LMArena Math leaderboard
LMArena’s text votes on math prompts. Gemini 4 Argon leads with a rating of 1538.
- Models
- 339
- 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 | 1514–1562 | 577 | $2 / $10 | |
| 2 | Claude Opus 5 | Anthropic | 1533 | 1518–1548 | 1.7K | $5 / $25 |
| 3 | Claude Fable 5.1 | Anthropic | 1532 | 1512–1553 | 796 | $10 / $50 |
| 4 | Gemini 3.8 Flash | 1532 | 1519–1545 | 2.3K | $0.82 / $4.13 | |
| 6 | Claude Opus 5.5 | Anthropic | 1518 | 1493–1543 | 535 | $4 / $20 |
| 7 | Claude Opus 4.6 | Anthropic | 1518 | 1508–1527 | 4.3K | $5 / $25 |
| 8 | Claude Fable 5 | Anthropic | 1516 | 1504–1529 | 2.2K | $10 / $50 |
| 10 | Gemini 3.7 Flash | 1510 | 1495–1525 | 1.6K | $0.75 / $3.75 | |
| 11 | Gemini 3.6 Flash | 1507 | 1493–1521 | 1.8K | $0.75 / $3.75 | |
| 12 | Gemini 3.5 Flash | 1504 | 1492–1517 | 2.4K | $1.50 / $9 | |
| 13 | Muse Spark 1.3 | Meta | 1502 | 1484–1521 | 1K | $1.25 / $4.25 |
| 14 | GLM-5.3-Flash | Z.ai | 1502 | 1488–1516 | 1.9K | $0.15 / $0.50 |
| 15 | Qwen3.8-Max | Alibaba | 1501 | 1486–1516 | 1.5K | $2 / $6 |
| 16 | MiMo-V2.6-Pro | Xiaomi | 1500 | 1460–1540 | 215 | $0.43 / $0.87 |
| 17 | Claude Opus 4.7 | Anthropic | 1498 | 1488–1509 | 3.3K | $5 / $25 |
| 18 | Claude Sonnet 5.5 | Anthropic | 1498 | 1471–1525 | 455 | $2 / $10 |
| 19 | GLM-5.3 | Z.ai | 1498 | 1480–1515 | 1.1K | $0.079 / $1.40 |
| 20 | Kimi K3 | Moonshot AI | 1493 | 1478–1507 | 1.6K | $0.24 / $11 |
| 21 | GPT-6.1 Sol | OpenAI | 1490 | 1464–1516 | 448 | $2 / $10 |
| 23 | Qwen3.7-Max-Preview | Alibaba | 1488 | 1450–1526 | 233 | $1.48 / $4.42 |
| 24 | GPT-5.4 | OpenAI | 1488 | 1477–1498 | 3.4K | $2.50 / $15 |
| 25 | GPT-5.5 | OpenAI | 1487 | 1477–1498 | 3.5K | $5 / $30 |
| 27 | Claude Opus 4.8 | Anthropic | 1486 | 1475–1497 | 3K | $5 / $25 |
| 28 | Gemini 3.1 Pro Preview | 1486 | 1478–1493 | 6.8K | $2 / $12 | |
| 29 | GLM-5.2 | Z.ai | 1485 | 1472–1497 | 2.4K | $0.034 / $7 |
| 30 | Muse Wonder | Meta | 1484 | 1453–1515 | 320 | $4 / $20 |
| 31 | Muse Spark 1.2 | Meta | 1483 | 1459–1508 | 547 | $1.25 / $4.25 |
| 32 | ERNIE 5.1 | Baidu | 1482 | 1468–1495 | 2K | — |
| 33 | Muse Spark 1.1 | Meta | 1481 | 1468–1494 | 2.2K | $1.25 / $4.25 |
| 34 | IInkling | Thinky | 1481 | 1468–1494 | 2K | $1 / $4.05 |
| 35 | MiMo-V2.5-Pro | Xiaomi | 1480 | 1470–1490 | 3.7K | $0.30 / $0.61 |
| 37 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 1479 | 1458–1500 | 733 | $0.15 / $0.60 |
| 38 | Gemini 3 Pro | 1476 | 1465–1487 | 2.8K | — | |
| 39 | Hy3 | Tencent | 1476 | 1454–1498 | 703 | $0.083 / $0.33 |
| 40 | Kimi K2.6 | Moonshot AI | 1474 | 1461–1487 | 2.1K | $0.65 / $3.41 |
| 41 | Qwen3.5-Max-Preview | Alibaba | 1474 | 1458–1490 | 1.4K | — |
| 42 | GLM-5.1 | Z.ai | 1474 | 1463–1485 | 3.2K | $1.40 / $4.40 |
| 43 | GPT-5.6 Sol | OpenAI | 1473 | 1460–1487 | 2K | $4 / $20 |
| 44 | Gemini 3 Flash | 1473 | 1460–1486 | 2.1K | $0.50 / $3 | |
| 46 | Kimi K2.5 | Moonshot AI | 1470 | 1461–1479 | 4.2K | $0.50 / $2.50 |
