LMArena Legal and government leaderboard
LMArena’s text votes on legal and government prompts. Claude Opus 5 leads with a rating of 1529.
- Models
- 325
- 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 | 1529 | 1518–1541 | 3K | $5 / $25 |
| 2 | Gemini 4 Argon | 1527 | 1506–1549 | 815 | $2 / $10 | |
| 4 | Claude Opus 5.5 | Anthropic | 1516 | 1496–1537 | 888 | $4 / $20 |
| 5 | Muse Spark 1.2 | Meta | 1513 | 1492–1534 | 832 | $1.25 / $4.25 |
| 6 | Claude Opus 4.6 | Anthropic | 1512 | 1504–1520 | 6.8K | $5 / $25 |
| 7 | Claude Fable 5.1 | Anthropic | 1512 | 1495–1528 | 1.3K | $10 / $50 |
| 9 | Muse Wonder | Meta | 1507 | 1480–1534 | 504 | $4 / $20 |
| 10 | Claude Opus 4.7 | Anthropic | 1504 | 1495–1513 | 5.3K | $5 / $25 |
| 11 | Kimi K3 | Moonshot AI | 1502 | 1490–1513 | 2.8K | $0.24 / $11 |
| 12 | Muse Spark 1.3 | Meta | 1499 | 1484–1514 | 1.7K | $1.25 / $4.25 |
| 13 | Gemini 3.8 Flash | 1498 | 1488–1508 | 3.9K | $0.82 / $4.13 | |
| 14 | Claude Fable 5 | Anthropic | 1498 | 1487–1508 | 3.7K | $10 / $50 |
| 15 | Gemini 3.7 Flash | 1497 | 1485–1510 | 2.6K | $0.75 / $3.75 | |
| 16 | Qwen3.8-Max | Alibaba | 1494 | 1481–1507 | 2.3K | $2 / $6 |
| 17 | Gemini 3 Pro | 1492 | 1481–1503 | 3K | — | |
| 18 | GPT-5.5 | OpenAI | 1491 | 1482–1500 | 5.6K | $5 / $30 |
| 20 | Gemini 3.5 Flash | 1488 | 1478–1498 | 3.8K | $1.50 / $9 | |
| 22 | Gemini 3.1 Pro Preview | 1487 | 1480–1493 | 10.7K | $2 / $12 | |
| 23 | GLM-5.2 | Z.ai | 1486 | 1476–1496 | 4.2K | $0.034 / $7 |
| 24 | GPT-5.4 | OpenAI | 1486 | 1477–1495 | 5.2K | $2.50 / $15 |
| 25 | Muse Spark | Meta | 1485 | 1466–1504 | 1K | — |
| 26 | MiMo-V2.6-Pro | Xiaomi | 1485 | 1453–1516 | 347 | $0.43 / $0.87 |
| 27 | Qwen3.5-Max-Preview | Alibaba | 1483 | 1469–1498 | 1.7K | — |
| 28 | Muse Spark 1.1 | Meta | 1482 | 1472–1492 | 4K | $1.25 / $4.25 |
| 30 | Claude Sonnet 5.5 | Anthropic | 1480 | 1459–1502 | 751 | $2 / $10 |
| 31 | Gemini 2.5 Pro | 1480 | 1473–1487 | 8.9K | $1.25 / $10 | |
| 32 | Gemini 3.6 Flash | 1479 | 1468–1490 | 3K | $0.75 / $3.75 | |
| 33 | Qwen3.7-Max-Preview | Alibaba | 1477 | 1443–1510 | 311 | $1.48 / $4.42 |
| 34 | Claude Opus 4.8 | Anthropic | 1477 | 1468–1485 | 5.5K | $5 / $25 |
| 36 | GPT-5.6 Sol | OpenAI | 1475 | 1465–1485 | 3.6K | $4 / $20 |
| 37 | GLM-5.3-Flash | Z.ai | 1475 | 1463–1486 | 3.1K | $0.15 / $0.50 |
| 38 | MiMo-V2.5-Pro | Xiaomi | 1474 | 1466–1482 | 6.3K | $0.30 / $0.61 |
| 39 | GLM-5.3 | Z.ai | 1473 | 1460–1486 | 2.2K | $0.079 / $1.40 |
| 40 | Gemini 3 Flash | 1473 | 1461–1485 | 2.4K | $0.50 / $3 | |
| 41 | Claude Sonnet 4.6 | Anthropic | 1470 | 1462–1479 | 5.7K | $3 / $15 |
| 42 | amazon-nova-experimental-chat | Amazon | 1469 | 1434–1504 | 260 | — |
| 43 | ERNIE 5.1 | Baidu | 1468 | 1457–1479 | 3.1K | — |
| 44 | GPT-6.1 Sol | OpenAI | 1467 | 1444–1489 | 696 | $2 / $10 |
| 45 | GLM-5.1 | Z.ai | 1465 | 1457–1474 | 5.1K | $1.40 / $4.40 |
