벤치마크 상세
Arena Text / LMArena
사람이 선호하는 답변: 일반 대화, 글쓰기, 설명력, 한국어처럼 사람이 읽었을 때 좋은 답변
공식 리더보드 보기
텍스트 전체·스타일 보정 조건입니다. 원문 순위의 신뢰구간과 투표수를 보존했습니다. 평점은 백분율이 아니며, 근소한 차이는 확정적인 우열을 뜻하지 않습니다.
모든 공개 결과
모델 검색 · 점수순확인 2026. 09. 07.원문 기준 2026. 09. 03.Text Overall · Style Control ONArena rating (Elo 계열, 높을수록 좋음)
400개 결과원문 ↗
| 순서 | 모델 / 실행 구성 | 점수 | 평가 조건·근거 |
|---|---|---|---|
| 1 | claude-fable-5Anthropic | 1507.16 | 27,189표 · 신뢰구간 1502.2–1512.13 |
| 2 | claude-opus-4-6-highAnthropic | 1504.84 | 72,099표 · 신뢰구간 1501.32–1508.36 |
| 3 | claude-fable-5.1-maxAnthropic | 1504.21 | 2,906표 · 신뢰구간 1493.02–1515.41 |
| 4 | claude-opus-4-7-highAnthropic | 1502.11 | 60,103표 · 신뢰구간 1498.22–1505.99 |
| 5 | muse-spark-1.2 (xHigh)Meta | 1498.99 | 3,240표 · 신뢰구간 1488.5–1509.48 |
| 6 | claude-opus-4-6Anthropic | 1497.57 | 76,015표 · 신뢰구간 1494.15–1501 |
| 7 | claude-opus-4-7Anthropic | 1494.48 | 61,238표 · 신뢰구간 1490.6–1498.35 |
| 8 | gemini-3.8-flash-highGoogle | 1493.85 | 5,125표 · 신뢰구간 1485.29–1502.4 |
| 9 | claude-opus-5-highAnthropic | 1493.33 | 35,174표 · 신뢰구간 1488.76–1497.89 |
| 10 | muse-spark-1.1Meta | 1492.06 | 24,064표 · 신뢰구간 1487.02–1497.1 |
| 11 | gemini-3.7-flash-highGoogle | 1490.93 | 5,682표 · 신뢰구간 1482.75–1499.1 |
| 12 | kimi-k3-maxMoonshot | 1488.67 | 18,090표 · 신뢰구간 1483.21–1494.13 |
| 13 | muse-sparkMeta | 1488.17 | 13,572표 · 신뢰구간 1482.32–1494.01 |
| 14 | claude-opus-5-maxAnthropic | 1487.7 | 17,119표 · 신뢰구간 1481.91–1493.5 |
| 15 | gemini-3.1-pro-previewGoogle | 1486.73 | 102,999표 · 신뢰구간 1483.52–1489.94 |
| 16 | gemini-3-proGoogle | 1485.58 | 40,668표 · 신뢰구간 1481.72–1489.43 |
| 17 | gpt-5.6-sol-xhighOpenAI | 1483.15 | 23,413표 · 신뢰구간 1478.04–1488.26 |
| 18 | claude-opus-4-8-highAnthropic | 1482.31 | 48,727표 · 신뢰구간 1478.06–1486.57 |
| 19 | gpt-5.5-highOpenAI | 1482.09 | 63,547표 · 신뢰구간 1478.24–1485.93 |
| 20 | glm-5.3-maxZ.ai | 1482.04 | 7,668표 · 신뢰구간 1474.74–1489.34 |
| 21 | gemini-3.6-flash-highGoogle | 1480.2 | 22,286표 · 신뢰구간 1475.08–1485.31 |
| 22 | qwen3.8-maxAlibaba | 1479.56 | 13,346표 · 신뢰구간 1473.34–1485.78 |
| 23 | gemini-3.5-flash-highGoogle | 1479.43 | 34,180표 · 신뢰구간 1475.1–1483.77 |
| 24 | gpt-5.5OpenAI | 1477.19 | 64,977표 · 신뢰구간 1473.36–1481.02 |
| 25 | gpt-5.4-highOpenAI | 1476.55 | 60,624표 · 신뢰구간 1472.67–1480.43 |
| 26 | gpt-5.2-chat-latest-20260210OpenAI | 1476.29 | 34,217표 · 신뢰구간 1472.16–1480.43 |
| 27 | gemini-3.5-flash-mediumGoogle | 1475.54 | 32,573표 · 신뢰구간 1470.86–1480.21 |
| 28 | grok-4.20-beta1SpaceXAI | 1474.58 | 26,630표 · 신뢰구간 1469.92–1479.23 |
| 29 | glm-5.3-flashZ.ai | 1474.16 | 4,672표 · 신뢰구간 1465.24–1483.08 |
| 30 | gemini-3-flashGoogle | 1473.83 | 30,244표 · 신뢰구간 1469.41–1478.25 |
| 31 | gpt-5.5-instantOpenAI | 1473.71 | 25,860표 · 신뢰구간 1468.6–1478.83 |
| 32 | qwen3.7-max-previewAlibaba | 1473.62 | 3,710표 · 신뢰구간 1463.62–1483.62 |
| 33 | claude-opus-4-8Anthropic | 1472.85 | 49,404표 · 신뢰구간 1468.57–1477.14 |
| 34 | claude-opus-4-5-20251101-high-32kAnthropic | 1472.84 | 36,269표 · 신뢰구간 1468.93–1476.74 |
| 35 | claude-sonnet-4-6Anthropic | 1472.39 | 66,316표 · 신뢰구간 1468.78–1476 |
| 36 | grok-4.20-beta-0309-reasoningSpaceXAI | 1471.72 | 62,251표 · 신뢰구간 1467.94–1475.5 |
| 37 | glm-5.2-maxZ.ai | 1471.72 | 33,966표 · 신뢰구간 1467–1476.43 |
| 38 | grok-4.5SpaceXAI | 1471.08 | 26,158표 · 신뢰구간 1466.17–1475.99 |
| 39 | grok-4.20-multi-agent-beta-0309SpaceXAI | 1470.46 | 60,820표 · 신뢰구간 1466.66–1474.25 |
| 40 | claude-opus-4-5-20251101Anthropic | 1469.4 | 70,052표 · 신뢰구간 1466.2–1472.6 |
| 41 | mimo-v2.5-proXiaomi | 1468.11 | 57,649표 · 신뢰구간 1464.19–1472.02 |
| 42 | ernie-5.1Baidu | 1468.09 | 37,129표 · 신뢰구간 1463.43–1472.75 |
| 43 | gpt-5.6-terra-xhighOpenAI | 1466.42 | 24,200표 · 신뢰구간 1461.37–1471.47 |
| 44 | glm-5.1Z.ai | 1466.02 | 45,650표 · 신뢰구간 1462.04–1470 |
| 45 | qwen3.5-max-previewAlibaba | 1465.75 | 21,485표 · 신뢰구간 1460.77–1470.72 |
| 46 | gpt-5.4OpenAI | 1465.61 | 63,588표 · 신뢰구간 1461.81–1469.42 |
| 47 | grok-4.1-thinkingSpaceXAI | 1465.46 | 64,198표 · 신뢰구간 1462.22–1468.7 |