| 47 | Gemma 4 26B A4B | 1470 | 1442–1497 | 390 | $0.068 / $0.23 | |
| 48 | MiMo-V2.6-Flash | Xiaomi | 1470 | 1449–1491 | 733 | $0.14 / $0.28 |
| 49 | Claude Sonnet 5 | Anthropic | 1467 | 1455–1480 | 2.4K | $2 / $10 |
| 50 | Qwen3.7-Plus | Alibaba | 1467 | 1454–1481 | 1.9K | $0.32 / $1.28 |
| 51 | Mistral Large 4 | Mistral AI | 1467 | 1442–1491 | 547 | $1.36 / $4.18 |
| 52 | GPT-5.6 Terra | OpenAI | 1466 | 1453–1479 | 2.1K | $2 / $12 |
| 53 | GPT-6 Astra | OpenAI | 1466 | 1445–1487 | 747 | $10 / $50 |
| 54 | Qwen3.6-Max-Preview | Alibaba | 1465 | 1436–1494 | 378 | — |
| 55 | Gemma 4 31B | 1464 | 1438–1491 | 430 | $0.20 / $0.40 | |
| 56 | Claude Opus 4.5 | Anthropic | 1463 | 1451–1475 | 2.3K | $5 / $25 |
| 57 | Claude Sonnet 4.6 | Anthropic | 1463 | 1453–1473 | 3.8K | $3 / $15 |
| 58 | Grok 4.5 | xAI | 1460 | 1446–1474 | 1.8K | $2 / $6 |
| 59 | BBeam 1.0 501B A23B | Reflection AI | 1460 | 1424–1496 | 237 | $0.25 / $1 |
| 60 | GPT-5.6 Luna | OpenAI | 1459 | 1446–1473 | 1.9K | $0.20 / $1.20 |
| 61 | IInkling-Small | Thinky | 1459 | 1444–1474 | 1.6K | $0.45 / $1.20 |
| 64 | NVIDIA-Nemotron-3-Ultra-550B-A55B | NVIDIA | 1457 | 1433–1481 | 580 | — |
| 65 | Muse Spark | Meta | 1456 | 1436–1475 | 891 | — |
| 66 | Qwen3.8-27B | Alibaba | 1456 | 1439–1472 | 1.3K | $0.20 / $2.50 |
| 67 | Grok 4.20 Beta | xAI | 1455 | 1445–1466 | 3.5K | — |
| 68 | DeepSeek-V4-Pro | DeepSeek | 1455 | 1443–1466 | 2.7K | $0.66 / $1.98 |
| 69 | Qwen3.5-397B-A17B | Alibaba | 1454 | 1445–1462 | 5.3K | $0.50 / $3.60 |
| 70 | Step 5 Preview | StepFun | 1454 | 1428–1479 | 499 | $1 / $2.70 |
| 71 | Qwen3.6-Plus | Alibaba | 1450 | 1438–1461 | 2.7K | $0.33 / $1.95 |
| 72 | Gemini 2.5 Pro | 1450 | 1443–1456 | 7.8K | $1.25 / $10 | |
| 73 | Claude Sonnet 4.5 | Anthropic | 1449 | 1440–1457 | 5.1K | $3 / $15 |
| 75 | MiMo-V2-Pro | Xiaomi | 1447 | 1433–1462 | 1.7K | — |
| 76 | GPT-5.1 | OpenAI | 1446 | 1435–1458 | 2.6K | $1.25 / $10 |
| 77 | Qwen3-Max-Preview | Alibaba | 1446 | 1431–1461 | 1.5K | — |
| 80 | GLM-5V-Turbo | Z.ai | 1442 | 1417–1467 | 486 | $1.20 / $4 |
| 81 | LongCat-Flash-Chat Exp | Meituan | 1441 | 1420–1463 | 686 | — |
| 82 | Grok 4.20 Multi-Agent Beta | xAI | 1441 | 1430–1451 | 3.4K | — |
| 84 | Qwen3-Next-80B-A3B-Instruct | Alibaba | 1440 | 1424–1457 | 1.2K | $0.09 / $1.10 |
| 85 | GLM-5 | Z.ai | 1440 | 1426–1454 | 1.7K | $1 / $3.20 |
| 86 | GPT-5.2 | OpenAI | 1440 | 1429–1450 | 3.1K | $1.75 / $14 |
| 87 | Dola Seed 2.0 Pro | ByteDance | 1439 | 1430–1448 | 4.3K | — |
| 88 | amazon-nova-experimental-chat | Amazon | 1437 | 1399–1476 | 209 | — |
| 89 | MiMo-V2.5 | Xiaomi | 1437 | 1425–1449 | 2.5K | $0.12 / $0.24 |
| 90 | ERNIE 5.0 | Baidu | 1436 | 1424–1449 | 2.3K | — |
| 92 | DeepSeek-V3.2-Exp | DeepSeek | 1435 | 1425–1446 | 3.1K | $0.28 / $0.42 |
| 93 | GPT-5.2 Chat | OpenAI | 1435 | 1422–1448 | 2.2K | $1.75 / $14 |
| 94 | Gemini 3.5 Flash-Lite | 1435 | 1420–1449 | 1.6K | $0.30 / $2.50 | |
