Best AI for design
Design here means producing an interface a person prefers, not writing about design.
Aldena runs these models inside your team's projects. See what each one costs.
| rank | model | vendor | composite | pricein / out | benchmarks | elo | elo | elo | elo |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 (max)anthropic/claude-opus-5.5:max | Anthropic | 81.9 | $4.00 / $20.00 | 4 of 4 benchmarks | 1818 | 1869 | 1734 | 1751 |
| 2 | Claude Sonnet 5.5 (xhigh)anthropic/claude-sonnet-5.5:xhigh | Anthropic | 81.6 | $2.00 / $10.00 | 4 of 4 benchmarks | 1773 | 1822 | 1754 | 1744 |
| 3 | GPT-6 Astra (max)openai/gpt-6-astra:max | OpenAI | 80.7 | $10.00 / $50.00 | 4 of 4 benchmarks | 1767 | 1781 | 1784 | 1721 |
| 4 | Claude Fable 5.1 (max)anthropic/claude-fable-5.1:max | Anthropic | 80.1 | $10.00 / $50.00 | 4 of 4 benchmarks | 1744 | 1788 | 1685 | 1724 |
| 5 | GPT-6.1 Sol (max)openai/gpt-6.1-sol:max | OpenAI | 80.1 | $2.00 / $10.00 | 4 of 4 benchmarks | 1743 | 1747 | 1793 | 1697 |
| 6 | Claude Opus 5 (max)anthropic/claude-opus-5:max | Anthropic | 78.3 | $5.00 / $25.00 | 4 of 4 benchmarks | 1691 | 1713 | 1679 | 1664 |
| 7 | Gemini 4 Carbon (high)google/gemini-4-carbon:high | 78.1 | — | 3 of 4 benchmarks | 1768 | 1792 | 1771 | ||
| 8 | GPT-6 Sol (max)openai/gpt-6-sol:max | OpenAI | 76.6 | $2.00 / $10.00 | 4 of 4 benchmarks | 1674 | 1676 | 1678 | 1657 |
| 9 | Claude Sonnet 5.5 (high)anthropic/claude-sonnet-5.5:high | Anthropic | 76.6 | $2.00 / $10.00 | 3 of 4 benchmarks | 1713 | 1748 | 1704 | |
| 10 | Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 | Qwen | 76.1 | $2.00 / $6.00 | 4 of 4 benchmarks | 1677 | 1698 | 1655 | 1637 |
| 11 | Kimi K3.1 Pro (max)moonshotai/kimi-k3.1-pro:max | MoonshotAI | 75.4 | $2.00 / $10.00 | 3 of 4 benchmarks | 1687 | 1699 | 1686 | |
| 12 | DeepSeek V4.1 Flash (max)deepseek/deepseek-v4.1-flash:max | DeepSeek | 75.4 | $0.051 / $0.567 | 4 of 4 benchmarks | 1664 | 1675 | 1696 | 1610 |
| 13 | Muse Spark 1.3 (max)meta/muse-spark-1.3:max | Meta | 74.8 | $1.25 / $4.25 | 4 of 4 benchmarks | 1654 | 1668 | 1653 | 1638 |
| 14 | Gemini 4 Argon (high)google/gemini-4-argon:high | 74.7 | $2.00 / $10.00 | 3 of 4 benchmarks | 1683 | 1703 | 1661 | ||
| 15 | Qwen3.8 Maxqwen/qwen3.8-max | Qwen | 74.4 | — | 4 of 4 benchmarks | 1670 | 1679 | 1626 | 1615 |
| 16 | GPT-6.1 Terra (max)openai/gpt-6.1-terra:max | OpenAI | 74.3 | $1.00 / $5.00 | 3 of 4 benchmarks | 1678 | 1662 | 1744 | |
