LMArena Coding Arena 代码能力排行榜
基于 LMArena Coding Arena 用户匿名投票的最新AI大模型代码编程能力排行榜，涵盖各模型的 Elo 得分、95% 置信区间、投票量、机构与许可证。
榜首模型
Opus 4.7 (high)
最高得分
1552.00
模型数量
395
数据版本
2026年09月02日
数据来源: LM Arena
关于本排行榜
本排行榜展示了当前 AI 大模型在代码编程任务中的实力排名。数据来源于 LMArena （前身为 LMSYS Chatbot Arena）的 Coding 子赛道，通过真实用户匿名盲测投票评估各模型在代码编程任务中的表现。
评测方法概要
匿名盲测：用户发出编程问题后，由两个"隐藏身份"的模型分别给出代码解答，用户投票选出更好的回答，排除品牌偏见。
Elo 评分：采用 Bradley-Terry 模型计算 Elo 分数，分数越高说明该模型的代码回答越容易被用户选择。
覆盖多种编程场景：包括代码生成、Bug 修复、算法实现、代码解释等高频真实编程场景。
DataLearner 在原始数据基础上提供中文解读与深度分析，并将排行榜模型关联至 DataLearner 模型库，方便您一键查看模型详情、API 定价、评测得分等完整信息。
排名总表
| 排名 | 模型名称 | 得分 | 95% CI | 投票数 | 机构 | 许可证 |
|---|---|---|---|---|---|---|
 Opus 4.7 (high)Anthropic | 1552.00 | +/-6 | 17,176 | Anthropic | Proprietary | |
| Claude Opus 4.6 (high)Anthropic | 1552.00 | +/-6 | 18,800 | Anthropic | Proprietary | |
| Claude Fable 5Anthropic | 1551.00 | +/-8 | 7,293 | Anthropic | Proprietary | |
| 4 | Opus 4.7Anthropic | 1547.00 | +/-6 | 17,342 | Anthropic | Proprietary |
| 5 | Claude Opus 4.6Anthropic | 1546.00 | +/-5 | 21,198 | Anthropic | Proprietary |
| 6 |  kimi-k3-maxMoonshot | 1542.00 | +/-9 | 4,719 | Moonshot | Kimi K3 license |
| 7 |  gemini-3.8-flash-highGoogle | 1537.00 | +/-16 | 1,456 | Proprietary | |
| 8 | Claude Opus 4.8 (high)Anthropic | 1534.00 | +/-6 | 13,439 | Anthropic | Proprietary |
| 9 |  glm-5.3-flashZ.ai | 1534.00 | +/-17 | 1,274 | Z.ai | MIT |
| 10 |  Muse Spark 1.2 (xhigh)Facebook AI研究实验室 | 1533.00 | +/-20 | 935 | Facebook AI研究实验室 | Proprietary |
| 11 | claude-opus-5-highAnthropic | 1533.00 | +/-7 | 9,354 | Anthropic | Proprietary |
| 12 | Muse Spark 1.1Facebook AI研究实验室 | 1531.00 | +/-8 | 6,988 | Facebook AI研究实验室 | Proprietary |
| 13 | Opus 4.5Anthropic | 1530.00 | +/-7 | 7,521 | Anthropic | Proprietary |
| 14 |  GPT-5.6 Sol (xhigh)OpenAI | 1529.00 | +/-8 | 6,534 | OpenAI | Proprietary |
| 15 | Claude Sonnet 4.6Anthropic | 1528.00 | +/-6 | 18,359 | Anthropic | Proprietary |
| 16 | glm-5.3-maxZ.ai | 1528.00 | +/-14 | 2,008 | Z.ai | MIT |
| 17 | Claude Opus 4.8Anthropic | 1527.00 | +/-6 | 13,853 | Anthropic | Proprietary |
| 18 | Muse SparkFacebook AI研究实验室 | 1526.00 | +/-10 | 3,770 | Facebook AI研究实验室 | Proprietary |
| 19 |  Qwen3.7-Max-Preview阿里巴巴 | 1525.00 | +/-18 | 1,118 | 阿里巴巴 | Proprietary |
| 20 | claude-opus-5-maxAnthropic | 1525.00 | +/-9 | 4,480 | Anthropic | Proprietary |
| 21 | Claude Opus 4Anthropic | 1523.00 | +/-6 | 17,189 | Anthropic | Proprietary |
| 22 |  Grok 4.5xAI | 1523.00 | +/-8 | 7,383 | xAI | Proprietary |
| 23 | gemini-3.7-flash-highGoogle | 1522.00 | +/-15 | 1,740 | Proprietary | |
| 24 | Claude Sonnet 4.5 (high)Anthropic | 1521.00 | +/-7 | 8,653 | Anthropic | Proprietary |
| 25 | Gemini 3.1 Pro PreviewGoogle Deep Mind | 1521.00 | +/-5 | 28,473 | Google Deep Mind | Proprietary |
| 26 | mimo-v2.5-proXiaomi | 1520.00 | +/-6 | 15,813 | Xiaomi | MIT |
| 27 | GPT-5.4 (high)OpenAI | 1520.00 | +/-6 | 16,433 | OpenAI | Proprietary |
| 28 | GPT-5.5 (high)OpenAI | 1520.00 | +/-6 | 17,668 | OpenAI | Proprietary |
| 29 | Claude Sonnet 4.5Anthropic | 1520.00 | +/-5 | 19,125 | Anthropic | Proprietary |