| 46 | DeepSeek-V4-Pro | DeepSeek | 1464 | 1455–1474 | 4.5K | $0.66 / $1.98 |
| 47 | Grok 4.5 | xAI | 1463 | 1453–1474 | 3.3K | $2 / $6 |
| 49 | GPT-5.6 Terra | OpenAI | 1462 | 1452–1472 | 3.9K | $2 / $12 |
| 50 | Kimi K2.6 | Moonshot AI | 1461 | 1450–1472 | 3K | $0.65 / $3.41 |
| 51 | GPT-6 Astra | OpenAI | 1461 | 1443–1478 | 1.2K | $10 / $50 |
| 53 | Claude Opus 4.5 | Anthropic | 1459 | 1450–1467 | 5.4K | $5 / $25 |
| 54 | GPT-5.1 | OpenAI | 1459 | 1448–1470 | 3.1K | $1.25 / $10 |
| 56 | ERNIE 5.0 | Baidu | 1458 | 1429–1488 | 325 | — |
| 57 | DeepSeek-V3.1-Terminus | DeepSeek | 1458 | 1422–1493 | 258 | $0.27 / $1 |
| 58 | Gemma 4 26B A4B | 1456 | 1429–1483 | 415 | $0.068 / $0.23 | |
| 59 | Qwen3.6-Max-Preview | Alibaba | 1455 | 1425–1485 | 400 | — |
| 61 | Claude Sonnet 5 | Anthropic | 1454 | 1445–1464 | 4.4K | $2 / $10 |
| 62 | Grok 4.20 Beta | xAI | 1454 | 1445–1463 | 5.3K | — |
| 63 | GLM-5 | Z.ai | 1454 | 1441–1466 | 2.3K | $1 / $3.20 |
| 64 | NVIDIA-Nemotron-3-Ultra-550B-A55B | NVIDIA | 1453 | 1434–1472 | 967 | — |
| 65 | Qwen3.7-Plus | Alibaba | 1452 | 1441–1462 | 3.6K | $0.32 / $1.28 |
| 66 | Claude Sonnet 4.5 | Anthropic | 1450 | 1442–1458 | 6K | $3 / $15 |
| 67 | Dola Seed 2.0 Pro | ByteDance | 1449 | 1441–1457 | 6.2K | — |
| 68 | Grok 4.20 Multi-Agent Beta | xAI | 1449 | 1440–1457 | 5.2K | — |
| 69 | GLM-4.6 | Z.ai | 1448 | 1436–1460 | 2.5K | $0.55 / $2.20 |
| 71 | IInkling | Thinky | 1448 | 1437–1458 | 3.6K | $1 / $4.05 |
| 72 | Qwen3.8-27B | Alibaba | 1447 | 1434–1461 | 2K | $0.20 / $2.50 |
| 73 | MiMo-V2-Pro | Xiaomi | 1446 | 1432–1460 | 1.9K | — |
| 74 | GPT-5.6 Luna | OpenAI | 1446 | 1435–1457 | 3.5K | $0.20 / $1.20 |
| 75 | Grok 4.1 | xAI | 1445 | 1436–1454 | 5K | — |
| 77 | Grok 3 Preview | xAI | 1445 | 1431–1459 | 1.9K | — |
| 78 | ChatGPT-4o Latest | OpenAI | 1445 | 1436–1453 | 5.3K | — |
| 79 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 1445 | 1427–1462 | 1.2K | $0.15 / $0.60 |
| 80 | GLM-4.7 | Z.ai | 1445 | 1426–1463 | 969 | $0.54 / $1.98 |
| 81 | MiMo-V2.6-Flash | Xiaomi | 1442 | 1424–1459 | 1.2K | $0.14 / $0.28 |
| 83 | Qwen3.5-397B-A17B | Alibaba | 1441 | 1434–1449 | 7.4K | $0.50 / $3.60 |
| 84 | Step 5 Preview | StepFun | 1441 | 1421–1461 | 822 | $1 / $2.70 |
| 85 | Kimi K2.5 | Moonshot AI | 1441 | 1433–1449 | 5.6K | $0.50 / $2.50 |
| 86 | Mistral Large 3 | Mistral AI | 1441 | 1433–1448 | 6.6K | $0.50 / $1.50 |
| 88 | Mistral Medium 3.1 | Mistral AI | 1439 | 1432–1447 | 6.7K | $0.40 / $2 |
| 89 | DeepSeek-V4-Flash | DeepSeek | 1439 | 1429–1449 | 4.1K | $0.042 / $0.18 |
| 90 | Qwen3-VL-235B-A22B-Instruct | Alibaba | 1439 | 1416–1461 | 736 | $0.21 / $1.90 |
| 92 | Gemma 4 31B | 1438 | 1412–1464 | 451 | $0.20 / $0.40 | |
| 94 | GLM-4.5 | Z.ai | 1438 | 1422–1453 | 1.5K | $0.60 / $2.20 |