| 17 | Claude Opus 5 (high)anthropic/claude-opus-5:high | Anthropic | 72.6 | $5.00 / $25.00 | 3 of 4 benchmarks | 1656 | 1678 | 1650 | |
| 18 | Claude Fable 5 (high)anthropic/claude-fable-5:high | Anthropic | 72.1 | $10.00 / $50.00 | 4 of 4 benchmarks | 1625 | 1632 | 1649 | 1621 |
| 19 | Inkling 2 Smallthinkingmachines/inkling-2-small | Thinking Machines | 71.5 | — | 3 of 4 benchmarks | 1649 | 1661 | 1661 | |
| 20 | Kimi K3 (max)moonshotai/kimi-k3:max | MoonshotAI | 71.4 | $0.192 / $16.00 | 4 of 4 benchmarks | 1657 | 1672 | 1641 | 1586 |
| 21 | Muse Wonder (max)meta/muse-wonder:max | Meta | 71.3 | $4.00 / $20.00 | 3 of 4 benchmarks | 1650 | 1650 | 1666 | |
| 22 | Grok 4.7 (xhigh)x-ai/grok-4.7:xhigh | SpaceXAI | 70.6 | $2.00 / $6.00 | 4 of 4 benchmarks | 1640 | 1662 | 1635 | 1591 |
| 23 | MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | Xiaomi | 70.5 | $0.14 / $0.28 | 4 of 4 benchmarks | 1636 | 1653 | 1636 | 1594 |
| 24 | Hy4 previewtencent/hy4-preview | Tencent | 69.6 | $0.7506 / $2.2509 | 3 of 4 benchmarks | 1632 | 1653 | 1624 | |
| 25 | MiMo-V2.6-Proxiaomi/mimo-v2.6-pro | Xiaomi | 69.5 | $0.435 / $0.87 | 4 of 4 benchmarks | 1624 | 1637 | 1623 | 1595 |
| 26 | Grok 4.6 (high)x-ai/grok-4.6:high | SpaceXAI | 69.4 | $2.00 / $6.00 | 4 of 4 benchmarks | 1618 | 1631 | 1600 | 1607 |
| 27 | Muse Spark 1.3 (xhigh)meta/muse-spark-1.3:xhigh | Meta | 69.0 | $1.25 / $4.25 | 4 of 4 benchmarks | 1621 | 1630 | 1619 | 1599 |
| 28 | GPT-5.6 Sol (xhigh)openai/gpt-5.6-sol:xhigh | OpenAI | 68.8 | $4.00 / $20.00 | 4 of 4 benchmarks | 1615 | 1618 | 1612 | 1606 |
| 29 | Qwen3.8 Flash Nextqwen/qwen3.8-flash-next | Qwen | 68.2 | — | 3 of 4 benchmarks | 1624 | 1654 | 1594 | |
| 30 | GLM 5.3 (max)z-ai/glm-5.3:max | Z.ai | 67.7 | $0.0699 / $1.40 | 3 of 4 benchmarks | 1622 | 1643 | 1595 | |
| 31 | Gemini 3.7 Flash (high)google/gemini-3.7-flash:high | 66.4 | $0.75 / $3.75 | 4 of 4 benchmarks | 1588 | 1584 | 1593 | 1600 | |
| 32 | GLM 5.3 Flashz-ai/glm-5.3-flash | Z.ai | 66.0 | $0.15 / $0.50 | 4 of 4 benchmarks | 1609 | 1628 | 1576 | 1582 |
| 33 | Gemini 3.8 Flash (high)google/gemini-3.8-flash:high | 65.6 | $0.75 / $3.75 | 4 of 4 benchmarks | 1584 | 1577 | 1609 | 1594 | |
| 34 | GLM 5.2 (max)z-ai/glm-5.2:max | Z.ai | 65.3 | $0.006 / $6.80 | 3 of 4 benchmarks | 1608 | 1621 | 1567 | |
| 35 | Claude Haiku 5.5 (high)anthropic/claude-haiku-5.5:high | Anthropic | 64.7 | $0.10 / $0.50 | 3 of 4 benchmarks | 1595 | 1615 | 1566 | |
| 36 | Qwen3.8 27Bqwen/qwen3.8-27b | Qwen | 64.4 | $0.15 / $1.875 | 4 of 4 benchmarks | 1591 | 1596 | 1571 | 1574 |