| 48 | claude-sonnet-5-highAnthropic | 1462.37 | 31,387표 · 신뢰구간 1457.62–1467.11 |
| 49 | grok-4.6-highSpaceXAI | 1461.15 | 3,453표 · 신뢰구간 1451.01–1471.29 |
| 50 | kimi-k2.6Moonshot | 1460.73 | 37,568표 · 신뢰구간 1456.2–1465.27 |
| 51 | qwen3.6-max-previewAlibaba | 1460.13 | 5,196표 · 신뢰구간 1451.78–1468.49 |
| 52 | deepseek-v4-pro-high-20260813DeepSeek | 1459.61 | 5,557표 · 신뢰구간 1451.43–1467.79 |
| 53 | grok-4.1SpaceXAI | 1459.16 | 66,382표 · 신뢰구간 1455.94–1462.38 |
| 54 | gemini-3-flash (thinking-minimal)Google | 1458.45 | 85,921표 · 신뢰구간 1455.35–1461.56 |
| 55 | deepseek-v4-proDeepSeek | 1457.82 | 54,225표 · 신뢰구간 1453.81–1461.83 |
| 56 | glm-5Z.ai | 1457.77 | 27,647표 · 신뢰구간 1453.42–1462.12 |
| 57 | gemini-3.5-flash-liteGoogle | 1456.93 | 22,122표 · 신뢰구간 1451.72–1462.13 |
| 58 | claude-sonnet-4-5-20250929-high-32kAnthropic | 1456.27 | 81,033표 · 신뢰구간 1453.46–1459.08 |
| 59 | dola-seed-2.0-proBytedance | 1455.8 | 74,277표 · 신뢰구간 1452.3–1459.29 |
| 60 | hy3Tencent | 1455.39 | 6,958표 · 신뢰구간 1447.77–1463 |
| 61 | qwen3.7-plusAlibaba | 1455.29 | 38,121표 · 신뢰구간 1450.8–1459.79 |
| 62 | claude-sonnet-4-5-20250929Anthropic | 1455.14 | 79,668표 · 신뢰구간 1452.23–1458.06 |
| 63 | deepseek-v4-pro-high-previewDeepSeek | 1455.09 | 51,569표 · 신뢰구간 1451.02–1459.17 |
| 64 | gpt-5.1-highOpenAI | 1455.05 | 40,293표 · 신뢰구간 1451.27–1458.83 |
| 65 | gpt-5.6-luna-xhighOpenAI | 1452.6 | 24,740표 · 신뢰구간 1447.58–1457.62 |
| 66 | gemma-4-31bGoogle | 1451.28 | 5,898표 · 신뢰구간 1443.7–1458.86 |
| 67 | kimi-k2.5-thinkingMoonshot | 1450.58 | 70,586표 · 신뢰구간 1447.22–1453.95 |
| 68 | claude-opus-4-1-20250805-thinking-16kAnthropic | 1449.71 | 48,828표 · 신뢰구간 1446.23–1453.18 |
| 69 | gpt-5.3-chat-latestOpenAI | 1449.04 | 32,743표 · 신뢰구간 1444.7–1453.37 |
| 70 | ernie-5.0-preview-1203Baidu | 1448.86 | 9,556표 · 신뢰구간 1442.29–1455.43 |
| 71 | mimo-v2-proXiaomi | 1448.4 | 24,384표 · 신뢰구간 1443.65–1453.15 |
| 72 | gpt-5.4-mini-highOpenAI | 1448.2 | 59,455표 · 신뢰구간 1444.35–1452.05 |
| 73 | claude-opus-4-1-20250805Anthropic | 1447.65 | 75,935표 · 신뢰구간 1444.65–1450.65 |
| 74 | ernie-5.0-0110Baidu | 1446.17 | 34,899표 · 신뢰구간 1442.19–1450.14 |
| 75 | gemini-2.5-proGoogle | 1445.62 | 122,612표 · 신뢰구간 1443.13–1448.12 |
| 76 | gpt-4.5-preview-2025-02-27OpenAI | 1444.54 | 14,547표 · 신뢰구간 1438.83–1450.24 |
| 77 | qwen3.6-plusAlibaba | 1443.74 | 45,357표 · 신뢰구간 1439.5–1447.98 |
| 78 | chatgpt-4o-latest-20250326OpenAI | 1443.14 | 80,696표 · 신뢰구간 1440.31–1445.97 |
| 79 | grok-4.3SpaceXAI | 1442.96 | 65,316표 · 신뢰구간 1439.2–1446.73 |
| 80 | minimax-m3MiniMax | 1442.95 | 44,829표 · 신뢰구간 1438.6–1447.3 |
| 81 | glm-4.7Z.ai | 1441.81 | 11,889표 · 신뢰구간 1435.68–1447.94 |
| 82 | qwen3.5-397b-a17bAlibaba | 1441.11 | 73,640표 · 신뢰구간 1437.73–1444.48 |
| 83 | inklingThinky | 1439.42 | 22,229표 · 신뢰구간 1434.29–1444.56 |
| 84 | gpt-5.1OpenAI | 1438.95 | 43,008표 · 신뢰구간 1435.3–1442.6 |
| 85 | deepseek-v4-flash-high-previewDeepSeek | 1438.47 | 48,691표 · 신뢰구간 1434.26–1442.68 |
| 86 | gemma-4-26b-a4bGoogle | 1438.45 | 5,813표 · 신뢰구간 1430.83–1446.07 |
| 87 | gpt-5.2-highOpenAI | 1437.84 | 47,560표 · 신뢰구간 1434.22–1441.47 |
| 88 | gpt-5.2OpenAI | 1435.91 | 79,070표 · 신뢰구간 1432.66–1439.16 |
| 89 | qwen3.8-27bAlibaba | 1435.89 | 6,913표 · 신뢰구간 1428.35–1443.44 |
| 90 | longcat-flash-chat-2602-expMeituan | 1435.76 | 27,983표 · 신뢰구간 1431.13–1440.38 |
| 91 | deepseek-v4-flashDeepSeek | 1435.75 | 48,950표 · 신뢰구간 1431.6–1439.9 |
| 92 | qwen3-max-previewAlibaba | 1434.62 | 27,194표 · 신뢰구간 1430.09–1439.15 |
| 93 | gpt-5-highOpenAI | 1434.39 | 31,433표 · 신뢰구간 1429.86–1438.92 |
| 94 | mimo-v2.5Xiaomi | 1433.81 | 44,530표 · 신뢰구간 1429.47–1438.15 |
| 95 | glm-5v-turboZ.ai | 1433.13 | 9,361표 · 신뢰구간 1426.41–1439.85 |
| 96 | gemini-3.1-flash-lite-previewGoogle | 1432.49 | 60,474표 · 신뢰구간 1428.76–1436.21 |
| 97 | o3-2025-04-16OpenAI | 1431.36 | 58,583표 · 신뢰구간 1427.71–1435 |
| 98 | kimi-k2.5-instantMoonshot | 1430.96 | 7,998표 · 신뢰구간 1424.31–1437.6 |
| 99 | grok-4-1-fast-reasoningSpaceXAI | 1430.25 | 55,408표 · 신뢰구간 1426.99–1433.51 |