| 95 | Qwen3.6-Plus | Alibaba | 1437 | 1427–1448 | 3.6K | $0.33 / $1.95 |
| 97 | Mistral Medium 3.5 | Mistral AI | 1437 | 1417–1457 | 889 | $1.50 / $7.50 |
| 98 | GPT-5.2 Chat | OpenAI | 1437 | 1425–1449 | 2.7K | $1.75 / $14 |
| 99 | GLM-5V-Turbo | Z.ai | 1436 | 1416–1457 | 827 | $1.20 / $4 |
| 100 | MiniMax-M3 | MiniMax | 1436 | 1427–1445 | 5.4K | $0.30 / $1.20 |
| 102 | Qwen3-Max-Preview | Alibaba | 1435 | 1420–1449 | 1.7K | — |
| 103 | GPT-4.5 Preview | OpenAI | 1434 | 1411–1456 | 701 | — |
| 104 | Grok 4.20 Beta 1 | xAI | 1434 | 1420–1447 | 2.1K | — |
| 105 | BBeam 1.0 501B A23B | Reflection AI | 1431 | 1400–1462 | 349 | $0.25 / $1 |
| 106 | Gemini 3.5 Flash-Lite | 1431 | 1420–1443 | 3.1K | $0.30 / $2.50 | |
| 107 | Qwen3-Next-80B-A3B-Instruct | Alibaba | 1431 | 1416–1447 | 1.4K | $0.09 / $1.10 |
| 108 | GPT-5 Chat | OpenAI | 1431 | 1417–1445 | 1.9K | — |
| 109 | Hy3 | Tencent | 1431 | 1405–1457 | 554 | $0.083 / $0.33 |
| 110 | Gemini 2.5 Flash | 1431 | 1424–1437 | 8.9K | $0.30 / $2.50 | |
| 111 | Grok 4.6 | xAI | 1429 | 1417–1441 | 2.7K | $2 / $6 |
| 112 | MiMo-V2-Omni | Xiaomi | 1429 | 1414–1444 | 1.7K | — |
| 113 | Qwen3-235B-A22B-Instruct | Alibaba | 1428 | 1421–1436 | 6.6K | $0.09 / $0.55 |
| 114 | o3 | OpenAI | 1428 | 1418–1438 | 3.7K | $2 / $8 |
| 115 | Grok 4 | xAI | 1428 | 1416–1440 | 2.6K | — |
| 117 | GPT-5.2 | OpenAI | 1427 | 1417–1437 | 3.8K | $1.75 / $14 |
| 118 | Mistral Large 4 | Mistral AI | 1427 | 1407–1448 | 844 | $1.36 / $4.18 |
| 119 | Grok 4 Fast | xAI | 1427 | 1410–1444 | 1.1K | — |
| 120 | DeepSeek-V3.2-Exp | DeepSeek | 1426 | 1415–1436 | 3.5K | $0.28 / $0.42 |
| 122 | MiMo-V2.5 | Xiaomi | 1425 | 1414–1435 | 3.8K | $0.12 / $0.24 |
| 124 | GPT-5 | OpenAI | 1423 | 1409–1437 | 1.8K | $1.25 / $10 |
| 126 | Qwen3.5-122B-A10B | Alibaba | 1422 | 1410–1435 | 2.3K | $0.40 / $3.20 |
| 127 | Claude Opus 4.1 | Anthropic | 1421 | 1410–1431 | 3.2K | $15 / $75 |
| 130 | GPT-5.5 Instant | OpenAI | 1420 | 1407–1433 | 2.3K | — |
| 131 | Grok 4.7 | xAI | 1420 | 1403–1436 | 1.2K | $2 / $6 |
| 133 | DeepSeek-R1 | DeepSeek | 1419 | 1402–1435 | 1.4K | $0.50 / $2.15 |
| 134 | Gemini 3.1 Flash-Lite Preview | 1418 | 1409–1427 | 5K | $0.25 / $1.50 | |
| 136 | LongCat-Flash-Chat Exp | Meituan | 1417 | 1396–1438 | 777 | — |
| 137 | DeepSeek-V3.1 | DeepSeek | 1417 | 1397–1438 | 770 | $0.25 / $0.95 |
| 139 | Hunyuan T1 | Tencent | 1416 | 1383–1450 | 274 | — |
| 141 | Kimi K2 Thinking Turbo | Moonshot AI | 1416 | 1407–1425 | 4.6K | — |
| 142 | Qwen3-235B-A22B-Thinking | Alibaba | 1415 | 1390–1440 | 532 | $0.45 / $3.50 |
| 143 | IInkling-Small | Thinky | 1415 | 1404–1426 | 3.1K | $0.45 / $1.20 |
| 144 | GPT-5.4 mini | OpenAI | 1414 | 1404–1423 | 5.1K | $0.75 / $4.50 |
| 145 | MiniMax-M2.1 Preview | MiniMax | 1410 | 1394–1427 | 1.2K | $0.30 / $1.20 |
| 146 | MiMo-V2-Flash | Xiaomi | 1410 | 1400–1420 | 3.5K | — |