| 37 | MiniMax M3.1 Flashminimax/minimax-m3.1-flash | MiniMax | 63.3 | $0.075 / $0.30 | 3 of 4 benchmarks | 1582 | 1602 | 1557 | |
| 38 | GPT-6 Luna (max)openai/gpt-6-luna:max | OpenAI | 63.1 | $0.10 / $0.50 | 4 of 4 benchmarks | 1577 | 1575 | 1595 | 1567 |
| 39 | DeepSeek V4 Pro 0423 (high)deepseek/deepseek-v4-pro:high | DeepSeek | 63.0 | $0.8837 / $1.7675 | 3 of 4 benchmarks | 1581 | 1586 | 1564 | |
| 40 | DeepSeek V4 Flash 0423 (high)deepseek/deepseek-v4-flash:high | DeepSeek | 62.7 | $0.091 / $0.182 | 3 of 4 benchmarks | 1582 | 1585 | 1559 | |
| 41 | Mistral Large 4mistralai/mistral-large-4-0 | Mistral | 61.3 | $0.70 / $2.10 | 3 of 4 benchmarks | 1563 | 1570 | 1554 | |
| 42 | Claude Opus 4.7 (high)anthropic/claude-opus-4.7:high | Anthropic | 61.1 | $5.00 / $25.00 | 4 of 4 benchmarks | 1557 | 1560 | 1545 | 1579 |
| 43 | Step 5 Preview (high)stepfun/step-5-preview:high | StepFun | 61.0 | $1.00 / $2.70 | 4 of 4 benchmarks | 1572 | 1589 | 1545 | 1551 |
| 44 | Grok 4.5x-ai/grok-4.5 | SpaceXAI | 60.6 | $2.00 / $6.00 | 4 of 4 benchmarks | 1552 | 1556 | 1565 | 1562 |
| 45 | Claude Opus 4.7anthropic/claude-opus-4.7 | Anthropic | 60.1 | $5.00 / $25.00 | 4 of 4 benchmarks | 1555 | 1552 | 1551 | 1562 |
| 46 | Claude Opus 4.8 (high)anthropic/claude-opus-4.8:high | Anthropic | 59.6 | $5.00 / $25.00 | 3 of 4 benchmarks | 1555 | 1556 | 1542 | |
| 47 | Claude Opus 4.6 (high)anthropic/claude-opus-4.6:high | Anthropic | 59.1 | $5.00 / $25.00 | 4 of 4 benchmarks | 1546 | 1539 | 1559 | 1544 |
| 48 | Gemini 3.6 Flash (high)google/gemini-3.6-flash:high | 57.9 | $0.75 / $3.75 | 4 of 4 benchmarks | 1538 | 1527 | 1547 | 1545 | |
| 49 | Muse Spark 1.1meta/muse-spark-1.1 | Meta | 57.0 | $1.25 / $4.25 | 4 of 4 benchmarks | 1542 | 1531 | 1539 | 1539 |
| 50 | Claude Opus 4.8anthropic/claude-opus-4.8 | Anthropic | 57.0 | $5.00 / $25.00 | 3 of 4 benchmarks | 1536 | 1537 | 1525 | |
| 51 | Muse Spark 1.2 (xhigh)meta/muse-spark-1.2:xhigh | Meta | 57.0 | $1.25 / $4.25 | 3 of 4 benchmarks | 1534 | 1525 | 1542 | |
| 52 | Claude Sonnet 5 (high)anthropic/claude-sonnet-5:high | Anthropic | 56.7 | $2.00 / $10.00 | 4 of 4 benchmarks | 1539 | 1539 | 1526 | 1539 |
| 53 | Claude Opus 4.6anthropic/claude-opus-4.6 | Anthropic | 56.5 | $5.00 / $25.00 | 4 of 4 benchmarks | 1537 | 1528 | 1547 | 1538 |
| 54 | Qwen3.7 Maxqwen/qwen3.7-max | Qwen | 54.4 | $1.475 / $4.425 | 3 of 4 benchmarks | 1515 | 1512 | 1514 | |
| 55 | Muse Spark Open (max)meta/muse-spark-open:max | Meta | 54.1 | $1.25 / $4.25 | 3 of 4 benchmarks | 1528 | 1526 | 1476 | |