| 95 | Mistral Medium 3.5 | Mistral AI | 1432 | 1408–1457 | 567 | $1.50 / $7.50 |
| 97 | Grok 4.20 Beta 1 | xAI | 1432 | 1418–1447 | 1.7K | — |
| 98 | GLM-4.6 | Z.ai | 1432 | 1419–1445 | 2.2K | $0.55 / $2.20 |
| 99 | Qwen3-235B-A22B-Instruct | Alibaba | 1432 | 1424–1439 | 6.1K | $0.09 / $0.55 |
| 100 | Qwen3.5-122B-A10B | Alibaba | 1431 | 1418–1445 | 1.8K | $0.40 / $3.20 |
| 101 | MiMo-V2-Omni | Xiaomi | 1431 | 1412–1450 | 984 | — |
| 102 | Claude Opus 4.1 | Anthropic | 1431 | 1421–1442 | 3.1K | $15 / $75 |
| 104 | Kimi K2 Thinking Turbo | Moonshot AI | 1429 | 1420–1439 | 3.9K | — |
| 105 | Qwen3.5-27B | Alibaba | 1429 | 1415–1443 | 1.7K | $0.27 / $2.16 |
| 106 | MiniMax-M3 | MiniMax | 1429 | 1418–1439 | 3.4K | $0.30 / $1.20 |
| 107 | Gemini 3.1 Flash-Lite Preview | 1428 | 1418–1438 | 3.6K | $0.25 / $1.50 | |
| 108 | GLM-4.5 | Z.ai | 1427 | 1412–1443 | 1.4K | $0.60 / $2.20 |
| 109 | o3 | OpenAI | 1426 | 1416–1436 | 3.7K | $2 / $8 |
| 110 | DeepSeek-V4-Flash | DeepSeek | 1426 | 1414–1438 | 2.7K | $0.042 / $0.18 |
| 113 | Qwen3-VL-235B-A22B-Instruct | Alibaba | 1425 | 1403–1448 | 699 | $0.21 / $1.90 |
| 115 | GLM-4.7 | Z.ai | 1424 | 1404–1444 | 738 | $0.54 / $1.98 |
| 116 | Grok 4 | xAI | 1422 | 1410–1435 | 2.3K | — |
| 120 | Grok 4.1 | xAI | 1422 | 1412–1431 | 3.9K | — |
| 122 | MiniMax-M2.7 | MiniMax | 1421 | 1412–1431 | 4.4K | $0.30 / $1.20 |
| 123 | GPT-5.5 Instant | OpenAI | 1420 | 1404–1435 | 1.5K | — |
| 124 | DeepSeek-V3.1 | DeepSeek | 1419 | 1401–1438 | 980 | $0.25 / $0.95 |
| 126 | Grok 4 Fast | xAI | 1419 | 1389–1448 | 380 | — |
| 127 | GPT-5.4 mini | OpenAI | 1418 | 1408–1429 | 3.4K | $0.75 / $4.50 |
| 130 | Solar Pro 4 | Upstage | 1417 | 1400–1434 | 1.2K | $0.15 / $0.60 |
| 131 | Grok 4.6 | xAI | 1416 | 1402–1431 | 1.6K | $2 / $6 |
| 133 | Muse Glimmer | Meta | 1416 | 1377–1455 | 226 | — |
| 134 | Gemini 2.5 Flash | 1416 | 1403–1429 | 2K | $0.30 / $2.50 | |
| 136 | Mistral Large 3 | Mistral AI | 1414 | 1405–1423 | 5K | $0.50 / $1.50 |
| 137 | Hunyuan T1 | Tencent | 1414 | 1375–1452 | 233 | — |
| 138 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | NVIDIA | 1413 | 1376–1450 | 237 | — |
| 139 | Claude Haiku 5.5 | Anthropic | 1413 | 1383–1443 | 344 | $0.10 / $0.50 |
| 140 | Grok 4.7 | xAI | 1413 | 1392–1434 | 760 | $2 / $6 |
| 141 | Qwen3-235B-A22B-Thinking | Alibaba | 1412 | 1388–1437 | 479 | $0.45 / $3.50 |
| 142 | GPT-4.5 Preview | OpenAI | 1412 | 1397–1427 | 1.4K | — |
| 144 | Qwen3-VL-235B-A22B-Thinking | Alibaba | 1410 | 1382–1439 | 423 | — |
| 146 | GPT-6 Luna | OpenAI | 1410 | 1399–1420 | 4K | $0.10 / $0.50 |
| 148 | Mistral Medium 3.1 | Mistral AI | 1408 | 1401–1416 | 6K | $0.40 / $2 |
| 149 | Step-3.5-Flash | StepFun | 1408 | 1398–1419 | 3.4K | $0.10 / $0.30 |
| 150 | Grok 4.1 Fast | xAI | 1408 | 1398–1418 | 3.6K | — |
| 151 | Qwen3.5-Flash | Alibaba | 1407 | 1397–1418 | 3.4K | $0.065 / $0.26 |
| 152 | GPT-5 Chat | OpenAI | 1407 | 1393–1421 | 1.8K | — |
| 153 | ChatGPT-4o Latest | OpenAI | 1407 | 1399–1415 | 5.8K | — |