| 148 | Step-3.5-Flash | StepFun | 1408 | 1399–1417 | 4.7K | $0.10 / $0.30 |
| 150 | Qwen3-VL-235B-A22B-Thinking | Alibaba | 1407 | 1382–1433 | 494 | — |
| 152 | Qwen3.5-27B | Alibaba | 1405 | 1392–1418 | 2.2K | $0.27 / $2.16 |
| 153 | MiniMax-M2.7 | MiniMax | 1403 | 1395–1411 | 6.7K | $0.30 / $1.20 |
| 154 | Kimi K2 Preview | Moonshot AI | 1403 | 1382–1424 | 768 | $0.60 / $2.50 |
| 155 | Grok 4.1 Fast | xAI | 1402 | 1393–1411 | 4.2K | — |
| 157 | Claude Haiku 4.5 | Anthropic | 1400 | 1394–1406 | 11.5K | $1 / $5 |
| 158 | GPT-4.1 | OpenAI | 1400 | 1389–1410 | 3.2K | $2 / $8 |
| 159 | Qwen3.5-35B-A3B | Alibaba | 1398 | 1386–1411 | 2.4K | $0.14 / $1 |
| 160 | Qwen3.5-Flash | Alibaba | 1398 | 1388–1407 | 4.8K | $0.065 / $0.26 |
| 162 | GPT-6 Luna | OpenAI | 1396 | 1387–1405 | 5.9K | $0.10 / $0.50 |
| 163 | GPT-6 Sol | OpenAI | 1396 | 1379–1413 | 1.3K | $2 / $10 |
| 164 | Claude Haiku 5.5 | Anthropic | 1395 | 1368–1421 | 487 | $0.10 / $0.50 |
| 165 | Qwen3-235B-A22B | Alibaba | 1394 | 1382–1406 | 2.5K | $0.09 / $0.55 |
| 166 | GPT-5.3 Chat | OpenAI | 1394 | 1382–1406 | 2.6K | — |
| 167 | GLM-4.6V | Z.ai | 1393 | 1353–1433 | 211 | $0.30 / $0.90 |
| 168 | NVIDIA-Nemotron-3-Super-120B-A12B | NVIDIA | 1392 | 1368–1416 | 552 | — |
| 169 | Grok 3 Mini | xAI | 1391 | 1373–1409 | 1.1K | — |
| 170 | Gemini 2.5 Flash-Lite Preview | 1391 | 1381–1401 | 3.2K | $0.10 / $0.40 | |
| 172 | Qwen3-30B-A3B-Instruct | Alibaba | 1387 | 1371–1402 | 1.5K | $0.09 / $0.30 |
| 173 | Muse Glimmer | Meta | 1386 | 1353–1420 | 300 | — |
| 174 | Grok 4.3 | xAI | 1385 | 1377–1394 | 5.8K | $1.25 / $2.50 |
| 175 | Solar Pro 4 | Upstage | 1384 | 1370–1398 | 2K | $0.15 / $0.60 |
| 176 | Mistral Medium 3 | Mistral AI | 1384 | 1371–1397 | 2.1K | $0.40 / $2 |
| 177 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | NVIDIA | 1383 | 1350–1416 | 327 | — |
| 178 | GLM-4.5-Air | Z.ai | 1382 | 1369–1395 | 1.9K | $0.13 / $0.85 |
| 179 | Gemma 3 12B IT | 1381 | 1343–1419 | 217 | $0.05 / $0.15 | |
| 181 | DeepSeek-V3 | DeepSeek | 1379 | 1368–1390 | 2.9K | $0.29 / $1.14 |
| 182 | Gemma 3 27B IT | 1375 | 1364–1387 | 2.7K | $0.08 / $0.35 | |
| 183 | Qwen2.5-Max | Alibaba | 1375 | 1361–1389 | 1.9K | — |
| 184 | GPT-5 mini | OpenAI | 1375 | 1360–1389 | 1.7K | $0.25 / $2 |
| 186 | Claude Opus 4 | Anthropic | 1373 | 1362–1384 | 2.9K | — |
| 187 | Grok 3 Mini Beta | xAI | 1372 | 1356–1388 | 1.4K | — |
| 188 | Hunyuan TurboS | Tencent | 1371 | 1350–1393 | 733 | — |
| 190 | Gemini 2.0 Flash | 1371 | 1359–1383 | 2.6K | — | |
| 191 | o1 | OpenAI | 1368 | 1353–1384 | 1.5K | $15 / $60 |
| 192 | GPT-5.4 nano | OpenAI | 1368 | 1358–1377 | 5K | $0.20 / $1.25 |
| 194 | MiniMax-M2.5 | MiniMax | 1366 | 1355–1377 | 3.3K | $0.30 / $1.20 |
| 195 | Qwen3-Next-80B-A3B-Thinking | Alibaba | 1364 | 1344–1384 | 842 | $0.15 / $1.20 |