| 56 | GPT-5.6 Terra (xhigh)openai/gpt-5.6-terra:xhigh | OpenAI | 54.0 | $2.00 / $12.00 | 4 of 4 benchmarks | 1520 | 1511 | 1523 | 1539 |
| 57 | Claude Sonnet 4.6anthropic/claude-sonnet-4.6 | Anthropic | 53.8 | $3.00 / $15.00 | 4 of 4 benchmarks | 1522 | 1511 | 1526 | 1529 |
| 58 | GPT-5.5 (xhigh)openai/gpt-5.5:xhigh | OpenAI | 53.5 | $5.00 / $30.00 | 4 of 4 benchmarks | 1512 | 1505 | 1543 | 1531 |
| 59 | GLM 5.1z-ai/glm-5.1 | Z.ai | 52.7 | $1.40 / $4.40 | 3 of 4 benchmarks | 1508 | 1504 | 1510 | |
| 60 | Hy3tencent/hy3 | Tencent | 52.3 | $0.0825 / $0.33 | 3 of 4 benchmarks | 1506 | 1507 | 1490 | |
| 61 | GPT-5.6 Luna (xhigh)openai/gpt-5.6-luna:xhigh | OpenAI | 51.9 | $0.20 / $1.20 | 4 of 4 benchmarks | 1519 | 1508 | 1522 | 1517 |
| 62 | Claude Opus 4.5 (high 32K)anthropic/claude-opus-4.5:high-32k | Anthropic | 51.5 | $5.00 / $25.00 | 3 of 4 benchmarks | 1493 | 1476 | 1510 | |
| 63 | Seed 2.1 Pro Previewbytedance/seed-2.1-pro-preview | ByteDance | 50.9 | — | 4 of 4 benchmarks | 1519 | 1515 | 1490 | 1505 |
| 64 | GPT-5.5 (high)openai/gpt-5.5:high | OpenAI | 50.7 | $5.00 / $30.00 | 4 of 4 benchmarks | 1487 | 1477 | 1534 | 1519 |
| 65 | Qwen3.6 Max Previewqwen/qwen3.6-max-preview | Qwen | 50.4 | — | 3 of 4 benchmarks | 1482 | 1473 | 1492 | |
| 66 | Kimi K2.6moonshotai/kimi-k2.6 | MoonshotAI | 50.3 | $0.65 / $3.41 | 4 of 4 benchmarks | 1509 | 1504 | 1486 | 1522 |
| 67 | Gemini 3.5 Flash (medium)google/gemini-3.5-flash:medium | 49.6 | $1.50 / $9.00 | 4 of 4 benchmarks | 1490 | 1480 | 1522 | 1506 | |
| 68 | Gemini 3.5 Flash (high)google/gemini-3.5-flash:high | 48.9 | $1.50 / $9.00 | 4 of 4 benchmarks | 1500 | 1495 | 1513 | 1500 | |
| 69 | Claude Opus 4.5anthropic/claude-opus-4.5 | Anthropic | 48.8 | $5.00 / $25.00 | 3 of 4 benchmarks | 1469 | 1456 | 1482 | |
| 70 | MiMo-V2.5-Proxiaomi/mimo-v2.5-pro | Xiaomi | 48.6 | $0.48 / $1.80 | 3 of 4 benchmarks | 1479 | 1468 | 1471 | |
| 71 | GPT-5.4 (high)openai/gpt-5.4:high | OpenAI | 48.0 | $2.50 / $15.00 | 3 of 4 benchmarks | 1462 | 1451 | 1474 | |
| 72 | Kimi K2.7 Codemoonshotai/kimi-k2.7-code | MoonshotAI | 46.6 | $0.60 / $3.50 | 4 of 4 benchmarks | 1474 | 1474 | 1454 | 1512 |
| 73 | GPT-5.4 (medium)openai/gpt-5.4:medium | OpenAI | 46.3 | $2.50 / $15.00 | 3 of 4 benchmarks | 1442 | 1427 | 1476 | |
| 74 | GPT-5.5openai/gpt-5.5 | OpenAI | 46.1 | $5.00 / $30.00 | 4 of 4 benchmarks | 1455 | 1444 | 1491 | 1504 |
| 75 | MiniMax M3minimax/minimax-m3 | MiniMax | 45.9 | $0.30 / $1.20 | 4 of 4 benchmarks | 1484 | 1479 | 1460 | 1474 |