| 30 | qwen3.8-maxAlibaba | 1520.00 | +/-10 | 3,867 | Alibaba | Proprietary |
| 31 | GPT-5.6 Terra (xhigh)OpenAI | 1519.00 | +/-8 | 6,686 | OpenAI | Proprietary |
| 32 | Gemini 3 ProGoogle Deep Mind | 1518.00 | +/-7 | 8,473 | Google Deep Mind | Proprietary |
| 33 | gemini-3.6-flash-highGoogle | 1518.00 | +/-8 | 6,629 | Proprietary | |
| 34 | Claude Fable 5.1 (max)Anthropic | 1517.00 | +/-26 | 553 | Anthropic | Proprietary |
| 35 | GPT-5.2 Chat (0210)OpenAI | 1515.00 | +/-7 | 9,094 | OpenAI | Proprietary |
| 36 | Kimi K2.6Moonshot AI | 1514.00 | +/-7 | 10,421 | Moonshot AI | Modified MIT |
| 37 | GLM 5.1智谱AI | 1514.00 | +/-6 | 12,715 | 智谱AI | MIT |
| 38 | GPT-5.5 InstantOpenAI | 1514.00 | +/-8 | 7,522 | OpenAI | Proprietary |
| 39 |  ERNIE-5.1-Preview百度 | 1514.00 | +/-7 | 10,299 | 百度 | Proprietary |
| 40 | Qwen3.5 Max Preview阿里巴巴 | 1514.00 | +/-8 | 6,055 | 阿里巴巴 | Proprietary |
| 41 | GPT-5.4OpenAI | 1514.00 | +/-6 | 17,695 | OpenAI | Proprietary |
| 42 | Claude Sonnet 4.5Anthropic | 1513.00 | +/-5 | 18,945 | Anthropic | Proprietary |
| 43 |  DOLA Seed 2.0 Pro字节跳动Seed团队 | 1513.00 | +/-6 | 20,711 | 字节跳动Seed团队 | Proprietary |
| 44 | Opus 4.1 (thinking-16k)Anthropic | 1512.00 | +/-6 | 9,723 | Anthropic | Proprietary |
| 45 | grok-4.6-highSpaceXAI | 1511.00 | +/-21 | 839 | SpaceXAI | Proprietary |
| 46 | grok-4.20-beta-0309-reasoningxAI | 1510.00 | +/-6 | 17,210 | xAI | Proprietary |
| 47 | Qwen3.6-Max-Preview阿里巴巴 | 1509.00 | +/-15 | 1,551 | 阿里巴巴 | Proprietary |
| 48 | glm-5.2-maxZ.ai | 1509.00 | +/-7 | 9,550 | Z.ai | MIT |
| 49 | GPT-5.5OpenAI | 1509.00 | +/-6 | 18,407 | OpenAI | Proprietary |
| 50 | Grok 4.20 BetaxAI | 1508.00 | +/-8 | 7,159 | xAI | Proprietary |
| 51 | grok-4.20-multi-agent-beta-0309xAI | 1508.00 | +/-6 | 16,889 | xAI | Proprietary |
| 52 | gemini-3.5-flash-highGoogle | 1508.00 | +/-7 | 9,940 | Proprietary | |
| 53 | Gemini 3.0 FlashGoogle Deep Mind | 1507.00 | +/-8 | 6,335 | Google Deep Mind | Proprietary |
| 54 | Kimi K2.5 InstantMoonshot AI | 1506.00 | +/-14 | 1,776 | Moonshot AI | Modified MIT |
| 55 | Opus 4.1Anthropic | 1505.00 | +/-5 | 15,388 | Anthropic | Proprietary |
| 56 |  deepseek-v4-pro-high-20260813DeepSeek | 1505.00 | +/-15 | 1,609 | DeepSeek | MIT |
| 57 | gemini-3.5-flash-mediumGoogle | 1503.00 | +/-7 | 9,576 | Proprietary | |
| 58 |  longcat-flash-chat-2602-expMeituan | 1503.00 | +/-7 | 7,755 | Meituan | Proprietary |
| 59 | mimo-v2-proXiaomi | 1503.00 | +/-8 | 6,911 | Xiaomi | Proprietary |
| 60 | gemini-3.5-flash-liteGoogle | 1502.00 | +/-8 | 6,220 | Proprietary | |
| 61 |  Hy3腾讯AI实验室 | 1502.00 | +/-14 | 1,947 | 腾讯AI实验室 | Apache 2.0 |
| 62 | Kimi K2 ThinkingMoonshot AI | 1502.00 | +/-5 | 19,585 | Moonshot AI | Modified MIT |
| 63 | DeepSeek-V4-ProDeepSeek-AI | 1502.00 | +/-6 | 16,164 | DeepSeek-AI | MIT |
| 64 | Qwen3.7-Plus阿里巴巴 | 1500.00 | +/-7 | 11,103 | 阿里巴巴 | Proprietary |
| 65 |  Gemma 4 31BDeepMind | 1499.00 | +/-15 | 1,371 | DeepMind | Apache 2.0 |
| 66 | Grok 4.1 ThinkingxAI | 1499.00 | +/-6 | 14,835 | xAI | Proprietary |