| 100 | kimi-k2-thinking-turboMoonshot | 1430.12 | 61,122표 · 신뢰구간 1426.97–1433.26 |
| 101 | mimo-v2-omniXiaomi | 1429.99 | 19,442표 · 신뢰구간 1424.3–1435.69 |
| 102 | muse-glimmerMeta | 1427.34 | 3,693표 · 신뢰구간 1417.39–1437.3 |
| 103 | mistral-medium-3.5Mistral | 1426.87 | 11,017표 · 신뢰구간 1420.31–1433.43 |
| 104 | gpt-5-chatOpenAI | 1426.71 | 30,974표 · 신뢰구간 1422.4–1431.03 |
| 105 | nvidia-nemotron-3-ultra-550b-a55b-nvfp4Nvidia | 1426.11 | 10,700표 · 신뢰구간 1419.1–1433.13 |
| 106 | amazon-nova-experimental-chat-26-02-10Amazon | 1426 | 3,371표 · 신뢰구간 1416.13–1435.87 |
| 107 | claude-opus-4-20250514-thinking-16kAnthropic | 1425.73 | 35,743표 · 신뢰구간 1421.32–1430.14 |
| 108 | deepseek-v3.2DeepSeek | 1425.25 | 46,493표 · 신뢰구간 1421.69–1428.8 |
| 109 | deepseek-v3.2-exp-thinkingDeepSeek | 1425.24 | 8,910표 · 신뢰구간 1418.65–1431.83 |
| 110 | glm-4.6Z.ai | 1424.84 | 35,068표 · 신뢰구간 1420.91–1428.78 |
| 111 | qwen3-max-2025-09-23Alibaba | 1423.71 | 8,942표 · 신뢰구간 1417.19–1430.22 |
| 112 | qwen3-235b-a22b-instruct-2507Alibaba | 1423.08 | 95,700표 · 신뢰구간 1420.49–1425.67 |
| 113 | deepseek-v3.2-thinkingDeepSeek | 1422.54 | 40,520표 · 신뢰구간 1418.89–1426.18 |
| 114 | deepseek-v3.2-expDeepSeek | 1422.38 | 11,756표 · 신뢰구간 1415.95–1428.81 |
| 115 | deepseek-r1-0528DeepSeek | 1421.34 | 18,092표 · 신뢰구간 1415.66–1427.03 |
| 116 | ernie-5.0-preview-1022Baidu | 1418.88 | 4,663표 · 신뢰구간 1410.06–1427.71 |
| 117 | grok-4-fast-chatSpaceXAI | 1418.26 | 6,336표 · 신뢰구간 1410.45–1426.07 |
| 118 | kimi-k2-0905-previewMoonshot | 1417.9 | 11,569표 · 신뢰구간 1411.37–1424.44 |
| 119 | kimi-k2-0711-previewMoonshot | 1417.62 | 27,033표 · 신뢰구간 1412.71–1422.52 |
| 120 | deepseek-v3.1-terminus-thinkingDeepSeek | 1417.53 | 3,372표 · 신뢰구간 1407.42–1427.64 |
| 121 | deepseek-v3.1DeepSeek | 1417.36 | 14,609표 · 신뢰구간 1411.3–1423.42 |
| 122 | qwen3.5-122b-a10bAlibaba | 1417.15 | 28,376표 · 신뢰구간 1412.77–1421.53 |
| 123 | deepseek-v3.1-thinkingDeepSeek | 1415.97 | 11,463표 · 신뢰구간 1409.3–1422.64 |
| 124 | minimax-m2.7MiniMax | 1415.36 | 65,655표 · 신뢰구간 1411.68–1419.05 |
| 125 | amazon-nova-experimental-chat-26-01-10Amazon | 1414.82 | 3,352표 · 신뢰구간 1404.88–1424.76 |
| 126 | deepseek-v3.1-terminusDeepSeek | 1414.67 | 3,613표 · 신뢰구간 1404.95–1424.38 |
| 127 | gpt-4.1-2025-04-14OpenAI | 1414.41 | 49,930표 · 신뢰구간 1410.68–1418.13 |
| 128 | qwen3-vl-235b-a22b-instructAlibaba | 1413.95 | 11,222표 · 신뢰구간 1407.39–1420.51 |
| 129 | claude-opus-4-20250514Anthropic | 1413.72 | 42,848표 · 신뢰구간 1409.39–1418.06 |
| 130 | mistral-large-3Mistral | 1413.67 | 65,587표 · 신뢰구간 1410.59–1416.74 |
| 131 | claude-haiku-4-5-20251001Anthropic | 1413.18 | 125,243표 · 신뢰구간 1410.63–1415.73 |
| 132 | hunyuan-hy3-previewTencent | 1413.13 | 6,611표 · 신뢰구간 1405.59–1420.67 |
| 133 | grok-3-preview-02-24SpaceXAI | 1411.47 | 32,415표 · 신뢰구간 1407.12–1415.82 |
| 134 | glm-4.5Z.ai | 1411.32 | 23,715표 · 신뢰구간 1406.38–1416.26 |
| 135 | grok-4-0709SpaceXAI | 1410.98 | 39,300표 · 신뢰구간 1407.03–1414.94 |
| 136 | gemini-2.5-flashGoogle | 1409.79 | 122,781표 · 신뢰구간 1407.32–1412.26 |
| 137 | mistral-medium-2508Mistral | 1408.74 | 92,749표 · 신뢰구간 1406.1–1411.38 |
| 138 | qwen3.5-27bAlibaba | 1407.97 | 27,238표 · 신뢰구간 1403.57–1412.37 |
| 139 | Inkling SmallThinky | 1406.66 | 15,183표 · 신뢰구간 1400.84–1412.47 |
| 140 | grok-4-fast-reasoningSpaceXAI | 1404.48 | 17,971표 · 신뢰구간 1399.39–1409.57 |
| 141 | gemini-2.5-flash-preview-09-2025Google | 1403.55 | 32,359표 · 신뢰구간 1399.46–1407.63 |
| 142 | qwen3-235b-a22b-no-thinkingAlibaba | 1402.49 | 37,389표 · 신뢰구간 1397.96–1407.03 |
| 143 | gpt-5.4-nano-highOpenAI | 1402.21 | 58,540표 · 신뢰구간 1398.33–1406.09 |
| 144 | o1-2024-12-17OpenAI | 1401.97 | 27,807표 · 신뢰구간 1397.5–1406.45 |
| 145 | longcat-flash-chatMeituan | 1401.5 | 11,161표 · 신뢰구간 1395.08–1407.92 |
| 146 | claude-sonnet-4-20250514-thinking-32kAnthropic | 1400.78 | 33,952표 · 신뢰구간 1396.33–1405.24 |
| 147 | qwen3-235b-a22b-thinking-2507Alibaba | 1399.89 | 8,800표 · 신뢰구간 1393.31–1406.48 |
| 148 | qwen3-next-80b-a3b-instructAlibaba | 1399.21 | 22,532표 · 신뢰구간 1394.41–1404.01 |