| 76 | DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | DeepSeek | 45.7 | $0.8837 / $1.7675 | 3 of 4 benchmarks | 1448 | 1441 | 1434 | |
| 77 | Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | Reflection | 44.9 | $0.30 / $1.00 | 3 of 4 benchmarks | 1438 | 1443 | 1431 | |
| 78 | Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 44.6 | $2.00 / $12.00 | 4 of 4 benchmarks | 1446 | 1438 | 1489 | 1480 | |
| 79 | GPT-5.2openai/gpt-5.2 | OpenAI | 44.4 | $1.75 / $14.00 | 2 of 4 benchmarks | 1420 | 1429 | ||
| 80 | Qwen3.6 Plusqwen/qwen3.6-plus | Qwen | 44.1 | $0.325 / $1.95 | 4 of 4 benchmarks | 1462 | 1453 | 1463 | 1473 |
| 81 | GLM 5z-ai/glm-5 | Z.ai | 44.1 | $1.00 / $3.20 | 3 of 4 benchmarks | 1435 | 1424 | 1449 | |
| 82 | GPT-5 (medium)openai/gpt-5:medium | OpenAI | 43.7 | $1.25 / $10.00 | 2 of 4 benchmarks | 1417 | 1425 | ||
| 83 | Mimo v2 Proxiaomi/mimo-v2-pro | Xiaomi | 43.6 | — | 3 of 4 benchmarks | 1434 | 1425 | 1440 | |
| 84 | MiMo-V2.5xiaomi/mimo-v2.5 | Xiaomi | 43.5 | $0.40 / $2.00 | 3 of 4 benchmarks | 1438 | 1423 | 1429 | |
| 85 | GLM 4.7z-ai/glm-4.7 | Z.ai | 43.5 | $0.60 / $2.20 | 3 of 4 benchmarks | 1435 | 1418 | 1446 | |
| 86 | Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | 41.7 | $0.50 / $3.00 | 4 of 4 benchmarks | 1440 | 1428 | 1444 | 1451 | |
| 87 | Gemini 3 Progoogle/gemini-3-pro | 40.4 | — | 4 of 4 benchmarks | 1441 | 1396 | 1472 | 1441 | |
| 88 | GPT-5.1 (medium)openai/gpt-5.1:medium | OpenAI | 40.4 | $1.25 / $10.00 | 2 of 4 benchmarks | 1397 | 1406 | ||
| 89 | Inklingthinkingmachines/inkling | Thinking Machines | 40.3 | $1.00 / $4.05 | 3 of 4 benchmarks | 1414 | 1404 | 1405 | |
| 90 | Kimi K2.5 (thinking)moonshotai/kimi-k2.5:thinking | MoonshotAI | 39.5 | $0.532 / $3.325 | 4 of 4 benchmarks | 1436 | 1428 | 1427 | 1439 |
| 91 | Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | 39.3 | $0.30 / $2.50 | 3 of 4 benchmarks | 1435 | 1408 | 1449 | ||
| 92 | Claude Opus 4.1anthropic/claude-opus-4.1 | Anthropic | 39.2 | $15.00 / $75.00 | 2 of 4 benchmarks | 1389 | 1397 | ||
| 93 | Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | Qwen | 39.0 | $0.60 / $3.60 | 3 of 4 benchmarks | 1400 | 1387 | 1409 | |
| 94 | GPT-5.4 Mini (high)openai/gpt-5.4-mini:high | OpenAI | 38.4 | $0.75 / $4.50 | 3 of 4 benchmarks | 1398 | 1386 | 1420 | |
| 95 | MiniMax M2.7minimax/minimax-m2.7 | MiniMax | 37.9 | $0.21 / $0.84 | 3 of 4 benchmarks | 1398 | 1387 | 1401 | |
| 96 | GPT-5.3-Codexopenai/gpt-5.3-codex | OpenAI | 37.5 | $1.75 / $14.00 | 4 of 4 benchmarks | 1406 | 1394 | 1421 | 1443 |