| 196 | LLing-flash-2.0 | Ant Group | 1363 | 1336–1391 | 417 | — |
| 197 | GLM-4-Plus | Z.ai | 1362 | 1332–1392 | 367 | — |
| 199 | Amazon Nova 2 Lite | Amazon | 1359 | 1339–1379 | 900 | — |
| 200 | Qwen3-Coder-480B-A35B-Instruct | Alibaba | 1358 | 1343–1373 | 1.6K | — |
| 201 | GLM-4.7-Flash | Z.ai | 1358 | 1338–1377 | 868 | $0.06 / $0.40 |
| 203 | Step-1o Turbo | StepFun | 1355 | 1332–1378 | 654 | — |
| 204 | gpt-oss-120b | OpenAI | 1354 | 1341–1368 | 1.9K | $0.15 / $0.60 |
| 206 | Granite 4.2 30B | IBM | 1352 | 1316–1389 | 255 | — |
| 207 | o4-mini | OpenAI | 1350 | 1339–1362 | 2.7K | $1.10 / $4.40 |
| 208 | Llama 3.3 Nemotron Super 49B v1.5 | NVIDIA | 1349 | 1312–1387 | 233 | — |
| 209 | Qwen-Plus | Alibaba | 1349 | 1320–1377 | 392 | $0.26 / $0.78 |
| 210 | MiniMax-M2 | MiniMax | 1349 | 1321–1376 | 433 | $0.26 / $1.02 |
| 211 | Command A | Cohere | 1348 | 1338–1358 | 3.4K | $0.30 / $1.50 |
| 213 | Trinity Large Thinking | Arcee | 1345 | 1332–1358 | 2.4K | $0.25 / $0.80 |
| 214 | Gemini 2.0 Flash-Lite Preview | 1345 | 1329–1360 | 1.4K | — | |
| 215 | GPT-4.1 mini | OpenAI | 1343 | 1331–1355 | 2.4K | $0.40 / $1.60 |
| 216 | Claude Sonnet 4 | Anthropic | 1342 | 1330–1354 | 2.6K | — |
| 218 | NVIDIA-Nemotron-3-Nano-30B-A3B | NVIDIA | 1341 | 1324–1358 | 1.2K | — |
| 219 | Trinity Large Preview | Arcee | 1341 | 1328–1354 | 2.3K | — |
| 220 | Mistral Small 3.2 | Mistral AI | 1340 | 1323–1357 | 1.1K | — |
| 221 | GLM-4.5V | Z.ai | 1338 | 1304–1372 | 271 | $0.60 / $1.80 |
| 222 | MiniMax-M1 | MiniMax | 1337 | 1325–1350 | 2.3K | $0.55 / $2.20 |
| 223 | Step-3 | StepFun | 1337 | 1309–1366 | 408 | — |
| 225 | Step-2 16K Exp | StepFun | 1337 | 1303–1370 | 278 | — |
| 226 | QwQ-32B | Alibaba | 1336 | 1322–1351 | 1.6K | — |
| 227 | Olmo 3.1 32B Instruct | Ai2 | 1331 | 1312–1351 | 885 | — |
| 228 | o3-mini | OpenAI | 1329 | 1311–1347 | 1K | $1.10 / $4.40 |
| 229 | Gemini 1.5 Pro | 1328 | 1317–1340 | 3.3K | — | |
| 230 | Yi Lightning | 01.AI | 1328 | 1313–1343 | 1.7K | — |
| 231 | Gemma 3 4B IT | 1327 | 1292–1363 | 245 | $0.04 / $0.05 | |
| 232 | Granite 4.2 8B | IBM | 1327 | 1290–1364 | 273 | $0.06 / $0.25 |
| 233 | Granite 4.1 8B | IBM | 1326 | 1286–1366 | 245 | — |
| 234 | Grok 2 | xAI | 1326 | 1315–1337 | 3.8K | — |
| 235 | Qwen3-32B | Alibaba | 1325 | 1293–1357 | 285 | $0.08 / $0.28 |
| 236 | IINTELLECT-3 | — | 1321 | 1293–1350 | 414 | — |
| 237 | Granite 4.2 3B | IBM | 1318 | 1279–1357 | 255 | — |
| 238 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B | NVIDIA | 1317 | 1302–1332 | 1.9K | — |
| 239 | o1-mini | OpenAI | 1315 | 1304–1327 | 3.1K | — |
| 240 | Qwen3-30B-A3B | Alibaba | 1314 | 1300–1328 | 1.8K | $0.12 / $0.50 |
| 241 | GPT-4o | OpenAI | 1314 | 1304–1324 | 6.7K | $2.50 / $10 |
| 243 | Gemma 3n E4B IT | 1309 | 1294–1325 | 1.4K | — | |
| 244 | RRing-flash-2.0 | Ant Group | 1308 | 1279–1337 | 429 | — |