| 149 | deepseek-r1DeepSeek | 1397.97 | 18,524표 · 신뢰구간 1393.07–1402.86 |
| 150 | qwen3.5-flashAlibaba | 1396.9 | 58,280표 · 신뢰구간 1393.14–1400.67 |
| 151 | deepseek-v3-0324DeepSeek | 1395.69 | 44,795표 · 신뢰구간 1391.79–1399.59 |
| 152 | hunyuan-vision-1.5-thinkingTencent | 1395.43 | 2,170표 · 신뢰구간 1383.04–1407.82 |
| 153 | qwen3.5-35b-a3bAlibaba | 1395.15 | 29,065표 · 신뢰구간 1390.83–1399.48 |
| 154 | qwen3-vl-235b-a22b-thinkingAlibaba | 1395.03 | 7,785표 · 신뢰구간 1388.17–1401.88 |
| 155 | amazon-nova-experimental-chat-12-10Amazon | 1394.49 | 3,635표 · 신뢰구간 1384.9–1404.07 |
| 156 | step-3.5-flashStepFun | 1394.4 | 57,212표 · 신뢰구간 1390.76–1398.04 |
| 157 | mimo-v2-flash (non-thinking)Xiaomi | 1392.15 | 46,158표 · 신뢰구간 1388.59–1395.7 |
| 158 | o4-mini-2025-04-16OpenAI | 1390.57 | 44,632표 · 신뢰구간 1386.57–1394.57 |
| 159 | minimax-m2.5MiniMax | 1390.54 | 40,884표 · 신뢰구간 1386.56–1394.53 |
| 160 | claude-sonnet-4-20250514Anthropic | 1390.37 | 38,959표 · 신뢰구간 1385.96–1394.78 |
| 161 | gpt-5-mini-highOpenAI | 1389.42 | 26,569표 · 신뢰구간 1384.75–1394.09 |
| 162 | o1-previewOpenAI | 1388.27 | 31,122표 · 신뢰구간 1383.26–1393.28 |
| 163 | claude-3-7-sonnet-20250219-thinking-32kAnthropic | 1387.82 | 38,090표 · 신뢰구간 1383.61–1392.03 |
| 164 | hunyuan-t1-20250711Tencent | 1387.35 | 4,581표 · 신뢰구간 1378.63–1396.07 |
| 165 | mistral-medium-2505Mistral | 1387.33 | 32,665표 · 신뢰구간 1382.6–1392.06 |
| 166 | qwen3-coder-480b-a35b-instructAlibaba | 1387.32 | 25,092표 · 신뢰구간 1382.33–1392.31 |
| 167 | mimo-v2-flash (thinking)Xiaomi | 1386.12 | 10,749표 · 신뢰구간 1379.84–1392.4 |
| 168 | minimax-m2.1-previewMiniMax | 1383.81 | 16,633표 · 신뢰구간 1378.55–1389.07 |
| 169 | hunyuan-turbos-20250416Tencent | 1382.58 | 10,587표 · 신뢰구간 1376.08–1389.09 |
| 170 | gpt-4.1-mini-2025-04-14OpenAI | 1382.32 | 38,636표 · 신뢰구간 1377.98–1386.65 |
| 171 | qwen3-30b-a3b-instruct-2507Alibaba | 1382.3 | 23,224표 · 신뢰구간 1377.38–1387.22 |
| 172 | gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle | 1379.66 | 46,393표 · 신뢰구간 1376.21–1383.12 |
| 173 | trinity-large-preview | 1378.54 | 29,771표 · 신뢰구간 1374.18–1382.9 |
| 174 | glm-4.6vZ.ai | 1378.43 | 2,762표 · 신뢰구간 1367.1–1389.76 |
| 175 | solar-pro4Upstage | 1376.84 | 2,437표 · 신뢰구간 1364.63–1389.06 |
| 176 | qwen3-235b-a22bAlibaba | 1374.94 | 25,864표 · 신뢰구간 1370.23–1379.65 |
| 177 | gemini-2.5-flash-lite-preview-06-17-thinkingGoogle | 1374.5 | 32,218표 · 신뢰구간 1369.96–1379.03 |
| 178 | qwen2.5-maxAlibaba | 1373.81 | 32,417표 · 신뢰구간 1369.69–1377.93 |
| 179 | claude-3-5-sonnet-20241022Anthropic | 1373.65 | 87,696표 · 신뢰구간 1370.44–1376.85 |
| 180 | glm-4.5-airZ.ai | 1373.17 | 30,372표 · 신뢰구간 1368.9–1377.45 |
| 181 | claude-3-7-sonnet-20250219Anthropic | 1371.9 | 42,452표 · 신뢰구간 1367.93–1375.87 |
| 182 | trinity-large-thinking | 1369.12 | 28,989표 · 신뢰구간 1364.44–1373.8 |
| 183 | qwen3-next-80b-a3b-thinkingAlibaba | 1369.04 | 13,391표 · 신뢰구간 1363.16–1374.92 |
| 184 | glm-4.7-flashZ.ai | 1366.44 | 11,514표 · 신뢰구간 1360.62–1372.26 |
| 185 | amazon-nova-experimental-chat-11-10Amazon | 1365.36 | 25,104표 · 신뢰구간 1361.01–1369.72 |
| 186 | gemma-3-27b-itGoogle | 1365.11 | 46,421표 · 신뢰구간 1361.4–1368.83 |
| 187 | grok-3-mini-highSpaceXAI | 1363.78 | 15,536표 · 신뢰구간 1358.29–1369.26 |
| 188 | minimax-m1MiniMax | 1363.77 | 34,038표 · 신뢰구간 1359.46–1368.08 |
| 189 | o3-mini-highOpenAI | 1363.35 | 18,589표 · 신뢰구간 1358.08–1368.61 |
| 190 | nvidia-nemotron-3-super-120b-a12bNvidia | 1360.69 | 7,458표 · 신뢰구간 1353.41–1367.98 |
| 191 | gemini-2.0-flash-001Google | 1359.88 | 43,346표 · 신뢰구간 1356.08–1363.68 |
| 192 | deepseek-v3DeepSeek | 1358.26 | 21,770표 · 신뢰구간 1353.5–1363.02 |
| 193 | grok-3-mini-betaSpaceXAI | 1357.87 | 20,840표 · 신뢰구간 1352.73–1363.01 |
| 194 | mistral-small-2506Mistral | 1356.68 | 17,399표 · 신뢰구간 1351.45–1361.91 |
| 195 | intellect-3 | 1356.16 | 5,284표 · 신뢰구간 1347.81–1364.51 |
| 196 | nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4Nvidia | 1355.4 | 4,814표 · 신뢰구간 1346.15–1364.65 |