| 97 | MiniMax M2.5minimax/minimax-m2.5 | MiniMax | 36.9 | $0.30 / $1.20 | 3 of 4 benchmarks | 1386 | 1373 | 1414 | |
| 98 | Claude Sonnet 4.5 (high 32K)anthropic/claude-sonnet-4.5:high-32k | Anthropic | 36.9 | $3.00 / $15.00 | 3 of 4 benchmarks | 1394 | 1386 | 1398 | |
| 99 | GPT-5.4openai/gpt-5.4 | OpenAI | 36.6 | $2.50 / $15.00 | 4 of 4 benchmarks | 1400 | 1387 | 1424 | 1441 |
| 100 | GPT-5.1 (high)openai/gpt-5.1:high | OpenAI | 35.9 | $1.25 / $10.00 | 1 of 4 benchmarks | 1419 | |||
| 101 | Claude Sonnet 4.5anthropic/claude-sonnet-4.5 | Anthropic | 35.6 | $3.00 / $15.00 | 3 of 4 benchmarks | 1385 | 1382 | 1389 | |
| 102 | MiniMax M2.1minimax/minimax-m2.1 | MiniMax | 35.5 | — | 3 of 4 benchmarks | 1384 | 1365 | 1398 | |
| 103 | Kimi K2.5 Instantmoonshotai/kimi-k2.5-instant | Moonshot AI | 34.9 | — | 4 of 4 benchmarks | 1406 | 1392 | 1411 | 1411 |
| 104 | Inkling Smallthinkingmachines/inkling-small | Thinking Machines | 34.3 | $0.45 / $1.20 | 4 of 4 benchmarks | 1407 | 1396 | 1395 | 1410 |
| 105 | Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl | NVIDIA | 34.2 | $0.15 / $0.47 | 4 of 4 benchmarks | 1399 | 1391 | 1420 | 1391 |
| 106 | Grok 4.20 Beta 0309 (reasoning)x-ai/grok-4.20-beta-0309:reasoning | SpaceXAI | 34.2 | — | 3 of 4 benchmarks | 1376 | 1368 | 1370 | |
| 107 | Gemma 4 31Bgoogle/gemma-4-31b-it | 34.0 | $0.20 / $0.40 | 3 of 4 benchmarks | 1369 | 1361 | 1379 | ||
| 108 | Solar Pro 4upstage/solar-pro4 | Upstage | 33.6 | $0.15 / $0.60 | 3 of 4 benchmarks | 1369 | 1361 | 1371 | |
| 109 | GLM 4.6z-ai/glm-4.6 | Z.ai | 33.4 | $0.50 / $2.00 | 2 of 4 benchmarks | 1342 | 1351 | ||
| 110 | DeepSeek V3.2 (thinking)deepseek/deepseek-v3.2:thinking | DeepSeek | 32.7 | $0.26 / $0.38 | 3 of 4 benchmarks | 1363 | 1350 | 1370 | |
| 111 | GPT-5.1-Codexopenai/gpt-5.1-codex | OpenAI | 32.7 | $1.25 / $10.00 | 2 of 4 benchmarks | 1338 | 1346 | ||
| 112 | Gemini 3 Flash Preview (minimal)google/gemini-3-flash-preview:minimal | 32.2 | $0.50 / $3.00 | 4 of 4 benchmarks | 1384 | 1374 | 1395 | 1431 | |
| 113 | Qwen3.5-27Bqwen/qwen3.5-27b | Qwen | 32.0 | $0.26 / $2.60 | 3 of 4 benchmarks | 1357 | 1345 | 1384 | |
| 114 | GLM 5V Turboz-ai/glm-5v-turbo | Z.ai | 31.9 | $1.20 / $4.00 | 4 of 4 benchmarks | 1399 | 1382 | 1358 | 1427 |
| 115 | Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b | Qwen | 31.6 | $0.26 / $2.08 | 3 of 4 benchmarks | 1360 | 1351 | 1352 | |
| 116 | Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 31.6 | $0.0765 / $0.255 | 3 of 4 benchmarks | 1359 | 1350 | 1362 | ||