| 154 | GPT-6 Sol | OpenAI | 1406 | 1385–1426 | 827 | $2 / $10 |
| 155 | GPT-5.4 nano | OpenAI | 1406 | 1395–1417 | 3.3K | $0.20 / $1.25 |
| 158 | Qwen3.5-35B-A3B | Alibaba | 1404 | 1391–1418 | 1.9K | $0.14 / $1 |
| 160 | DeepSeek-V3.1-Terminus | DeepSeek | 1402 | 1363–1440 | 216 | $0.27 / $1 |
| 161 | DeepSeek-R1 | DeepSeek | 1400 | 1380–1420 | 861 | $0.50 / $2.15 |
| 162 | Qwen3-32B | Alibaba | 1399 | 1369–1429 | 316 | $0.08 / $0.28 |
| 163 | GPT-5 | OpenAI | 1398 | 1385–1412 | 1.9K | $1.25 / $10 |
| 164 | Qwen3-Next-80B-A3B-Thinking | Alibaba | 1398 | 1379–1418 | 821 | $0.15 / $1.20 |
| 165 | Claude Haiku 4.5 | Anthropic | 1398 | 1391–1405 | 8.5K | $1 / $5 |
| 166 | Kimi K2 Preview | Moonshot AI | 1397 | 1376–1418 | 754 | $0.60 / $2.50 |
| 167 | Qwen3-235B-A22B | Alibaba | 1397 | 1385–1409 | 2.4K | $0.09 / $0.55 |
| 168 | MiniMax-M2.1 Preview | MiniMax | 1396 | 1378–1414 | 1K | $0.30 / $1.20 |
| 169 | o3-mini | OpenAI | 1396 | 1383–1409 | 1.9K | $1.10 / $4.40 |
| 170 | MiMo-V2-Flash | Xiaomi | 1396 | 1385–1407 | 3K | — |
| 171 | GLM-4.5-Air | Z.ai | 1396 | 1381–1410 | 1.5K | $0.13 / $0.85 |
| 173 | Qwen3-30B-A3B-Instruct | Alibaba | 1395 | 1379–1410 | 1.4K | $0.09 / $0.30 |
| 175 | Llama 3.3 Nemotron Super 49B v1.5 | NVIDIA | 1392 | 1354–1431 | 194 | — |
| 176 | Claude Opus 4 | Anthropic | 1391 | 1378–1403 | 2.2K | — |
| 177 | Grok 3 Preview | xAI | 1391 | 1380–1402 | 2.7K | — |
| 178 | o4-mini | OpenAI | 1389 | 1379–1400 | 2.9K | $1.10 / $4.40 |
| 179 | GPT-5.3 Chat | OpenAI | 1389 | 1376–1402 | 2.1K | — |
| 180 | gpt-oss-120b | OpenAI | 1389 | 1375–1403 | 1.8K | $0.15 / $0.60 |
| 181 | o1 | OpenAI | 1388 | 1378–1399 | 3K | $15 / $60 |
| 182 | Grok 4.3 | xAI | 1387 | 1376–1398 | 3.4K | $1.25 / $2.50 |
| 183 | Grok 3 Mini | xAI | 1386 | 1367–1404 | 967 | — |
| 184 | NVIDIA-Nemotron-3-Super-120B-A12B | NVIDIA | 1380 | 1356–1405 | 547 | — |
| 185 | GPT-5 mini | OpenAI | 1378 | 1363–1393 | 1.5K | $0.25 / $2 |
| 186 | MiniMax-M2.5 | MiniMax | 1378 | 1366–1390 | 2.6K | $0.30 / $1.20 |
| 188 | Claude Sonnet 4 | Anthropic | 1375 | 1362–1388 | 2K | — |
| 189 | IINTELLECT-3 | — | 1375 | 1344–1405 | 342 | — |
| 191 | Gemini 2.5 Flash-Lite Preview | 1373 | 1362–1384 | 3K | $0.10 / $0.40 | |
| 194 | DeepSeek-V3 | DeepSeek | 1373 | 1362–1383 | 3.2K | $0.29 / $1.14 |
| 195 | Grok 3 Mini Beta | xAI | 1372 | 1358–1387 | 1.5K | — |
| 196 | NVIDIA-Nemotron-3-Nano-30B-A3B | NVIDIA | 1371 | 1353–1389 | 1K | — |
| 197 | GPT-4.1 | OpenAI | 1370 | 1359–1380 | 3.2K | $2 / $8 |
| 198 | Qwen2.5-Max | Alibaba | 1369 | 1359–1379 | 3.3K | — |
| 200 | Step-3 | StepFun | 1367 | 1336–1398 | 349 | — |
| 201 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B | NVIDIA | 1366 | 1347–1385 | 1K | — |
| 202 | Trinity Large Thinking | Arcee | 1365 | 1351–1380 | 1.7K | $0.25 / $0.80 |
| 203 | Qwen3-Coder-480B-A35B-Instruct | Alibaba | 1365 | 1350–1380 | 1.6K | — |
| 204 | LLing-flash-2.0 | Ant Group | 1364 | 1337–1391 | 452 | — |