| 197 | command-a-03-2025Cohere | 1353.61 | 55,449표 · 신뢰구간 1350.13–1357.09 |
| 198 | gemini-2.0-flash-lite-preview-02-05Google | 1353.33 | 24,955표 · 신뢰구간 1349.01–1357.65 |
| 199 | glm-4.5vZ.ai | 1352.5 | 4,817표 · 신뢰구간 1344.06–1360.94 |
| 200 | gpt-oss-120bOpenAI | 1352.45 | 29,955표 · 신뢰구간 1348.06–1356.84 |
| 201 | gemini-1.5-pro-002Google | 1350.95 | 55,606표 · 신뢰구간 1347.55–1354.35 |
| 202 | amazon-nova-experimental-chat-10-20Amazon | 1349.74 | 11,363표 · 신뢰구간 1343.54–1355.95 |
| 203 | step-3StepFun | 1349.43 | 6,277표 · 신뢰구간 1341.91–1356.95 |
| 204 | hunyuan-turbos-20250226Tencent | 1348.68 | 2,220표 · 신뢰구간 1336.97–1360.4 |
| 205 | o3-miniOpenAI | 1347.55 | 56,661표 · 신뢰구간 1344–1351.1 |
| 206 | llama-3.1-nemotron-ultra-253b-v1Nvidia | 1347.45 | 2,549표 · 신뢰구간 1335.77–1359.14 |
| 207 | qwen3-32bAlibaba | 1346.92 | 3,926표 · 신뢰구간 1337.46–1356.38 |
| 208 | amazon-nova-experimental-chat-10-09Amazon | 1346.91 | 2,775표 · 신뢰구간 1335.96–1357.85 |
| 209 | mercury-2Inception AI | 1346.51 | 3,043표 · 신뢰구간 1335.79–1357.22 |
| 210 | qwen-plus-0125Alibaba | 1345.8 | 5,819표 · 신뢰구간 1337.47–1354.14 |
| 211 | gpt-4o-2024-05-13OpenAI | 1345.76 | 112,881표 · 신뢰구간 1342.29–1349.22 |
| 212 | minimax-m2MiniMax | 1345.68 | 6,752표 · 신뢰구간 1337.92–1353.44 |
| 213 | ling-flash-2.0Ant Group | 1344.19 | 6,853표 · 신뢰구간 1336.86–1351.52 |
| 214 | nvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia | 1343.07 | 3,316표 · 신뢰구간 1333.06–1353.09 |
| 215 | claude-3-5-sonnet-20240620Anthropic | 1342.66 | 82,419표 · 신뢰구간 1339.21–1346.11 |
| 216 | glm-4-plus-0111Z.ai | 1342.55 | 5,760표 · 신뢰구간 1334.13–1350.97 |
| 217 | granite-4.2-30bIBM | 1341.72 | 3,275표 · 신뢰구간 1331.06–1352.39 |
| 218 | gemma-3-12b-itGoogle | 1341.68 | 3,829표 · 신뢰구간 1332.16–1351.19 |
| 219 | hunyuan-turbo-0110Tencent | 1340.52 | 2,290표 · 신뢰구간 1328.99–1352.04 |
| 220 | gpt-5-nano-highOpenAI | 1337.22 | 8,134표 · 신뢰구간 1330.3–1344.14 |
| 221 | o1-miniOpenAI | 1336.74 | 51,981표 · 신뢰구간 1333.07–1340.4 |
| 222 | nova-2-liteAmazon | 1336.05 | 12,119표 · 신뢰구간 1329.9–1342.2 |
| 223 | qwq-32bAlibaba | 1335.75 | 25,092표 · 신뢰구간 1331.29–1340.22 |
| 224 | gemini-advanced-0514Google | 1335.49 | 50,148표 · 신뢰구간 1330.33–1340.65 |
| 225 | grok-2-2024-08-13SpaceXAI | 1335.44 | 63,498표 · 신뢰구간 1331.75–1339.14 |
| 226 | gpt-4o-2024-08-06OpenAI | 1335.16 | 45,499표 · 신뢰구간 1330.95–1339.37 |
| 227 | llama-3.1-405b-instruct-bf16Meta | 1334.92 | 41,375표 · 신뢰구간 1331.19–1338.65 |
| 228 | step-2-16k-exp-202412StepFun | 1333.49 | 4,833표 · 신뢰구간 1324.9–1342.08 |
| 229 | llama-3.1-405b-instruct-fp8Meta | 1333.06 | 59,656표 · 신뢰구간 1329.46–1336.67 |
| 230 | olmo-3.1-32b-instructAi2 | 1329.96 | 11,460표 · 신뢰구간 1323.74–1336.18 |
| 231 | yi-lightning | 1328.08 | 27,332표 · 신뢰구간 1323.14–1333.03 |
| 232 | llama-3.3-nemotron-49b-super-v1Nvidia | 1327.7 | 2,218표 · 신뢰구간 1315.56–1339.84 |
| 233 | molmo-2-8bAi2 | 1327.65 | 792표 · 신뢰구간 1306.26–1349.04 |
| 234 | qwen3-30b-a3bAlibaba | 1326.85 | 26,092표 · 신뢰구간 1322.09–1331.6 |
| 235 | llama-4-maverick-17b-128e-instructMeta | 1326.66 | 39,360표 · 신뢰구간 1322.38–1330.94 |
| 236 | hunyuan-large-2025-02-10Tencent | 1326.09 | 3,738표 · 신뢰구간 1316.35–1335.82 |
| 237 | gpt-4-turbo-2024-04-09OpenAI | 1324.05 | 98,114표 · 신뢰구간 1320.12–1327.98 |
| 238 | claude-3-5-haiku-20241022Anthropic | 1324.03 | 68,974표 · 신뢰구간 1320.76–1327.29 |
| 239 | gemini-1.5-pro-001Google | 1323.68 | 79,138표 · 신뢰구간 1319.69–1327.67 |
| 240 | deepseek-v2.5-1210DeepSeek | 1323.21 | 6,795표 · 신뢰구간 1314.93–1331.48 |
| 241 | gpt-4.1-nano-2025-04-14OpenAI | 1322.1 | 6,103표 · 신뢰구간 1314.37–1329.83 |
| 242 | claude-3-opus-20240229Anthropic | 1321.61 | 194,909표 · 신뢰구간 1318.53–1324.69 |
| 243 | llama-4-scout-17b-16e-instructMeta | 1321.31 | 29,747표 · 신뢰구간 1316.57–1326.05 |
| 244 | ring-flash-2.0Ant Group | 1321.08 | 6,902표 · 신뢰구간 1313.77–1328.39 |
| 245 | step-1o-turbo-202506StepFun | 1320.18 | 8,860표 · 신뢰구간 1313.29–1327.07 |
| 246 | glm-4-plusZ.ai | 1319.18 | 26,126표 · 신뢰구간 1314.24–1324.11 |
| 247 | qwen-max-0919Alibaba | 1317.85 | 16,478표 · 신뢰구간 1312.14–1323.55 |