| 245 | Qwen2.5-Plus | Alibaba | 1307 | 1283–1331 | 588 | — |
| 246 | GPT-4o mini | OpenAI | 1305 | 1295–1316 | 3.9K | $0.15 / $0.60 |
| 248 | Gemini Advanced | 1304 | 1290–1319 | 3K | — | |
| 249 | Llama 3.1 405B Instruct | Meta | 1303 | 1292–1315 | 3.4K | — |
| 250 | Llama 3.1 Nemotron 70B Instruct | NVIDIA | 1303 | 1277–1330 | 489 | — |
| 251 | Gemini 1.5 Flash | 1302 | 1289–1315 | 2.2K | — | |
| 253 | Claude 3.7 Sonnet | Anthropic | 1302 | 1289–1314 | 2.5K | — |
| 255 | GPT-4.1 nano | OpenAI | 1300 | 1272–1328 | 382 | $0.10 / $0.40 |
| 256 | AAthene V2 Chat | — | 1299 | 1284–1315 | 1.4K | — |
| 257 | GPT-5 nano | OpenAI | 1299 | 1272–1326 | 470 | $0.05 / $0.40 |
| 258 | AAthene 70B | — | 1293 | 1274–1312 | 1K | — |
| 259 | Grok 2 mini | xAI | 1292 | 1281–1304 | 3K | — |
| 260 | Hunyuan Standard | Tencent | 1290 | 1256–1324 | 288 | — |
| 261 | Olmo 3 32B Think | Ai2 | 1289 | 1260–1319 | 414 | — |
| 262 | Qwen2.5-72B-Instruct | Alibaba | 1288 | 1275–1301 | 2.4K | $0.36 / $0.40 |
| 263 | Olmo 3.1 32B Think | Ai2 | 1287 | 1263–1311 | 620 | — |
| 264 | Llama 4 Maverick 17B 128E Instruct | Meta | 1286 | 1274–1298 | 2.6K | — |
| 265 | Llama 4 Scout 17B 16E Instruct | Meta | 1285 | 1271–1299 | 2K | — |
| 266 | Llama 3.3 70B Instruct | Meta | 1284 | 1273–1295 | 3.2K | $0.10 / $0.32 |
| 267 | Llama 3.1 70B Instruct | Meta | 1284 | 1272–1295 | 3.2K | $0.40 / $0.40 |
| 268 | Qwen-Max | Alibaba | 1283 | 1265–1301 | 1.1K | — |
| 269 | DeepSeek-V2.5 | DeepSeek | 1282 | 1267–1298 | 1.5K | — |
| 270 | Amazon Nova Pro 1.0 | Amazon | 1282 | 1265–1298 | 1.3K | — |
| 271 | Hunyuan Large | Tencent | 1281 | 1245–1317 | 252 | — |
| 272 | gpt-oss-20b | OpenAI | 1280 | 1257–1303 | 678 | $0.018 / $0.09 |
| 274 | Claude 3.5 Sonnet | Anthropic | 1277 | 1268–1286 | 5.5K | — |
| 275 | Mistral Large 2 | Mistral AI | 1276 | 1264–1288 | 2.7K | — |
| 277 | Mistral Large | Mistral AI | 1275 | 1260–1290 | 1.6K | $0.50 / $1.50 |
| 278 | Reka Core | Reka | 1274 | 1245–1302 | 371 | — |
| 279 | Mistral Small 3.1 24B Instruct | Mistral AI | 1270 | 1257–1283 | 2.1K | $0.35 / $0.56 |
| 281 | Gemma 2 9B IT SimPO | 1269 | 1244–1293 | 543 | — | |
| 282 | Command R+ | Cohere | 1268 | 1245–1292 | 592 | $0.15 / $0.60 |
| 284 | GPT-4 Turbo | OpenAI | 1265 | 1254–1276 | 5.4K | $10 / $30 |
| 285 | Claude 3 Opus | Anthropic | 1265 | 1255–1274 | 11.1K | — |
| 286 | Jamba 1.5 Large | AI21 Labs | 1264 | 1237–1291 | 448 | — |
| 288 | Claude 3.5 Haiku | Anthropic | 1259 | 1249–1268 | 4.2K | — |
| 289 | Qwen2.5-Coder-32B-Instruct | Alibaba | 1257 | 1223–1291 | 273 | $0.66 / $1 |
| 290 | Llama 3.1 Nemotron 51B Instruct | NVIDIA | 1252 | 1216–1288 | 230 | — |
| 292 | Aya Expanse 32B | Cohere | 1248 | 1233–1262 | 1.7K | — |
| 293 | Gemini 1.5 Flash-8B | 1248 | 1234–1261 | 2.1K | — | |
| 295 | Nemotron-4 340B Instruct | NVIDIA | 1246 | 1228–1264 | 1.2K | — |