| 206 | MiniMax-M1 | MiniMax | 1361 | 1347–1374 | 1.8K | $0.55 / $2.20 |
| 207 | Llama 3.1 Nemotron Ultra 253B v1 | NVIDIA | 1360 | 1323–1397 | 209 | — |
| 208 | Hunyuan TurboS | Tencent | 1359 | 1340–1378 | 854 | — |
| 209 | QwQ-32B | Alibaba | 1359 | 1345–1373 | 1.7K | — |
| 211 | Amazon Nova 2 Lite | Amazon | 1359 | 1339–1378 | 861 | — |
| 212 | o1-mini | OpenAI | 1358 | 1350–1366 | 7.5K | — |
| 213 | GLM-4.7-Flash | Z.ai | 1355 | 1335–1376 | 756 | $0.06 / $0.40 |
| 214 | Qwen3-30B-A3B | Alibaba | 1355 | 1341–1368 | 1.7K | $0.12 / $0.50 |
| 215 | GLM-4.5V | Z.ai | 1354 | 1319–1388 | 269 | $0.60 / $1.80 |
| 216 | Mistral Medium 3 | Mistral AI | 1353 | 1341–1365 | 2.2K | $0.40 / $2 |
| 217 | Gemini 2.0 Flash | 1352 | 1343–1361 | 4.1K | — | |
| 218 | MiniMax-M2 | MiniMax | 1351 | 1318–1384 | 320 | $0.26 / $1.02 |
| 219 | RRing-flash-2.0 | Ant Group | 1349 | 1323–1376 | 448 | — |
| 220 | GPT-4.1 mini | OpenAI | 1343 | 1332–1354 | 2.7K | $0.40 / $1.60 |
| 221 | Mistral Small 3.2 | Mistral AI | 1341 | 1324–1358 | 1K | — |
| 222 | Claude 3.7 Sonnet | Anthropic | 1336 | 1325–1347 | 2.8K | — |
| 223 | Trinity Large Preview | Arcee | 1336 | 1322–1350 | 2K | — |
| 224 | Qwen-Plus | Alibaba | 1326 | 1307–1345 | 732 | $0.26 / $0.78 |
| 226 | GPT-5 nano | OpenAI | 1318 | 1292–1345 | 493 | $0.05 / $0.40 |
| 227 | Step-1o Turbo | StepFun | 1318 | 1294–1341 | 563 | — |
| 228 | gpt-oss-20b | OpenAI | 1317 | 1295–1339 | 678 | $0.018 / $0.09 |
| 229 | Olmo 3 32B Think | Ai2 | 1317 | 1285–1348 | 329 | — |
| 230 | Gemini 1.5 Pro | 1315 | 1307–1322 | 7.6K | — | |
| 231 | Granite 4.1 8B | IBM | 1314 | 1276–1352 | 248 | — |
| 232 | Gemma 3 27B IT | 1312 | 1303–1322 | 3.6K | $0.08 / $0.35 | |
| 234 | Gemini 2.0 Flash-Lite Preview | 1309 | 1299–1320 | 2.8K | — | |
| 235 | Gemma 3 12B IT | 1307 | 1281–1334 | 389 | $0.05 / $0.15 | |
| 236 | Claude 3.5 Sonnet | Anthropic | 1307 | 1300–1313 | 10K | — |
| 237 | Olmo 3.1 32B Think | Ai2 | 1305 | 1279–1331 | 478 | — |
| 238 | Step-2 16K Exp | StepFun | 1305 | 1285–1324 | 642 | — |
| 239 | Olmo 3.1 32B Instruct | Ai2 | 1304 | 1282–1327 | 693 | — |
| 241 | AAthene V2 Chat | — | 1300 | 1291–1310 | 3.4K | — |
| 242 | Command A | Cohere | 1300 | 1291–1309 | 4K | $0.30 / $1.50 |
| 243 | Yi Lightning | 01.AI | 1300 | 1290–1309 | 3.9K | — |
| 244 | Llama 4 Maverick 17B 128E Instruct | Meta | 1299 | 1289–1310 | 2.8K | — |
| 245 | Qwen2.5-Plus | Alibaba | 1298 | 1284–1311 | 1.4K | — |
| 247 | DeepSeek-V2.5 | DeepSeek | 1288 | 1272–1305 | 1K | — |
| 248 | GLM-4-Plus | Z.ai | 1287 | 1268–1307 | 721 | — |
| 249 | Llama 4 Scout 17B 16E Instruct | Meta | 1287 | 1274–1300 | 1.9K | — |
| 250 | GPT-4o | OpenAI | 1285 | 1277–1293 | 6.8K | $2.50 / $10 |
| 252 | Grok 2 | xAI | 1283 | 1276–1290 | 9K | — |
| 253 | Qwen2.5-72B-Instruct | Alibaba | 1283 | 1274–1291 | 5.4K | $0.36 / $0.40 |
| 254 | Llama 3.1 405B Instruct | Meta | 1281 | 1274–1289 | 8.5K | — |