| 248 | gpt-4o-mini-2024-07-18OpenAI | 1317.47 | 68,697표 · 신뢰구간 1313.93–1321.02 |
| 249 | llama-3.3-70b-instructMeta | 1317.44 | 54,415표 · 신뢰구간 1313.94–1320.95 |
| 250 | gemma-3n-e4b-itGoogle | 1317.21 | 22,087표 · 신뢰구간 1312.02–1322.39 |
| 251 | gpt-oss-20bOpenAI | 1317.12 | 10,394표 · 신뢰구간 1310.71–1323.54 |
| 252 | qwen2.5-plus-1127Alibaba | 1314.52 | 10,187표 · 신뢰구간 1308.16–1320.88 |
| 253 | nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia | 1314.23 | 15,332표 · 신뢰구간 1308.69–1319.77 |
| 254 | mistral-large-2407Mistral | 1314.03 | 45,459표 · 신뢰구간 1310.1–1317.97 |
| 255 | athene-v2-chat | 1314 | 24,739표 · 신뢰구간 1309.44–1318.57 |
| 256 | gpt-4-0125-previewOpenAI | 1312.78 | 93,439표 · 신뢰구간 1308.69–1316.87 |
| 257 | gpt-4-1106-previewOpenAI | 1312.36 | 100,105표 · 신뢰구간 1308.47–1316.26 |
| 258 | hunyuan-standard-2025-02-10Tencent | 1311.03 | 3,904표 · 신뢰구간 1301.36–1320.7 |
| 259 | gemini-1.5-flash-002Google | 1308.98 | 34,902표 · 신뢰구간 1304.75–1313.21 |
| 260 | grok-2-mini-2024-08-13SpaceXAI | 1308.22 | 52,567표 · 신뢰구간 1304.49–1311.95 |
| 261 | mercuryInception AI | 1308.22 | 1,928표 · 신뢰구간 1294.36–1322.08 |
| 262 | deepseek-v2.5DeepSeek | 1306.96 | 24,572표 · 신뢰구간 1302.24–1311.67 |
| 263 | olmo-3-32b-thinkAi2 | 1306.71 | 5,683표 · 신뢰구간 1298.4–1315.02 |
| 264 | athene-70b-0725 | 1306.29 | 19,621표 · 신뢰구간 1300.61–1311.97 |
| 265 | granite-4.1-8bIBM | 1306 | 4,028표 · 신뢰구간 1295.83–1316.18 |
| 266 | mistral-large-2411Mistral | 1305.25 | 28,073표 · 신뢰구간 1300.8–1309.7 |
| 267 | magistral-medium-2506Mistral | 1304.39 | 11,467표 · 신뢰구간 1297.93–1310.85 |
| 268 | gemma-3-4b-itGoogle | 1303.12 | 4,171표 · 신뢰구간 1293.81–1312.44 |
| 269 | mistral-small-3.1-24b-instruct-2503Mistral | 1302.99 | 32,630표 · 신뢰구간 1298.44–1307.54 |
| 270 | qwen2.5-72b-instructAlibaba | 1302.64 | 39,406표 · 신뢰구간 1298.56–1306.73 |
| 271 | llama-3.1-nemotron-70b-instructNvidia | 1298.64 | 7,140표 · 신뢰구간 1290.88–1306.41 |
| 272 | granite-4.2-3bIBM | 1295.66 | 3,093표 · 신뢰구간 1283.86–1307.46 |
| 273 | hunyuan-large-visionTencent | 1294.01 | 5,260표 · 신뢰구간 1284.85–1303.17 |
| 274 | llama-3.1-70b-instructMeta | 1293.03 | 55,240표 · 신뢰구간 1289.29–1296.78 |
| 275 | amazon-nova-pro-v1.0Amazon | 1289.89 | 24,745표 · 신뢰구간 1285.31–1294.47 |
| 276 | jamba-1.5-large | 1289.09 | 8,662표 · 신뢰구간 1281.78–1296.4 |
| 277 | gemma-2-27b-itGoogle | 1289.06 | 75,754표 · 신뢰구간 1285.66–1292.46 |
| 278 | granite-4.2-8bIBM | 1288.4 | 3,111표 · 신뢰구간 1277.01–1299.8 |
| 279 | reka-core-20240904 | 1287.68 | 7,312표 · 신뢰구간 1280.5–1294.86 |
| 280 | gpt-4-0314OpenAI | 1287.13 | 54,173표 · 신뢰구간 1282.36–1291.9 |
| 281 | gemini-1.5-flash-001Google | 1286.19 | 62,833표 · 신뢰구간 1281.69–1290.7 |
| 282 | llama-3.1-nemotron-51b-instructNvidia | 1286.09 | 3,749표 · 신뢰구간 1276.12–1296.06 |
| 283 | llama-3.1-tulu-3-70bAi2 | 1285.77 | 2,846표 · 신뢰구간 1275.31–1296.24 |
| 284 | olmo-3.1-32b-thinkAi2 | 1285.64 | 8,116표 · 신뢰구간 1278.31–1292.97 |
| 285 | ibm-granite-h-smallIBM | 1285.4 | 5,535표 · 신뢰구간 1276.9–1293.89 |
| 286 | claude-3-sonnet-20240229Anthropic | 1280.77 | 109,284표 · 신뢰구간 1276.78–1284.76 |
| 287 | gemma-2-9b-it-simpo | 1279.98 | 10,072표 · 신뢰구간 1273.12–1286.84 |
| 288 | nemotron-4-340b-instructNvidia | 1276.62 | 19,659표 · 신뢰구간 1271.3–1281.95 |
| 289 | llama-3-70b-instructMeta | 1276.07 | 156,876표 · 신뢰구간 1272.48–1279.66 |
| 290 | command-r-plus-08-2024Cohere | 1275.84 | 9,866표 · 신뢰구간 1269.26–1282.42 |
| 291 | gpt-4-0613OpenAI | 1275.47 | 88,723표 · 신뢰구간 1271.41–1279.53 |
| 292 | mistral-small-24b-instruct-2501Mistral | 1274.09 | 14,681표 · 신뢰구간 1268.17–1280.01 |
| 293 | glm-4-0520Z.ai | 1272.99 | 9,788표 · 신뢰구간 1266.01–1279.98 |
| 294 | reka-flash-20240904 | 1271.91 | 7,536표 · 신뢰구간 1264.91–1278.92 |
| 295 | qwen2.5-coder-32b-instructAlibaba | 1270.3 | 5,432표 · 신뢰구간 1262.17–1278.43 |
| 296 | c4ai-aya-expanse-32bCohere | 1266.87 | 27,124표 · 신뢰구간 1261.97–1271.77 |
| 297 | gemma-2-9b-itGoogle | 1266.59 | 54,611표 · 신뢰구간 1262.75–1270.42 |