| 296 | Hunyuan Large Vision | Tencent | 1245 | 1214–1277 | 383 | — |
| 298 | GLM-4 | Z.ai | 1244 | 1220–1269 | 556 | — |
| 299 | Gemma 2 27B IT | 1241 | 1231–1252 | 4.5K | $0.65 / $0.65 | |
| 300 | Phi-4 | Microsoft | 1241 | 1225–1258 | 1.3K | $0.07 / $0.14 |
| 301 | Amazon Nova Lite 1.0 | Amazon | 1238 | 1220–1257 | 1.1K | — |
| 302 | Magistral Medium | Mistral AI | 1232 | 1209–1254 | 842 | — |
| 304 | OLMo 2 32B Instruct | Ai2 | 1228 | 1188–1269 | 202 | — |
| 305 | Llama 3 70B Instruct | Meta | 1228 | 1217–1239 | 8.3K | — |
| 306 | Granite-4.0-H-Small | IBM | 1225 | 1190–1261 | 312 | — |
| 307 | Aya Expanse 8B | Cohere | 1225 | 1200–1250 | 551 | — |
| 308 | Jamba 1.5 Mini | AI21 Labs | 1224 | 1199–1249 | 531 | — |
| 309 | Amazon Nova Micro 1.0 | Amazon | 1221 | 1203–1240 | 1.1K | — |
| 310 | Mistral Small 24B Instruct | Mistral AI | 1219 | 1198–1240 | 869 | $0.05 / $0.08 |
| 311 | Reka Flash | Reka | 1217 | 1188–1247 | 414 | — |
| 312 | Gemma 2 9B IT | 1215 | 1204–1227 | 3.2K | — | |
| 313 | Claude 3 Sonnet | Anthropic | 1214 | 1202–1226 | 6.1K | — |
| 314 | Ministral 8B | Mistral AI | 1211 | 1178–1244 | 324 | $0.15 / $0.15 |
| 316 | Llama 3.1 8B Instruct | Meta | 1206 | 1194–1219 | 2.9K | $0.05 / $0.08 |
| 317 | Yi 1.5 34B Chat | 01.AI | 1196 | 1180–1213 | 1.5K | — |
| 318 | Reka Flash 21B | Reka | 1194 | 1174–1215 | 876 | — |
| 319 | Qwen2-72B-Instruct | Alibaba | 1193 | 1179–1207 | 2.3K | — |
| 320 | GPT-4 | OpenAI | 1192 | 1177–1206 | 2.9K | $30 / $60 |
| 321 | Claude 3 Haiku | Anthropic | 1191 | 1181–1202 | 6.8K | — |
| 322 | Qwen1.5-110B-Chat | Alibaba | 1188 | 1171–1205 | 1.5K | — |
| 325 | Qwen1.5-72B-Chat | Alibaba | 1174 | 1158–1189 | 2.1K | — |
| 326 | Granite 3.1 8B Instruct | IBM | 1171 | 1130–1211 | 215 | — |
| 327 | Mistral Medium | Mistral AI | 1170 | 1154–1186 | 1.8K | — |
| 328 | Gemma 2 2B IT | 1170 | 1157–1182 | 2.7K | — | |
| 329 | Llama 3 8B Instruct | Meta | 1168 | 1156–1179 | 5.6K | — |
| 330 | Gemini Pro | 1166 | 1145–1188 | 970 | $2 / $10 | |
| 331 | Mixtral 8x22B Instruct v0.1 | Mistral AI | 1165 | 1152–1179 | 2.8K | — |
| 332 | DeepSeek-Coder-V2 | DeepSeek | 1163 | 1143–1184 | 888 | — |
| 334 | IInternLM2.5 20B Chat | — | 1152 | 1128–1175 | 685 | — |
| 335 | SStarling LM 7B Beta | — | 1151 | 1130–1172 | 878 | — |
| 337 | Qwen1.5-32B-Chat | Alibaba | 1141 | 1123–1159 | 1.2K | — |
| 338 | Yi 34B Chat | 01.AI | 1138 | 1116–1160 | 857 | — |
| 339 | TTulu 2 DPO 70B | — | 1136 | 1106–1166 | 377 | — |
| 340 | ZZephyr ORPO 141B A35B v0.1 | — | 1136 | 1098–1173 | 240 | — |
| 341 | Mixtral 8x7B Instruct v0.1 | Mistral AI | 1132 | 1119–1145 | 4K | — |
| 342 | Phi-3 Medium 4K Instruct | Microsoft | 1131 | 1115–1147 | 1.5K | — |
| 343 | WizardLM 70B | Microsoft | 1129 | 1100–1158 | 434 | — |
| 344 | SStarling LM 7B Alpha | — | 1122 | 1095–1149 | 504 | — |