| 67 | Claude Opus 4 (thinking-16k)Anthropic | 1498.00 | +/-8 | 6,561 | Anthropic | Proprietary |
| 68 |  MiniMax M3MiniMaxAI | 1498.00 | +/-6 | 13,035 | MiniMaxAI | MiniMax Community License |
| 69 | GLM-5智谱AI | 1498.00 | +/-7 | 7,189 | 智谱AI | MIT |
| 70 | GPT-5.6 Luna (xhigh)OpenAI | 1497.00 | +/-8 | 6,918 | OpenAI | Proprietary |
| 71 | GPT-5.3 ChatOpenAI | 1496.00 | +/-7 | 8,703 | OpenAI | Proprietary |
| 72 | GPT-5.4 mini (high)OpenAI | 1496.00 | +/-6 | 16,205 | OpenAI | Proprietary |
| 73 | Qwen 3.6 Plus Preview阿里巴巴 | 1495.00 | +/-6 | 13,767 | 阿里巴巴 | Proprietary |
| 74 | qwen3.8-27bAlibaba | 1494.00 | +/-14 | 2,006 | Alibaba | Apache 2.0 |
| 75 | Grok 4.1xAI | 1493.00 | +/-6 | 15,438 | xAI | Proprietary |
| 76 | GPT-5.1 Pro (high)OpenAI | 1492.00 | +/-7 | 8,110 | OpenAI | Proprietary |
| 77 | InklingThinking Machines Lab | 1491.00 | +/-8 | 6,353 | Thinking Machines Lab | Apache 2.0 |
| 78 | mimo-v2.5Xiaomi | 1491.00 | +/-7 | 12,853 | Xiaomi | MIT |
| 79 | Qwen3.5-397B-A17B阿里巴巴 | 1491.00 | +/-5 | 21,233 | 阿里巴巴 | Apache 2.0 |
| 80 | Gemini 3.0 Flash (minimal)Google Deep Mind | 1491.00 | +/-5 | 22,561 | Google Deep Mind | Proprietary |
| 81 | GLM-5V-Turbo智谱AI | 1490.00 | +/-12 | 2,613 | 智谱AI | Proprietary |
| 82 | GPT-5.2 Pro (high)OpenAI | 1490.00 | +/-6 | 11,686 | OpenAI | Proprietary |
| 83 | ERNIE 5.0 (0110)百度 | 1489.00 | +/-7 | 8,558 | 百度 | Proprietary |
| 84 | deepseek-v4-pro-high-previewDeepSeek | 1488.00 | +/-6 | 15,107 | DeepSeek | MIT |
| 85 | Grok 4.3 BetaxAI | 1488.00 | +/-6 | 18,320 | xAI | Proprietary |
| 86 |  amazon-nova-experimental-chat-26-02-10Amazon | 1487.00 | +/-20 | 835 | Amazon | Proprietary |
| 87 | Kimi K2 Thinking (thinking-turbo)Moonshot AI | 1486.00 | +/-6 | 14,686 | Moonshot AI | Modified MIT |
| 88 | mimo-v2-omniXiaomi | 1486.00 | +/-9 | 5,534 | Xiaomi | Proprietary |
| 89 | GLM-4.7智谱AI | 1485.00 | +/-12 | 2,387 | 智谱AI | MIT |
| 90 | DeepSeek-V4-FlashDeepSeek-AI | 1483.00 | +/-6 | 14,341 | DeepSeek-AI | MIT |
| 91 | Muse Glimmer-30BFacebook AI研究实验室 | 1482.00 | +/-18 | 1,065 | Facebook AI研究实验室 | Apache-2.0 |
| 92 | GPT-5.2OpenAI | 1482.00 | +/-5 | 20,803 | OpenAI | Proprietary |
| 93 | amazon-nova-experimental-chat-26-01-10Amazon | 1482.00 | +/-21 | 735 | Amazon | Proprietary |
| 94 | Qwen3 Max (Preview)阿里巴巴 | 1481.00 | +/-8 | 5,309 | 阿里巴巴 | Proprietary |
| 95 | Gemma 4 26B A4BDeepMind | 1481.00 | +/-15 | 1,379 | DeepMind | Apache 2.0 |
| 96 | Haiku 4.5Anthropic | 1481.00 | +/-4 | 32,074 | Anthropic | Proprietary |
| 97 | MiniMax-M2.7MiniMaxAI | 1480.00 | +/-6 | 18,875 | MiniMaxAI | Modified MIT |
| 98 | deepseek-v4-flash-high-previewDeepSeek | 1479.00 | +/-6 | 14,305 | DeepSeek | MIT |
| 99 |  Mistral Medium 3.5MistralAI | 1479.00 | +/-11 | 3,077 | MistralAI | Modified MIT |
| 100 | Inkling SmallThinky | 1477.00 | +/-9 | 4,303 | Thinky | Apache 2.0 |
| 101 | DeepSeek V3.2-Exp (thinking)DeepSeek-AI | 1476.00 | +/-7 | 8,482 | DeepSeek-AI | MIT |
| 102 | DeepSeek V3.2-Exp (thinking)DeepSeek-AI | 1476.00 | +/-13 | 1,907 | DeepSeek-AI | MIT |
| 103 |  Nemotron 3 UltraNVIDIA | 1475.00 | +/-11 | 2,953 | NVIDIA | OpenMDW-1.1 |