| 298 | deepseek-coder-v2DeepSeek | 1264.82 | 15,147표 · 신뢰구간 1258.54–1271.1 |
| 299 | qwen2-72b-instructAlibaba | 1261.27 | 37,325표 · 신뢰구간 1256.32–1266.23 |
| 300 | command-r-plusCohere | 1261.22 | 77,554표 · 신뢰구간 1256.89–1265.54 |
| 301 | claude-3-haiku-20240307Anthropic | 1261.08 | 117,701표 · 신뢰구간 1257.31–1264.84 |
| 302 | amazon-nova-lite-v1.0Amazon | 1260.19 | 19,372표 · 신뢰구간 1255–1265.38 |
| 303 | gemini-1.5-flash-8b-001Google | 1258.46 | 35,558표 · 신뢰구간 1254.15–1262.77 |
| 304 | phi-4Microsoft | 1255.98 | 24,126표 · 신뢰구간 1251.37–1260.58 |
| 305 | olmo-2-0325-32b-instructAi2 | 1251.31 | 3,334표 · 신뢰구간 1240.53–1262.09 |
| 306 | command-r-08-2024Cohere | 1249.87 | 10,140표 · 신뢰구간 1243.26–1256.47 |
| 307 | mistral-large-2402Mistral | 1241.94 | 62,436표 · 신뢰구간 1237.22–1246.66 |
| 308 | amazon-nova-micro-v1.0Amazon | 1240.45 | 19,364표 · 신뢰구간 1235.27–1245.62 |
| 309 | jamba-1.5-mini | 1239.4 | 8,858표 · 신뢰구간 1232.18–1246.63 |
| 310 | ministral-8b-2410Mistral | 1237.28 | 4,781표 · 신뢰구간 1228.19–1246.37 |
| 311 | gemini-pro-dev-apiGoogle | 1236.18 | 18,354표 · 신뢰구간 1228.86–1243.5 |
| 312 | qwen1.5-110b-chatAlibaba | 1233.64 | 26,195표 · 신뢰구간 1228.09–1239.19 |
| 313 | hunyuan-standard-256kTencent | 1233.02 | 2,728표 · 신뢰구간 1221.29–1244.76 |
| 314 | reka-flash-21b-20240226-online | 1232.98 | 15,450표 · 신뢰구간 1225.59–1240.38 |
| 315 | qwen1.5-72b-chatAlibaba | 1232.93 | 39,302표 · 신뢰구간 1227.66–1238.21 |
| 316 | mixtral-8x22b-instruct-v0.1Mistral | 1228.97 | 51,416표 · 신뢰구간 1224.41–1233.53 |
| 317 | command-rCohere | 1226.27 | 54,036표 · 신뢰구간 1221.49–1231.06 |
| 318 | reka-flash-21b-20240226 | 1226.26 | 24,806표 · 신뢰구간 1220.31–1232.2 |
| 319 | gpt-3.5-turbo-0125OpenAI | 1224.79 | 66,207표 · 신뢰구간 1220.09–1229.49 |
| 320 | llama-3-8b-instructMeta | 1223.13 | 104,642표 · 신뢰구간 1219.38–1226.87 |
| 321 | gemini-proGoogle | 1222.92 | 6,390표 · 신뢰구간 1211.19–1234.66 |
| 322 | c4ai-aya-expanse-8bCohere | 1222.74 | 9,818표 · 신뢰구간 1215.76–1229.72 |
| 323 | mistral-mediumMistral | 1222.14 | 34,550표 · 신뢰구간 1216.65–1227.63 |
| 324 | llama-3.1-tulu-3-8bAi2 | 1220.21 | 2,896표 · 신뢰구간 1209.54–1230.89 |
| 325 | yi-1.5-34b-chat | 1212.44 | 24,146표 · 신뢰구간 1207.4–1217.48 |
| 326 | zephyr-orpo-141b-A35b-v0.1 | 1212.41 | 4,652표 · 신뢰구간 1201.62–1223.19 |
| 327 | llama-3.1-8b-instructMeta | 1211.03 | 49,605표 · 신뢰구간 1206.87–1215.19 |
| 328 | granite-3.1-8b-instructIBM | 1207.96 | 3,090표 · 신뢰구간 1196.87–1219.06 |
| 329 | qwen1.5-32b-chatAlibaba | 1203.39 | 21,741표 · 신뢰구간 1197.27–1209.5 |
| 330 | gpt-3.5-turbo-1106OpenAI | 1203.37 | 16,619표 · 신뢰구간 1194.64–1212.11 |
| 331 | gemma-2-2b-itGoogle | 1199.8 | 46,616표 · 신뢰구간 1195.69–1203.9 |
| 332 | phi-3-medium-4k-instructMicrosoft | 1197.35 | 25,055표 · 신뢰구간 1192.18–1202.51 |
| 333 | mixtral-8x7b-instruct-v0.1Mistral | 1196.56 | 73,503표 · 신뢰구간 1192.29–1200.82 |
| 334 | dbrx-instruct-preview | 1194.85 | 32,191표 · 신뢰구간 1188.74–1200.97 |
| 335 | qwen1.5-14b-chatAlibaba | 1190.51 | 17,839표 · 신뢰구간 1183.39–1197.62 |
| 336 | internlm2_5-20b-chat | 1190.4 | 9,901표 · 신뢰구간 1183.22–1197.59 |
| 337 | deepseek-llm-67b-chatDeepSeek | 1184.25 | 4,932표 · 신뢰구간 1172.78–1195.73 |
| 338 | wizardlm-70bMicrosoft | 1184.15 | 8,214표 · 신뢰구간 1174.72–1193.58 |
| 339 | yi-34b-chat | 1183.22 | 15,483표 · 신뢰구간 1176.4–1190.05 |
| 340 | granite-3.0-8b-instructIBM | 1182.45 | 6,638표 · 신뢰구간 1173.77–1191.13 |
| 341 | openchat-3.5 | 1182.34 | 7,968표 · 신뢰구간 1172.68–1191.99 |
| 342 | openchat-3.5-0106 | 1182.09 | 12,637표 · 신뢰구간 1174.1–1190.07 |
| 343 | gemma-1.1-7b-itGoogle | 1181.99 | 23,893표 · 신뢰구간 1175.92–1188.06 |
| 344 | snowflake-arctic-instruct | 1179.37 | 32,832표 · 신뢰구간 1173.46–1185.28 |
| 345 | granite-3.1-2b-instructIBM | 1178.38 | 3,188표 · 신뢰구간 1167.19–1189.57 |
| 346 | tulu-2-dpo-70b | 1177.11 | 6,535표 · 신뢰구간 1167.31–1186.9 |
| 347 | openhermes-2.5-mistral-7b | 1175.26 | 5,006표 · 신뢰구간 1164.86–1185.66 |
| 348 | vicuna-33b | 1172.32 | 22,479표 · 신뢰구간 1166.13–1178.52 |
| 349 | starling-lm-7b-beta | 1170.53 | 16,056표 · 신뢰구간 1163.13–1177.93 |