| 117 | Hy3 previewtencent/hy3-preview | Tencent | 31.3 | $0.18 / $0.60 | 3 of 4 benchmarks | 1359 | 1350 | 1355 | |
| 118 | Muse Glimmer 30Bmeta/muse-glimmer-30b | Meta | 31.0 | $0.30 / $1.20 | 3 of 4 benchmarks | 1355 | 1347 | 1364 | |
| 119 | MiniMax M2minimax/minimax-m2 | MiniMax | 30.6 | — | 2 of 4 benchmarks | 1299 | 1308 | ||
| 120 | Laguna M.1poolside/laguna-m.1 | Poolside | 29.2 | — | 3 of 4 benchmarks | 1349 | 1338 | 1333 | |
| 121 | DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | DeepSeek | 29.1 | $0.27 / $0.41 | 2 of 4 benchmarks | 1270 | 1279 | ||
| 122 | GPT-5.2-Codexopenai/gpt-5.2-codex | OpenAI | 28.9 | $1.75 / $14.00 | 3 of 4 benchmarks | 1338 | 1329 | 1348 | |
| 123 | Mimo v2 Flashxiaomi/mimo-v2-flash | Xiaomi | 28.5 | — | 3 of 4 benchmarks | 1331 | 1312 | 1353 | |
| 124 | KAT-Coder-Pro V1kwaipilot/kat-coder-pro-v1 | Kwaipilot | 28.4 | — | 2 of 4 benchmarks | 1257 | 1266 | ||
| 125 | Grok 4.3x-ai/grok-4.3 | SpaceXAI | 27.9 | $1.25 / $2.50 | 4 of 4 benchmarks | 1357 | 1352 | 1367 | 1375 |
| 126 | Claude Haiku 4.5anthropic/claude-haiku-4.5 | Anthropic | 27.6 | $1.00 / $5.00 | 3 of 4 benchmarks | 1330 | 1325 | 1318 | |
| 127 | GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini | OpenAI | 27.5 | $0.25 / $2.00 | 2 of 4 benchmarks | 1245 | 1253 | ||
| 128 | DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek | 27.4 | $0.26 / $0.38 | 3 of 4 benchmarks | 1326 | 1333 | 1306 | |
| 129 | Kimi K2 Thinking Turbomoonshotai/kimi-k2-thinking-turbo | Moonshot AI | 27.3 | — | 3 of 4 benchmarks | 1322 | 1313 | 1325 | |
| 130 | Grok 4.1 (thinking)x-ai/grok-4.1:thinking | SpaceXAI | 25.8 | — | 2 of 4 benchmarks | 1217 | 1226 | ||
| 131 | Mimo v2 Flash (thinking)xiaomi/mimo-v2-flash:thinking | Xiaomi | 25.7 | — | 3 of 4 benchmarks | 1292 | 1228 | 1344 | |
| 132 | Laguna XS.2poolside/laguna-xs.2 | Poolside | 25.6 | — | 3 of 4 benchmarks | 1303 | 1295 | 1285 | |
| 133 | Mistral Medium 3.5mistralai/mistral-medium-3-5 | Mistral | 25.5 | $1.50 / $7.50 | 3 of 4 benchmarks | 1262 | 1252 | 1308 | |
| 134 | GPT-5.1openai/gpt-5.1 | OpenAI | 25.2 | $1.25 / $10.00 | 4 of 4 benchmarks | 1342 | 1307 | 1364 | 1349 |
| 135 | Qwen3 Coder 480B A35b Instructqwen/qwen3-coder-480b-a35b-instruct | Qwen | 25.2 | — | 3 of 4 benchmarks | 1275 | 1258 | 1286 | |
| 136 | Grok Code Fast 1x-ai/grok-code-fast-1 | SpaceXAI | 24.4 | — | 2 of 4 benchmarks | 1164 | 1171 | ||