| 104 | GPT-5.1OpenAI | 1475.00 | +/-7 | 9,032 | OpenAI | Proprietary |
| 105 | qwen3-max-2025-09-23Alibaba | 1474.00 | +/-13 | 2,009 | Alibaba | Proprietary |
| 106 | Claude Sonnet 4 (thinking-32k)Anthropic | 1473.00 | +/-8 | 6,300 | Anthropic | Proprietary |
| 107 | longcat-flash-chatMeituan | 1473.00 | +/-13 | 2,207 | Meituan | MIT |
| 108 | ERNIE 5.0 Preview (1203)百度 | 1472.00 | +/-13 | 1,925 | 百度 | Proprietary |
| 109 | Qwen3-235B-A22B-2507阿里巴巴 | 1472.00 | +/-5 | 21,116 | 阿里巴巴 | Apache 2.0 |
| 110 | GPT-5-Pro (high)OpenAI | 1470.00 | +/-8 | 6,307 | OpenAI | Proprietary |
| 111 | DeepSeek V3.2DeepSeek-AI | 1470.00 | +/-6 | 10,523 | DeepSeek-AI | MIT |
| 112 | Mistral Large 3MistralAI | 1469.00 | +/-5 | 16,356 | MistralAI | Apache 2.0 |
| 113 | GPT-4o(2025-03-27)OpenAI | 1468.00 | +/-5 | 15,566 | OpenAI | Proprietary |
| 114 | Kimi K2 0905Moonshot AI | 1467.00 | +/-13 | 2,219 | Moonshot AI | Modified MIT |
| 115 | Gemini 2.5 ProGoogle Deep Mind | 1465.00 | +/-4 | 26,271 | Google Deep Mind | Proprietary |
| 116 | DeepSeek V3.2-ExpDeepSeek-AI | 1465.00 | +/-12 | 2,471 | DeepSeek-AI | MIT |
| 117 | Claude Opus 4Anthropic | 1465.00 | +/-7 | 7,782 | Anthropic | Proprietary |
| 118 | Qwen3-VL-235B-A22B-Instruct阿里巴巴 | 1465.00 | +/-13 | 2,285 | 阿里巴巴 | Apache 2.0 |
| 119 | DeepSeek-R1-0528DeepSeek-AI | 1464.00 | +/-11 | 2,686 | DeepSeek-AI | MIT |
| 120 | GPT-5.2 Chat (0210)OpenAI | 1462.00 | +/-8 | 5,931 | OpenAI | Proprietary |
| 121 | DeepSeek-V3.1 Terminus (thinking)DeepSeek-AI | 1461.00 | +/-24 | 632 | DeepSeek-AI | MIT |
| 122 | Grok 4.1 Fast (fast-reasoning)xAI | 1461.00 | +/-6 | 13,365 | xAI | Proprietary |
| 123 | hunyuan-hy3-previewTencent | 1460.00 | +/-14 | 1,959 | Tencent | tencent-hunyuan-community |
| 124 | OpenAI o3OpenAI | 1460.00 | +/-6 | 11,517 | OpenAI | Proprietary |
| 125 | GPT-5.4 nano (high)OpenAI | 1460.00 | +/-6 | 16,569 | OpenAI | Proprietary |
| 126 | Kimi K2Moonshot AI | 1460.00 | +/-8 | 5,178 | Moonshot AI | Modified MIT |
| 127 | Qwen3.5-122B-A10B阿里巴巴 | 1459.00 | +/-7 | 7,776 | 阿里巴巴 | Apache 2.0 |
| 128 | GPT-4.5OpenAI | 1459.00 | +/-13 | 1,939 | OpenAI | Proprietary |
| 129 | Grok 4 FastxAI | 1458.00 | +/-17 | 1,180 | xAI | Proprietary |
| 130 | GLM-4.6智谱AI | 1458.00 | +/-7 | 7,392 | 智谱AI | MIT |
| 131 | Qwen3-Coder-480B-A35B阿里巴巴 | 1458.00 | +/-9 | 4,794 | 阿里巴巴 | Apache 2.0 |
| 132 | Gemini 3.1 Flash-LiteGoogle Deep Mind | 1457.00 | +/-6 | 16,715 | Google Deep Mind | Proprietary |
| 133 | GPT-4.1OpenAI | 1457.00 | +/-7 | 9,149 | OpenAI | Proprietary |
| 134 | DeepSeek-V3.1 (thinking)DeepSeek-AI | 1456.00 | +/-13 | 1,877 | DeepSeek-AI | MIT |
| 135 | GLM-4.5智谱AI | 1455.00 | +/-9 | 4,712 | 智谱AI | MIT |
| 136 | Magistral-Medium-2506MistralAI | 1454.00 | +/-5 | 20,923 | MistralAI | Proprietary |
| 137 | Qwen3-VL-235B-A22B-Instruct (thinking)阿里巴巴 | 1453.00 | +/-14 | 1,614 | 阿里巴巴 | Apache 2.0 |
| 138 | Claude3-Sonnet (thinking-32k)Anthropic | 1452.00 | +/-8 | 6,130 | Anthropic | Proprietary |
| 139 |  Step 3.5 FlashStepFunAI | 1450.00 | +/-6 | 14,324 | StepFunAI | Apache 2.0 |