| 350 | phi-3-small-8k-instructMicrosoft | 1170.52 | 17,766표 · 신뢰구간 1164.6–1176.43 |
| 351 | llama-2-70b-chatMeta | 1170.11 | 38,492표 · 신뢰구간 1164.62–1175.6 |
| 352 | starling-lm-7b-alpha | 1166.85 | 10,224표 · 신뢰구간 1158.79–1174.9 |
| 353 | llama-3.2-3b-instructMeta | 1166.29 | 7,936표 · 신뢰구간 1158.58–1173.99 |
| 354 | nous-hermes-2-mixtral-8x7b-dpo | 1163.88 | 3,777표 · 신뢰구간 1151.98–1175.78 |
| 355 | granite-3.0-2b-instructIBM | 1156.02 | 6,837표 · 신뢰구간 1147.64–1164.41 |
| 356 | llama2-70b-steerlm-chatNvidia | 1154.12 | 3,585표 · 신뢰구간 1141.54–1166.71 |
| 357 | qwq-32b-previewAlibaba | 1154.08 | 3,231표 · 신뢰구간 1142.59–1165.56 |
| 358 | solar-10.7b-instruct-v1.0 | 1151.8 | 4,155표 · 신뢰구간 1138.65–1164.95 |
| 359 | dolphin-2.2.1-mistral-7b | 1151.65 | 1,679표 · 신뢰구간 1136.34–1166.95 |
| 360 | mpt-30b-chat | 1150.07 | 2,572표 · 신뢰구간 1137.84–1162.29 |
| 361 | wizardlm-13bMicrosoft | 1148.89 | 7,044표 · 신뢰구간 1139.68–1158.1 |
| 362 | mistral-7b-instruct-v0.2Mistral | 1148.82 | 19,402표 · 신뢰구간 1142.17–1155.47 |
| 363 | falcon-180b-chat | 1147.37 | 1,295표 · 신뢰구간 1130.34–1164.4 |
| 364 | qwen1.5-7b-chatAlibaba | 1143.3 | 4,737표 · 신뢰구간 1133.42–1153.18 |
| 365 | phi-3-mini-4k-instruct-june-2024Microsoft | 1142.56 | 12,297표 · 신뢰구간 1136.12–1149 |
| 366 | llama-2-13b-chatMeta | 1140.89 | 19,174표 · 신뢰구간 1134.17–1147.61 |
| 367 | vicuna-13b | 1140.86 | 19,367표 · 신뢰구간 1134.17–1147.55 |
| 368 | qwen-14b-chatAlibaba | 1138.63 | 4,964표 · 신뢰구간 1127.7–1149.56 |
| 369 | palm-2Google | 1138.33 | 8,554표 · 신뢰구간 1128.98–1147.69 |
| 370 | gemma-7b-itGoogle | 1137.15 | 8,925표 · 신뢰구간 1127.67–1146.63 |
| 371 | codellama-34b-instructMeta | 1136.24 | 7,366표 · 신뢰구간 1127.36–1145.12 |
| 372 | zephyr-7b-beta | 1130.22 | 11,118표 · 신뢰구간 1121.4–1139.05 |
| 373 | phi-3-mini-128k-instructMicrosoft | 1129.17 | 20,685표 · 신뢰구간 1121.75–1136.59 |
| 374 | phi-3-mini-4k-instructMicrosoft | 1127.58 | 20,118표 · 신뢰구간 1121.18–1133.98 |
| 375 | guanaco-33b | 1126.84 | 2,921표 · 신뢰구간 1114.77–1138.92 |
| 376 | zephyr-7b-alpha | 1126.32 | 1,785표 · 신뢰구간 1110.74–1141.89 |
| 377 | stripedhyena-nous-7b | 1120.92 | 5,182표 · 신뢰구간 1109.95–1131.88 |
| 378 | codellama-70b-instructMeta | 1118.63 | 1,143표 · 신뢰구간 1100.52–1136.74 |
| 379 | gemma-1.1-2b-itGoogle | 1116.04 | 10,854표 · 신뢰구간 1108.31–1123.76 |
| 380 | vicuna-7b | 1114.61 | 6,923표 · 신뢰구간 1105.49–1123.73 |
| 381 | smollm2-1.7b-instruct | 1114.09 | 2,199표 · 신뢰구간 1099.73–1128.44 |
| 382 | llama-3.2-1b-instructMeta | 1110.62 | 8,045표 · 신뢰구간 1102.74–1118.5 |
| 383 | mistral-7b-instructMistral | 1109.65 | 8,977표 · 신뢰구간 1100.37–1118.92 |
| 384 | llama-2-7b-chatMeta | 1107.4 | 14,148표 · 신뢰구간 1100.36–1114.45 |
| 385 | gemma-2b-itGoogle | 1093.02 | 4,780표 · 신뢰구간 1081.55–1104.49 |
| 386 | qwen1.5-4b-chatAlibaba | 1090.38 | 7,597표 · 신뢰구간 1081.05–1099.7 |
| 387 | olmo-7b-instructAi2 | 1073.15 | 6,328표 · 신뢰구간 1062–1084.29 |
| 388 | koala-13b | 1070.25 | 6,965표 · 신뢰구간 1060.41–1080.1 |
| 389 | alpaca-13b | 1069.25 | 5,745표 · 신뢰구간 1057.83–1080.67 |
| 390 | gpt4all-13b-snoozy | 1066.87 | 1,743표 · 신뢰구간 1051.7–1082.04 |
| 391 | mpt-7b-chat | 1062.63 | 3,924표 · 신뢰구간 1050.69–1074.56 |
| 392 | chatglm3-6b | 1055.86 | 4,658표 · 신뢰구간 1044.22–1067.51 |
| 393 | RWKV-4-Raven-14B | 1041.6 | 4,845표 · 신뢰구간 1030.25–1052.95 |
| 394 | chatglm2-6b | 1024.06 | 2,658표 · 신뢰구간 1010.5–1037.62 |
| 395 | oasst-pythia-12b | 1022.71 | 6,310표 · 신뢰구간 1011.89–1033.54 |
| 396 | chatglm-6b | 995.17 | 4,914표 · 신뢰구간 982.65–1007.69 |
| 397 | fastchat-t5-3b | 991.82 | 4,203표 · 신뢰구간 979.49–1004.15 |
| 398 | dolly-v2-12b | 981.55 | 3,412표 · 신뢰구간 968.08–995.03 |
| 399 | llama-13bMeta | 974.2 | 2,391표 · 신뢰구간 958.48–989.92 |
| 400 | stablelm-tuned-alpha-7b | 952.52 | 3,287표 · 신뢰구간 939.85–965.18 |
일치하는 모델이 없습니다. 검색어를 줄여 보세요.
공개된 숫자만 높은 순으로 표시합니다. 순서가 신뢰구간을 고려한 확정 순위는 아닙니다. 텍스트 전체·스타일 보정 조건입니다. 원문 순위의 신뢰구간과 투표수를 보존했습니다. 평점은 백분율이 아니며, 근소한 차이는 확정적인 우열을 뜻하지 않습니다.
읽는 법
전체 벤치마크사람이 두 모델 답변을 직접 비교해 더 나은 쪽을 고르는 공개 아레나 리더보드입니다.
Text Overall의 스타일 보정 평점입니다. 평점 차이와 신뢰구간·투표 수를 함께 확인합니다.