| 345 | Qwen1.5-14B-Chat | Alibaba | 1119 | 1100–1139 | 1K | — |
| 346 | GPT-3.5 Turbo | OpenAI | 1118 | 1105–1131 | 3.6K | $1 / $2 |
| 347 | Llama 3.2 3B Instruct | Meta | 1115 | 1087–1143 | 506 | $0.051 / $0.34 |
| 348 | Llama 2 70B Chat | Meta | 1114 | 1099–1130 | 2.1K | — |
| 349 | OOpenChat 3.5 | — | 1113 | 1085–1142 | 467 | — |
| 352 | DDBRX Instruct Preview | — | 1105 | 1088–1121 | 1.7K | — |
| 353 | Qwen1.5-7B-Chat | Alibaba | 1103 | 1064–1143 | 230 | — |
| 354 | Phi-3 Small 8K Instruct | Microsoft | 1103 | 1084–1121 | 1.2K | — |
| 355 | WizardLM 13B | Microsoft | 1100 | 1068–1132 | 365 | — |
| 356 | OpenHermes 2.5 Mistral 7B | Mistral AI | 1100 | 1064–1135 | 275 | — |
| 357 | VVicuna 33B | — | 1099 | 1080–1118 | 1.2K | — |
| 358 | Mistral 7B Instruct v0.2 | Mistral AI | 1099 | 1078–1119 | 976 | — |
| 359 | ZZephyr 7B Beta | — | 1095 | 1070–1121 | 621 | — |
| 360 | Gemma 1.1 7B IT | 1094 | 1077–1112 | 1.4K | — | |
| 361 | Snowflake Arctic Instruct | Snowflake | 1091 | 1073–1110 | 1.5K | — |
| 362 | DeepSeek LLM 67B Chat | DeepSeek | 1089 | 1055–1124 | 300 | — |
| 363 | Granite 3.0 8B Instruct | IBM | 1084 | 1051–1117 | 428 | — |
| 364 | Granite 3.0 2B Instruct | IBM | 1084 | 1053–1115 | 435 | — |
| 365 | SOLAR 10.7B Instruct v1.0 | Upstage | 1083 | 1044–1122 | 219 | — |
| 366 | Llama 2 13B Chat | Meta | 1080 | 1059–1101 | 1K | — |
| 367 | Phi-3 Mini 4K Instruct | Microsoft | 1071 | 1052–1090 | 1.1K | — |
| 368 | Llama 3.2 1B Instruct | Meta | 1071 | 1042–1100 | 489 | $0.027 / $0.20 |
| 370 | Llama 2 7B Chat | Meta | 1065 | 1042–1088 | 760 | — |
| 371 | Code Llama 34B Instruct | Meta | 1064 | 1032–1097 | 383 | — |
| 372 | VVicuna 13B | — | 1057 | 1035–1079 | 899 | — |
| 374 | Qwen-14B-Chat | Alibaba | 1051 | 1013–1088 | 274 | — |
| 375 | OLMo 7B Instruct | Ai2 | 1047 | 1012–1081 | 301 | — |
| 376 | Gemma 7B IT | 1044 | 1016–1073 | 462 | — | |
| 377 | VVicuna 7B | — | 1032 | 997–1067 | 305 | — |
| 378 | Mistral 7B Instruct | Mistral AI | 1025 | 995–1054 | 487 | — |
| 379 | Gemma 2B IT | 1020 | 982–1058 | 273 | — | |
| 380 | Qwen1.5-4B-Chat | Alibaba | 1010 | 978–1042 | 390 | — |
| 381 | Phi-3 Mini 128K Instruct | Microsoft | 1006 | 984–1028 | 1K | — |
| 382 | PaLM 2 | 1006 | 974–1037 | 428 | — | |
| 383 | SStripedHyena Nous 7B | — | 1000 | 965–1035 | 309 | — |
| 384 | Gemma 1.1 2B IT | 995 | 967–1023 | 578 | — | |
| 385 | RRWKV-4 Raven 14B | — | 976 | 928–1024 | 190 | — |
| 386 | CChatGLM3 6B | — | 974 | 933–1015 | 268 | — |
| 387 | KKoala 13B | — | 964 | 924–1004 | 248 | — |
| 388 | OOpenAssistant Pythia 12B | — | 922 | 882–963 | 266 | — |
| 389 | AAlpaca 13B | — | 911 | 868–954 | 230 | — |
| 390 | FFastChat-T5 3B | — | 899 | 852–946 | 184 | — |
| 391 | CChatGLM 6B | — | 896 | 849–942 | 195 | — |
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