| 140 | Claude Sonnet 4Anthropic | 1450.00 | +/-7 | 7,271 | Anthropic | Proprietary |
| 141 | Qwen3.5-27B阿里巴巴 | 1450.00 | +/-7 | 7,496 | 阿里巴巴 | Apache 2.0 |
| 142 | solar-pro4Upstage | 1447.00 | +/-23 | 684 | Upstage | Proprietary |
| 143 | DeepSeek-V3.1DeepSeek-AI | 1447.00 | +/-12 | 2,606 | DeepSeek-AI | MIT |
| 144 | mimo-v2-flash (non-thinking)Xiaomi | 1446.00 | +/-6 | 11,928 | Xiaomi | MIT |
| 145 | qwen3-235b-a22b-no-thinkingAlibaba | 1445.00 | +/-8 | 6,903 | Alibaba | Apache 2.0 |
| 146 | Qwen3-Next阿里巴巴 | 1445.00 | +/-9 | 4,734 | 阿里巴巴 | Apache 2.0 |
| 147 | DeepSeek-R1DeepSeek-AI | 1444.00 | +/-12 | 2,317 | DeepSeek-AI | MIT |
| 148 | MiniMax M2.5MiniMaxAI | 1444.00 | +/-7 | 10,816 | MiniMaxAI | Modified MIT |
| 149 | qwen3-235b-a22b-thinking-2507Alibaba | 1443.00 | +/-15 | 1,594 | Alibaba | Apache 2.0 |
| 150 | Grok 3xAI | 1443.00 | +/-8 | 5,349 | xAI | Proprietary |
| 151 | trinity-large-preview Apache 2.0 | 1442.00 | +/-8 | 7,571 | — | — |
| 152 | DeepSeek-V3.1 TerminusDeepSeek-AI | 1440.00 | +/-21 | 771 | DeepSeek-AI | MIT |
| 153 | Qwen3-30B-A3B-2507阿里巴巴 | 1439.00 | +/-9 | 4,599 | 阿里巴巴 | Apache 2.0 |
| 154 | hunyuan-vision-1.5-thinkingTencent | 1439.00 | +/-27 | 422 | Tencent | Proprietary |
| 155 | M2.1MiniMaxAI | 1438.00 | +/-10 | 3,353 | MiniMaxAI | MIT |
| 156 | Grok 4 Fast (fast-reasoning)xAI | 1438.00 | +/-9 | 3,837 | xAI | Proprietary |
| 157 | Step 3.5 FlashStepFunAI | 1437.00 | +/-6 | 16,619 | StepFunAI | Proprietary |
| 158 | Claude 3.5 SonnetAnthropic | 1435.00 | +/-6 | 14,908 | Anthropic | Proprietary |
| 159 | Grok 4xAI | 1435.00 | +/-7 | 7,934 | xAI | Proprietary |
| 160 | Qwen3.5-35B-A3B阿里巴巴 | 1435.00 | +/-7 | 7,967 | 阿里巴巴 | Apache 2.0 |
| 161 | OpenAI o3-mini (high)OpenAI | 1435.00 | +/-12 | 2,596 | OpenAI | Proprietary |
| 162 | GPT-4.1 miniOpenAI | 1433.00 | +/-8 | 6,810 | OpenAI | Proprietary |
| 163 | mistral-medium-2505Mistral | 1433.00 | +/-8 | 5,831 | Mistral | Proprietary |
| 164 | OpenAI o1OpenAI | 1433.00 | +/-10 | 3,973 | OpenAI | Proprietary |
| 165 | OpenAI o4 - miniOpenAI | 1433.00 | +/-7 | 8,596 | OpenAI | Proprietary |
| 166 | ERNIE 5.0百度 | 1432.00 | +/-19 | 914 | 百度 | Proprietary |
| 167 | Qwen3-235B-A22B阿里巴巴 | 1432.00 | +/-9 | 4,306 | 阿里巴巴 | Apache 2.0 |
| 168 | amazon-nova-experimental-chat-12-10Amazon | 1432.00 | +/-21 | 708 | Amazon | Proprietary |
| 169 | nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4Nvidia | 1432.00 | +/-17 | 1,292 | Nvidia | OpenMDW-1.1 |
| 170 | Claude3-SonnetAnthropic | 1431.00 | +/-7 | 7,057 | Anthropic | Proprietary |
| 171 | GPT-5-mini (high)OpenAI | 1431.00 | +/-8 | 5,438 | OpenAI | Proprietary |
| 172 | mimo-v2-flash (thinking)Xiaomi | 1430.00 | +/-12 | 2,413 | Xiaomi | MIT |
| 173 | DeepSeek-V3-0324DeepSeek-AI | 1429.00 | +/-7 | 8,281 | DeepSeek-AI | MIT |
| 174 | Gemini 2.5 Flash-Preview-09-2025Google Deep Mind | 1428.00 | +/-8 | 6,754 | Google Deep Mind | Proprietary |
| 175 | GLM-4.5-Air智谱AI | 1427.00 | +/-8 | 6,005 | 智谱AI | MIT |
| 176 | GLM-4.7-Flash智谱AI | 1425.00 | +/-11 | 2,660 | 智谱AI | MIT |