| 255 | Hunyuan Large | Tencent | 1281 | 1257–1305 | 497 | — |
| 257 | Qwen-Max | Alibaba | 1275 | 1263–1287 | 2.2K | — |
| 259 | GPT-4.1 nano | OpenAI | 1274 | 1251–1297 | 582 | $0.10 / $0.40 |
| 260 | Hunyuan Standard | Tencent | 1274 | 1250–1298 | 499 | — |
| 261 | Hunyuan Turbo | Tencent | 1273 | 1242–1304 | 243 | — |
| 262 | Claude 3 Opus | Anthropic | 1273 | 1266–1279 | 25.8K | — |
| 263 | Gemini Advanced | 1272 | 1262–1281 | 6.4K | — | |
| 264 | GPT-4 Turbo | OpenAI | 1272 | 1264–1279 | 13.2K | $10 / $30 |
| 265 | Llama 3.1 Nemotron 70B Instruct | NVIDIA | 1271 | 1254–1288 | 1K | — |
| 269 | Gemini 1.5 Flash | 1269 | 1260–1278 | 4.8K | — | |
| 270 | Hunyuan Large Vision | Tencent | 1268 | 1238–1298 | 345 | — |
| 272 | GPT-4o mini | OpenAI | 1267 | 1260–1274 | 9.3K | $0.15 / $0.60 |
| 273 | Llama 3.3 70B Instruct | Meta | 1267 | 1259–1275 | 5.8K | $0.10 / $0.32 |
| 274 | Grok 2 mini | xAI | 1265 | 1257–1273 | 7.3K | — |
| 275 | Mistral Large 2 | Mistral AI | 1262 | 1253–1270 | 6.7K | — |
| 276 | Mistral Large | Mistral AI | 1261 | 1252–1270 | 3.6K | $0.50 / $1.50 |
| 277 | Mistral Small 3.1 24B Instruct | Mistral AI | 1261 | 1248–1274 | 2.1K | $0.35 / $0.56 |
| 278 | Granite-4.0-H-Small | IBM | 1252 | 1221–1284 | 344 | — |
| 279 | Llama 3.1 70B Instruct | Meta | 1252 | 1244–1259 | 7.7K | $0.40 / $0.40 |
| 280 | Amazon Nova Pro 1.0 | Amazon | 1252 | 1242–1262 | 3K | — |
| 281 | Gemma 3n E4B IT | 1251 | 1236–1266 | 1.6K | — | |
| 282 | Qwen2.5-Coder-32B-Instruct | Alibaba | 1251 | 1231–1270 | 725 | $0.66 / $1 |
| 283 | Magistral Medium | Mistral AI | 1250 | 1225–1276 | 551 | — |
| 284 | Phi-4 | Microsoft | 1246 | 1235–1256 | 2.8K | $0.07 / $0.14 |
| 285 | Claude 3.5 Haiku | Anthropic | 1244 | 1236–1251 | 6.3K | — |
| 286 | Llama 3.1 Tulu 3 70B | Ai2 | 1242 | 1217–1266 | 397 | — |
| 287 | DeepSeek-Coder-V2 | DeepSeek | 1241 | 1228–1255 | 1.9K | — |
| 288 | Mistral Small 24B Instruct | Mistral AI | 1240 | 1227–1254 | 1.7K | $0.05 / $0.08 |
| 289 | Gemma 3 4B IT | 1239 | 1211–1267 | 423 | $0.04 / $0.05 | |
| 290 | Qwen2-72B-Instruct | Alibaba | 1235 | 1225–1244 | 4.8K | — |
| 291 | Hunyuan Standard 256K | Tencent | 1235 | 1206–1263 | 361 | — |
| 292 | AAthene 70B | — | 1231 | 1221–1242 | 2.9K | — |
| 293 | GPT-4 | OpenAI | 1230 | 1220–1240 | 7.1K | $30 / $60 |
| 294 | Llama 3.1 Nemotron 51B Instruct | NVIDIA | 1230 | 1208–1252 | 507 | — |
| 296 | Amazon Nova Lite 1.0 | Amazon | 1227 | 1216–1238 | 2.5K | — |
| 297 | Reka Core | Reka | 1222 | 1207–1236 | 1.2K | — |
| 298 | Jamba 1.5 Large | AI21 Labs | 1221 | 1206–1236 | 1.1K | — |
| 299 | GLM-4 | Z.ai | 1218 | 1202–1234 | 1.2K | — |
| 300 | Llama 3 70B Instruct | Meta | 1218 | 1210–1225 | 20.9K | — |
| 302 | Nemotron-4 340B Instruct | NVIDIA | 1216 | 1204–1228 | 2.4K | — |
| 304 | Claude 3 Sonnet | Anthropic | 1213 | 1205–1221 | 13.8K | — |
| 305 | Gemma 2 27B IT | 1212 | 1205–1219 | 10.2K | $0.65 / $0.65 | |
| 306 | OLMo 2 32B Instruct | Ai2 | 1208 | 1179–1236 | 375 | — |