| 137 | Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | Qwen | 24.3 | $0.14 / $1.00 | 3 of 4 benchmarks | 1253 | 1236 | 1304 | |
| 138 | Grok 4 Fast (reasoning)x-ai/grok-4-fast:reasoning | SpaceXAI | 24.1 | — | 2 of 4 benchmarks | 1162 | 1170 | ||
| 139 | Devstral Medium 2507mistralai/devstral-medium-2507 | Mistral AI | 23.7 | — | 2 of 4 benchmarks | 1072 | 1078 | ||
| 140 | Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | Qwen | 23.6 | $0.065 / $0.26 | 3 of 4 benchmarks | 1244 | 1229 | 1290 | |
| 141 | Grok 4.1 Fast (reasoning)x-ai/grok-4-1-fast:reasoning | SpaceXAI | 22.3 | — | 3 of 4 benchmarks | 1242 | 1221 | 1254 | |
| 142 | Mistral Large 3mistralai/mistral-large-3 | Mistral AI | 22.3 | — | 3 of 4 benchmarks | 1233 | 1241 | 1362 | |
| 143 | Trinity Large Thinkingarcee-ai/trinity-large-thinking | Arcee AI | 22.1 | — | 3 of 4 benchmarks | 1236 | 1230 | 1232 | |
| 144 | Gemini 2.5 Progoogle/gemini-2.5-pro | 21.1 | $1.25 / $10.00 | 3 of 4 benchmarks | 1228 | 1236 | 1285 | ||
| 145 | Granite 4.1 8Bibm-granite/granite-4.1-8b | IBM | 20.4 | — | 3 of 4 benchmarks | 1193 | 1180 | 1208 | |
| 146 | Devstral 2 2512mistralai/devstral-2512 | Mistral | 20.4 | $0.40 / $2.00 | 3 of 4 benchmarks | 1196 | 1147 | 1217 | |
| 147 | Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | 20.2 | $0.25 / $1.50 | 4 of 4 benchmarks | 1256 | 1244 | 1275 | 1338 | |
| 148 | Mercury 2inception/mercury-2 | Inception | 20.0 | — | 3 of 4 benchmarks | 1171 | 1160 | 1199 |
How this ranks
Every benchmark value becomes a percentile among the models that have it, so accuracy scores, Elo ratings and word error rates compare without hand-tuned scaling. Metrics where lower is better are inverted first. Raw values are never summed or averaged across benchmarks. A model's mean percentile is then shrunk toward the mean of the models that were broadly benchmarked, so a model tested twice cannot outrank a broadly tested one on two lucky results. Turning a data source off runs that same ranking code again in your browser over the sources you left on.
A model scored on fewer than 2 of the 4 ranked benchmarks in this category still ranks here, on the benchmarks it does have, and its row carries a partial coverage mark. On an equal score it sits under the model that earned the same number across more of the board.
Data sources
Turn a source off to drop every benchmark it feeds and re-rank the board in your browser. Your choice follows you across the leaderboard pages.
- LMArenaCC BY 4.0
Arena ratings by LMArena, from the public leaderboard dataset.