| 177 | Gemini 2.5 FlashGoogle Deep Mind | 1424.00 | +/-4 | 25,667 | Google Deep Mind | Proprietary |
| 178 | Qwen3-Next (thinking)阿里巴巴 | 1422.00 | +/-11 | 2,645 | 阿里巴巴 | Apache 2.0 |
| 179 | amazon-nova-experimental-chat-11-10Amazon | 1419.00 | +/-8 | 5,267 | Amazon | Proprietary |
| 180 | OpenAI o3-miniOpenAI | 1417.00 | +/-6 | 9,383 | OpenAI | Proprietary |
| 181 | GLM-4.6V智谱AI | 1416.00 | +/-25 | 535 | 智谱AI | MIT |
| 182 | minimax-m1MiniMax | 1416.00 | +/-8 | 6,331 | MiniMax | Apache 2.0 |
| 183 | OpenAI o1OpenAI | 1416.00 | +/-9 | 5,123 | OpenAI | Proprietary |
| 184 | trinity-large-thinking Apache 2.0 | 1414.00 | +/-8 | 8,121 | — | — |
| 185 | Mistral-Small-3.2MistralAI | 1412.00 | +/-10 | 3,329 | MistralAI | Apache 2.0 |
| 186 | intellect-3 MIT | 1412.00 | +/-19 | 971 | — | — |
| 187 | amazon-nova-experimental-chat-10-20Amazon | 1411.00 | +/-12 | 2,269 | Amazon | Proprietary |
| 188 | ling-flash-2.0 AntGroup | 1411.00 | +/-15 | 1,514 | Group | MIT |
| 189 | Step3StepFunAI | 1410.00 | +/-17 | 1,208 | StepFunAI | Apache 2.0 |
| 190 | nvidia-nemotron-3-super-120b-a12bNvidia | 1409.00 | +/-14 | 1,776 | Nvidia | NVIDIA Open Model |
| 191 | Qwen3-32B阿里巴巴 | 1407.00 | +/-24 | 513 | 阿里巴巴 | Apache 2.0 |
| 192 | GLM-4.5V智谱AI | 1404.00 | +/-19 | 968 | 智谱AI | MIT |
| 193 | nvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia | 1403.00 | +/-22 | 653 | Nvidia | Nvidia Open |
| 194 | Qwen2.5-Max阿里巴巴 | 1402.00 | +/-8 | 5,076 | 阿里巴巴 | Proprietary |
| 195 | Hunyuan-T1腾讯AI实验室 | 1401.00 | +/-20 | 799 | 腾讯AI实验室 | Proprietary |
| 196 | hunyuan-turbos-20250226Tencent | 1399.00 | +/-31 | 275 | Tencent | Proprietary |
| 197 | Claude 3.5 SonnetAnthropic | 1399.00 | +/-7 | 13,607 | Anthropic | Proprietary |
| 198 | Gemini 2.5 Flash-Lite-Preview-09-2025 (no-thinking)Google Deep Mind | 1398.00 | +/-6 | 9,575 | Google Deep Mind | Proprietary |
| 199 | granite-4.2-30bIBM | 1396.00 | +/-21 | 824 | IBM | Apache 2.0 |
| 200 | Nova 2 Lite亚马逊 | 1394.00 | +/-12 | 2,498 | 亚马逊 | Proprietary |
| 201 | hunyuan-turbos-20250416Tencent | 1394.00 | +/-14 | 1,758 | Tencent | Proprietary |
| 202 | mercury-2 InceptionAI | 1394.00 | +/-21 | 758 | AI | Proprietary |
| 203 | OpenAI o3-mini (high)OpenAI | 1393.00 | +/-10 | 3,153 | OpenAI | Proprietary |
| 204 | amazon-nova-experimental-chat-10-09Amazon | 1392.00 | +/-24 | 543 | Amazon | Proprietary |
| 205 | llama-3.1-nemotron-ultra-253b-v1Nvidia | 1391.00 | +/-30 | 367 | Nvidia | Nvidia Open Model |
| 206 | GPT OSS 120BOpenAI | 1391.00 | +/-8 | 6,336 | OpenAI | Apache 2.0 |
| 207 | ring-flash-2.0 AntGroup | 1391.00 | +/-15 | 1,489 | Group | MIT |
| 208 |  C4AI Command A (202503)CohereAI | 1389.00 | +/-6 | 10,130 | CohereAI | CC-BY-NC-4.0 |
| 209 | DeepSeek-V3DeepSeek-AI | 1387.00 | +/-10 | 3,280 | DeepSeek-AI | DeepSeek |
| 210 | Magistral-Medium-2506MistralAI | 1387.00 | +/-12 | 2,233 | MistralAI | Proprietary |
| 211 | OpenAI o1-miniOpenAI | 1387.00 | +/-7 | 8,478 | OpenAI | Proprietary |
| 212 | grok-3-mini-betaxAI | 1386.00 | +/-9 | 4,083 | xAI | Proprietary |
| 213 | Qwen3-30B-A3B阿里巴巴 | 1386.00 | +/-9 | 4,492 | 阿里巴巴 | Apache 2.0 |