| 307 | Gemini 1.5 Flash-8B | 1207 | 1198–1215 | 5K | — | |
| 308 | Amazon Nova Micro 1.0 | Amazon | 1206 | 1195–1217 | 2.5K | — |
| 310 | Aya Expanse 32B | Cohere | 1200 | 1190–1209 | 3.9K | — |
| 311 | Reka Flash | Reka | 1195 | 1181–1209 | 1.3K | — |
| 312 | Llama 3.1 Tulu 3 8B | Ai2 | 1195 | 1169–1220 | 363 | — |
| 313 | Ministral 8B | Mistral AI | 1188 | 1169–1208 | 683 | $0.15 / $0.15 |
| 314 | Claude 3 Haiku | Anthropic | 1188 | 1181–1196 | 15K | — |
| 315 | Command R+ | Cohere | 1188 | 1174–1202 | 1.5K | $0.15 / $0.60 |
| 316 | Qwen1.5-110B-Chat | Alibaba | 1185 | 1174–1197 | 3.2K | — |
| 317 | Mixtral 8x22B Instruct v0.1 | Mistral AI | 1184 | 1175–1193 | 6.8K | — |
| 318 | Gemma 2 9B IT | 1183 | 1176–1191 | 7.1K | — | |
| 319 | Yi 1.5 34B Chat | 01.AI | 1182 | 1171–1193 | 3K | — |
| 320 | Mistral Medium | Mistral AI | 1180 | 1169–1191 | 4.4K | — |
| 321 | IInternLM2.5 20B Chat | — | 1180 | 1165–1195 | 1.4K | — |
| 322 | Llama 3.1 8B Instruct | Meta | 1179 | 1171–1187 | 7.1K | $0.05 / $0.08 |
| 323 | Phi-3 Medium 4K Instruct | Microsoft | 1173 | 1163–1184 | 3.2K | — |
| 324 | Gemma 2 9B IT SimPO | 1173 | 1158–1188 | 1.3K | — | |
| 325 | Aya Expanse 8B | Cohere | 1168 | 1153–1183 | 1.3K | — |
| 326 | Reka Flash 21B | Reka | 1168 | 1154–1182 | 2K | — |
| 328 | Qwen1.5-72B-Chat | Alibaba | 1164 | 1154–1173 | 5.3K | — |
| 329 | Jamba 1.5 Mini | AI21 Labs | 1160 | 1144–1176 | 1.1K | — |
| 330 | Granite 3.1 2B Instruct | IBM | 1159 | 1133–1185 | 391 | — |
| 332 | Qwen1.5-32B-Chat | Alibaba | 1155 | 1143–1167 | 2.6K | — |
| 334 | Phi-3 Mini 4K Instruct | Microsoft | 1152 | 1138–1166 | 1.6K | — |
| 335 | Granite 3.1 8B Instruct | IBM | 1152 | 1124–1180 | 382 | — |
| 336 | Llama 3 8B Instruct | Meta | 1151 | 1143–1159 | 14.3K | — |
| 337 | Phi-3 Small 8K Instruct | Microsoft | 1151 | 1138–1163 | 2.1K | — |
| 338 | ZZephyr ORPO 141B A35B v0.1 | — | 1148 | 1126–1170 | 589 | — |
| 339 | Mixtral 8x7B Instruct v0.1 | Mistral AI | 1147 | 1139–1156 | 9.7K | — |
| 340 | DDBRX Instruct Preview | — | 1145 | 1134–1157 | 4K | — |
| 341 | Granite 3.0 8B Instruct | IBM | 1143 | 1125–1162 | 873 | — |
| 342 | GPT-3.5 Turbo | OpenAI | 1142 | 1133–1150 | 8.6K | $1 / $2 |
| 344 | Gemma 2 2B IT | 1135 | 1127–1143 | 6.6K | — | |
| 345 | Gemini Pro | 1132 | 1118–1146 | 2.3K | $2 / $10 | |
| 347 | Llama 3.2 3B Instruct | Meta | 1126 | 1110–1142 | 1.1K | $0.051 / $0.34 |
| 348 | Qwen1.5-14B-Chat | Alibaba | 1125 | 1112–1139 | 2.2K | — |
| 349 | SStarling LM 7B Beta | — | 1124 | 1111–1138 | 2K | — |
| 351 | Granite 3.0 2B Instruct | IBM | 1117 | 1098–1136 | 908 | — |
| 352 | WizardLM 70B | Microsoft | 1116 | 1097–1135 | 903 | — |
| 353 | Yi 34B Chat | 01.AI | 1114 | 1100–1127 | 2K | — |
| 355 | Snowflake Arctic Instruct | Snowflake | 1109 | 1097–1120 | 4.8K | — |
| 356 | DeepSeek LLM 67B Chat | DeepSeek | 1108 | 1084–1131 | 576 | — |
| 357 | TTulu 2 DPO 70B | — | 1107 | 1088–1126 | 888 | — |
