemma 2 2B IT | 1118 | 1110–1126 | 7.9K | — | |
| 347 | GPT-3.5 Turbo | OpenAI | 1117 | 1108–1125 | 10.3K | $1 / $2 |
| 348 | Mixtral 8x7B Instruct v0.1 | Mistral AI | 1115 | 1106–1123 | 10.9K | — |
| 349 | Yi 34B Chat | 01.AI | 1113 | 1098–1128 | 1.9K | — |
| 350 | SStarling LM 7B Beta | — | 1111 | 1096–1126 | 2.2K | — |
| 351 | DDBRX Instruct Preview | — | 1111 | 1099–1123 | 4.9K | — |
| 352 | Qwen1.5-14B-Chat | Alibaba | 1110 | 1096–1124 | 2.6K | — |
| 353 | WizardLM 70B | Microsoft | 1108 | 1089–1128 | 1.2K | — |
| 354 | Granite 3.1 8B Instruct | IBM | 1108 | 1082–1134 | 551 | — |
| 355 | Llama 3.2 3B Instruct | Meta | 1105 | 1088–1122 | 1.3K | $0.051 / $0.34 |
| 356 | ZZephyr ORPO 141B A35B v0.1 | — | 1100 | 1076–1124 | 683 | — |
| 357 | Granite 3.1 2B Instruct | IBM | 1099 | 1072–1126 | 579 | — |
| 358 | OOpenChat 3.5 | — | 1091 | 1076–1106 | 1.8K | — |
| 359 | Llama 2 70B Chat | Meta | 1088 | 1078–1098 | 5.5K | — |
| 360 | Phi-3 Medium 4K Instruct | Microsoft | 1088 | 1077–1099 | 3.8K | — |
| 361 | TTulu 2 DPO 70B | — | 1085 | 1064–1107 | 827 | — |
| 363 | SStarling LM 7B Alpha | — | 1085 | 1068–1102 | 1.3K | — |
| 364 | DeepSeek LLM 67B Chat | DeepSeek | 1082 | 1058–1106 | 620 | — |
| 365 | Nous Hermes 2 Mixtral 8x7B DPO | Nous Research | 1081 | 1055–1107 | 467 | — |
| 366 | VVicuna 33B | — | 1080 | 1068–1093 | 3.1K | — |
| 368 | Snowflake Arctic Instruct | Snowflake | 1072 | 1060–1085 | 4K | — |
| 369 | Phi-3 Small 8K Instruct | Microsoft | 1068 | 1056–1081 | 3.1K | — |
| 370 | OpenHermes 2.5 Mistral 7B | Mistral AI | 1064 | 1042–1087 | 722 | — |
| 371 | Granite 3.0 8B Instruct | IBM | 1063 | 1043–1082 | 1.1K | — |
| 372 | Mistral 7B Instruct v0.2 | Mistral AI | 1062 | 1049–1076 | 2.6K | — |
| 373 | Qwen1.5-7B-Chat | Alibaba | 1062 | 1037–1086 | 589 | — |
| 374 | Llama 2 70B SteerLM Chat | NVIDIA | 1058 | 1030–1086 | 451 | — |
| 375 | MMPT 30B Chat | — | 1055 | 1023–1086 | 341 | — |
| 376 | Granite 3.0 2B Instruct | IBM | 1053 | 1034–1072 | 1.2K | — |
| 377 | Llama 2 13B Chat | Meta | 1050 | 1036–1064 | 2.6K | — |
| 378 | Phi-3 Mini 4K Instruct | Microsoft | 1049 | 1034–1064 | 1.8K | — |
| 379 | WizardLM 13B | Microsoft | 1047 | 1027–1067 | 983 | — |
| 380 | SOLAR 10.7B Instruct v1.0 | Upstage | 1045 | 1020–1070 | 601 | — |
| 381 | Gemma 1.1 7B IT | 1040 | 1028–1051 | 3.6K | — | |
| 382 | ZZephyr 7B Beta | — | 1038 | 1020–1055 | 1.6K | — |
| 383 | VVicuna 13B | — | 1031 | 1017–1045 | 2.6K | — |
| 384 | Llama 3.2 1B Instruct | Meta | 1030 | 1011–1048 | 1.2K | $0.027 / $0.20 |
| 385 | Llama 2 7B Chat | Meta | 1029 | 1014–1044 | 1.9K | — |
| 386 | Qwen-14B-Chat | Alibaba | 1022 | 999–1045 | 753 | — |
| 387 | Dolphin 2.2.1 Mistral 7B | Mistral AI | 1021 | 980–1061 | 208 | — |
| 389 | ZZephyr 7B Alpha | — | 1018 | 983–1052 | 283 | — |
| 390 | Code Llama 34B Instruct | Meta | 1015 | 997–1034 | 1.2K | — |
| 391 | Falcon 180B Chat | TII | 1013 | 973–1053 | 207 | — |
| 392 | Mistral 7B Instruct | Mistral AI | 1008 | 989–1027 | 1.3K | — |
| 393 | SStripedHyena Nous 7B | — | 1008 | 985–1030 | 738 | — |
| 394 | OLMo 7B Instruct | Ai2 | 1007 | 980–1035 | 537 | — |
| 395 | GGuanaco 33B | — | 1006 | 973–1039 | 331 | — |
| 396 | PaLM 2 | 994 | 975–1014 | 1.2K | — | |
| 397 | SSmolLM2 1.7B Instruct | — | 993 | 955–1031 | 339 | — |
| 398 | Phi-3 Mini 128K Instruct | Microsoft | 989 | 973–1004 | 2.5K | — |
| 399 | VVicuna 7B | — | 988 | 967–1009 | 935 | — |
| 400 | Qwen1.5-4B-Chat | Alibaba | 977 | 959–996 | 1.1K | — |
| 401 | Gemma 7B IT | 963 | 945–982 | 1.3K | — | |
| 402 | CChatGLM3 6B | — | 962 | 936–987 | 637 | — |
| 403 | Gemma 1.1 2B IT | 959 | 941–976 | 1.5K | — | |
| 404 | Gemma 2B IT | 945 | 922–968 | 768 | — | |
| 405 | GPT4All 13B Snoozy | OpenAI | 927 | 889–964 | 253 | — |
| 406 | KKoala 13B | — | 923 | 900–947 | 792 | — |
| 407 | CChatGLM2 6B | — | 902 | 870–934 | 369 | — |
| 408 | MMPT 7B Chat | — | 902 | 873–930 | 466 | — |
| 409 | RRWKV-4 Raven 14B | — | 894 | 867–921 | 556 | — |
| 410 | AAlpaca 13B | — | 884 | 859–910 | 653 | — |
| 411 | OOpenAssistant Pythia 12B | — | 869 | 844–894 | 683 | — |
| 412 | CChatGLM 6B | — | 856 | 827–886 | 492 | — |
| 413 | FFastChat-T5 3B | — | 853 | 823–883 | 387 | — |
| 414 | SStableLM Tuned Alpha 7B | — | 821 | 787–854 | 354 | — |
| 415 | LLaMA 13B | Meta | 753 | 711–796 | 247 | — |
| 416 | DDolly 2.0 12B | — | 740 | 705–776 | 356 | — |
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