| 214 | Claude 3.5 HaikuAnthropic | 1385.00 | +/-6 | 11,133 | Anthropic | Proprietary |
| 215 | GPT-5-Nano (high)OpenAI | 1384.00 | +/-15 | 1,664 | OpenAI | Proprietary |
| 216 | QwQ-32B阿里巴巴 | 1383.00 | +/-9 | 4,008 | 阿里巴巴 | Apache 2.0 |
| 217 | Gemini 2.5 Flash-Lite (thinking)Google Deep Mind | 1383.00 | +/-8 | 5,942 | Google Deep Mind | Proprietary |
| 218 | MiniMax M2MiniMaxAI | 1383.00 | +/-15 | 1,517 | MiniMaxAI | Apache 2.0 |
| 219 | olmo-3.1-32b-instructAi2 | 1381.00 | +/-12 | 2,376 | Ai2 | Apache 2.0 |
| 220 | granite-4.2-3bIBM | 1380.00 | +/-22 | 798 | IBM | Apache 2.0 |
| 221 | qwen-plus-0125Alibaba | 1379.00 | +/-18 | 893 | Alibaba | Proprietary |
| 222 | llama-3.1-405b-instruct-bf16Meta | 1376.00 | +/-8 | 6,249 | Meta | Llama 3.1 Community |
| 223 | deepseek-v2.5-1210DeepSeek | 1374.00 | +/-17 | 1,079 | DeepSeek | DeepSeek |
| 224 | GPT-4.1 nanoOpenAI | 1374.00 | +/-19 | 807 | OpenAI | Proprietary |
| 225 | Llama 4 Maverick InstructFacebook AI研究实验室 | 1373.00 | +/-7 | 6,933 | Facebook AI研究实验室 | Llama 4 |
| 226 | hunyuan-turbo-0110Tencent | 1371.00 | +/-30 | 299 | Tencent | Proprietary |
| 227 | step-2-16k-exp-202412StepFun | 1371.00 | +/-20 | 737 | StepFun | Proprietary |
| 228 | mercury InceptionAI | 1371.00 | +/-29 | 392 | AI | Proprietary |
| 229 | GPT-4oOpenAI | 1369.00 | +/-6 | 19,526 | OpenAI | Proprietary |
| 230 | GPT OSS 20BOpenAI | 1369.00 | +/-13 | 2,109 | OpenAI | Apache 2.0 |
| 231 | athene-v2-chat NexusFlow | 1369.00 | +/-9 | 4,019 | — | — |
| 232 | yi-lightning Proprietary | 1369.00 | +/-10 | 4,316 | — | — |
| 233 | llama-3.1-405b-instruct-fp8Meta | 1369.00 | +/-7 | 9,714 | Meta | Llama 3.1 Community |
| 234 | DeepSeek V2.5DeepSeek-AI | 1368.00 | +/-9 | 4,252 | DeepSeek-AI | DeepSeek |
| 235 | hunyuan-large-2025-02-10Tencent | 1366.00 | +/-25 | 519 | Tencent | Proprietary |
| 236 | Gemini 2.0 Flash ExperimentalDeepMind | 1364.00 | +/-7 | 6,945 | DeepMind | Proprietary |
| 237 | granite-4.2-8bIBM | 1364.00 | +/-22 | 803 | IBM | Apache 2.0 |
| 238 | olmo-3-32b-thinkAi2 | 1364.00 | +/-19 | 1,011 | Ai2 | Apache 2.0 |
| 239 | llama-3.3-nemotron-49b-super-v1Nvidia | 1362.00 | +/-31 | 286 | Nvidia | Nvidia |
| 240 | Llama 4 Scout InstructFacebook AI研究实验室 | 1362.00 | +/-9 | 5,213 | Facebook AI研究实验室 | Llama |
| 241 | Mistral-Small-3.1-24B-Instruct-2503MistralAI | 1361.00 | +/-8 | 6,081 | MistralAI | Apache 2.0 |
| 242 | nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia | 1361.00 | +/-10 | 3,259 | Nvidia | NVIDIA Open Model |
| 243 | GPT-4oOpenAI | 1360.00 | +/-8 | 7,318 | OpenAI | Proprietary |
| 244 | Grok 2xAI | 1358.00 | +/-7 | 10,368 | xAI | Proprietary |
| 245 | Gemma 3 - 27B (IT)Google Deep Mind | 1358.00 | +/-7 | 7,961 | Google Deep Mind | Gemma |
| 246 | hunyuan-large-visionTencent | 1357.00 | +/-19 | 952 | Tencent | Proprietary |
| 247 | qwen2.5-plus-1127Alibaba | 1357.00 | +/-14 | 1,553 | Alibaba | Proprietary |
| 248 | Gemini 1.5 ProGoogle Deep Mind | 1356.00 | +/-7 | 9,175 | Google Deep Mind | Proprietary |
| 249 | Qwen2.5-VL-72B-Instruct阿里巴巴 | 1355.00 | +/-8 | 6,688 | 阿里巴巴 | Qwen |