| 358 | Gemma 1.1 7B IT | 1107 | 1096–1118 | 3K | — | |
| 359 | OOpenChat 3.5 | — | 1107 | 1093–1120 | 1.7K | — |
| 360 | SSmolLM2 1.7B Instruct | — | 1105 | 1072–1138 | 271 | — |
| 361 | OpenHermes 2.5 Mistral 7B | Mistral AI | 1098 | 1078–1118 | 697 | — |
| 362 | Llama 2 70B Chat | Meta | 1091 | 1081–1102 | 4.7K | — |
| 363 | Phi-3 Mini 128K Instruct | Microsoft | 1089 | 1076–1102 | 2.8K | — |
| 364 | Llama 3.2 1B Instruct | Meta | 1086 | 1070–1102 | 1.2K | $0.027 / $0.20 |
| 365 | Mistral 7B Instruct v0.2 | Mistral AI | 1085 | 1073–1098 | 2.6K | — |
| 366 | SStarling LM 7B Alpha | — | 1081 | 1066–1097 | 1.3K | — |
| 367 | Qwen1.5-7B-Chat | Alibaba | 1080 | 1059–1100 | 690 | — |
| 368 | Dolphin 2.2.1 Mistral 7B | Mistral AI | 1077 | 1044–1109 | 219 | — |
| 369 | Llama 2 70B SteerLM Chat | NVIDIA | 1072 | 1045–1098 | 440 | — |
| 371 | VVicuna 33B | — | 1071 | 1058–1083 | 2.7K | — |
| 372 | Qwen-14B-Chat | Alibaba | 1068 | 1044–1091 | 534 | — |
| 373 | Gemma 7B IT | 1066 | 1050–1083 | 1.1K | — | |
| 374 | Llama 2 13B Chat | Meta | 1065 | 1052–1078 | 2.2K | — |
| 375 | SOLAR 10.7B Instruct v1.0 | Upstage | 1064 | 1042–1085 | 604 | — |
| 376 | Nous Hermes 2 Mixtral 8x7B DPO | Nous Research | 1061 | 1039–1082 | 628 | — |
| 377 | Code Llama 34B Instruct | Meta | 1056 | 1037–1076 | 770 | — |
| 378 | PaLM 2 | 1049 | 1030–1068 | 901 | — | |
| 379 | Gemma 1.1 2B IT | 1047 | 1031–1063 | 1.4K | — | |
| 380 | MMPT 30B Chat | — | 1047 | 1013–1080 | 242 | — |
| 381 | Llama 2 7B Chat | Meta | 1042 | 1028–1056 | 1.7K | — |
| 382 | ZZephyr 7B Beta | — | 1041 | 1024–1058 | 1.3K | — |
| 383 | SStripedHyena Nous 7B | — | 1033 | 1013–1053 | 676 | — |
| 384 | GGuanaco 33B | — | 1033 | 1000–1065 | 280 | — |
| 385 | VVicuna 13B | — | 1030 | 1017–1044 | 2.1K | — |
| 386 | Mistral 7B Instruct | Mistral AI | 1027 | 1009–1046 | 974 | — |
| 387 | Qwen1.5-4B-Chat | Alibaba | 1026 | 1008–1044 | 988 | — |
| 388 | OLMo 7B Instruct | Ai2 | 1018 | 999–1037 | 848 | — |
| 389 | WizardLM 13B | Microsoft | 1017 | 997–1038 | 669 | — |
| 390 | Gemma 2B IT | 1009 | 987–1031 | 597 | — | |
| 391 | VVicuna 7B | — | 994 | 972–1015 | 658 | — |
| 392 | CChatGLM3 6B | — | 989 | 966–1012 | 576 | — |
| 393 | GPT4All 13B Snoozy | OpenAI | 941 | 904–978 | 211 | — |
| 394 | KKoala 13B | — | 932 | 911–953 | 751 | — |
| 395 | CChatGLM 6B | — | 926 | 901–951 | 525 | — |
| 396 | RRWKV-4 Raven 14B | — | 922 | 898–946 | 544 | — |
| 397 | MMPT 7B Chat | — | 919 | 894–944 | 471 | — |
| 398 | CChatGLM2 6B | — | 915 | 881–950 | 227 | — |
| 399 | AAlpaca 13B | — | 908 | 886–931 | 652 | — |
| 400 | OOpenAssistant Pythia 12B | — | 892 | 870–914 | 687 | — |
| 401 | DDolly 2.0 12B | — | 871 | 843–899 | 370 | — |
| 402 | FFastChat-T5 3B | — | 862 | 836–887 | 462 | — |
| 403 | SStableLM Tuned Alpha 7B | — | 839 | 811–868 | 353 | — |
| 404 | LLaMA 13B | Meta | 838 | 805–870 | 252 | — |
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