| 250 | Claude3-OpusAnthropic | 1355.00 | +/-6 | 33,748 | Anthropic | Proprietary |
| 251 | mistral-large-2407Mistral | 1354.00 | +/-8 | 7,589 | Mistral | Mistral Research |
| 252 | granite-4.1-8bIBM | 1354.00 | +/-20 | 1,070 | IBM | Apache 2.0 |
| 253 | qwen-max-0919Alibaba | 1353.00 | +/-11 | 2,756 | Alibaba | Qwen |
| 254 | step-1o-turbo-202506StepFun | 1352.00 | +/-15 | 1,485 | StepFun | Proprietary |
| 255 | glm-4-plusZhipu AI | 1352.00 | +/-9 | 4,449 | Zhipu AI | Proprietary |
| 256 | athene-70b-0725 CC-BY-NC-4.0 | 1350.00 | +/-11 | 3,122 | — | — |
| 257 | GPT-4o miniOpenAI | 1348.00 | +/-7 | 10,926 | OpenAI | Proprietary |
| 258 | gpt-4-turbo-2024-04-09OpenAI | 1347.00 | +/-7 | 17,104 | OpenAI | Proprietary |
| 259 | Gemini 1.5 ProGoogle Deep Mind | 1347.00 | +/-8 | 12,747 | Google Deep Mind | Proprietary |
| 260 | mistral-large-2411Mistral | 1346.00 | +/-9 | 4,212 | Mistral | MRL |
| 261 | Llama3.3-70B-InstructFacebook AI研究实验室 | 1346.00 | +/-7 | 8,718 | Facebook AI研究实验室 | Llama-3.3 |
| 262 | amazon-nova-pro-v1.0Amazon | 1343.00 | +/-9 | 3,853 | Amazon | Proprietary |
| 263 | Gemini 2.0 Flash-LiteDeepMind | 1343.00 | +/-10 | 3,474 | DeepMind | Proprietary |
| 264 | deepseek-coder-v2DeepSeek | 1342.00 | +/-12 | 2,671 | DeepSeek | DeepSeek License |
| 265 | Qwen2.5-Coder-32B-Instruct阿里巴巴 | 1342.00 | +/-19 | 873 | 阿里巴巴 | Apache 2.0 |
| 266 | olmo-3.1-32b-thinkAi2 | 1340.00 | +/-16 | 1,512 | Ai2 | Apache 2.0 |
| 267 | GPT-4OpenAI | 1340.00 | +/-7 | 15,605 | OpenAI | Proprietary |
| 268 | gemini-advanced-0514Google | 1337.00 | +/-9 | 8,138 | Proprietary | |
| 269 | grok-2-mini-2024-08-13xAI | 1335.00 | +/-7 | 8,652 | xAI | Proprietary |
| 270 | Llama3.1-70B-InstructFacebook AI研究实验室 | 1333.00 | +/-7 | 9,389 | Facebook AI研究实验室 | Llama 3.1 Community |
| 271 | GPT-4OpenAI | 1332.00 | +/-8 | 15,289 | OpenAI | Proprietary |
| 272 | hunyuan-standard-2025-02-10Tencent | 1332.00 | +/-24 | 549 | Tencent | Proprietary |
| 273 | glm-4-plus-0111Zhipu | 1330.00 | +/-18 | 894 | Zhipu | Proprietary |
| 274 | GPT-4OpenAI | 1329.00 | +/-9 | 8,306 | OpenAI | Proprietary |
| 275 | ibm-granite-h-smallIBM | 1329.00 | +/-17 | 1,255 | IBM | Apache 2.0 |
| 276 | Llama3.1-70B-InstructFacebook AI研究实验室 | 1328.00 | +/-15 | 1,312 | Facebook AI研究实验室 | Llama 3.1 |
| 277 | Claude3-SonnetAnthropic | 1318.00 | +/-7 | 18,888 | Anthropic | Proprietary |
| 278 | Gemma 3 - 12B (IT)Google Deep Mind | 1316.00 | +/-23 | 543 | Google Deep Mind | Gemma |
| 279 | gemini-1.5-flash-002Google | 1316.00 | +/-8 | 5,892 | Proprietary | |
| 280 | reka-core-20240904 Proprietary | 1315.00 | +/-15 | 1,216 | — | — |
| 281 | GPT-4OpenAI | 1314.00 | +/-8 | 13,719 | OpenAI | Proprietary |
| 282 | Mistral Small 24B Instruct 2501MistralAI | 1312.00 | +/-12 | 2,083 | MistralAI | Apache 2.0 |
| 283 | jamba-1.5-large Jamba Open | 1312.00 | +/-15 | 1,440 | — | — |
| 284 | llama-3.1-nemotron-51b-instructNvidia | 1312.00 | +/-22 | 665 | Nvidia | Llama 3.1 |
| 285 | gemini-1.5-flash-001Google | 1309.00 | +/-8 | 10,680 | Proprietary | |
| 286 | GLM4智谱AI | 1309.00 | +/-14 | 1,718 | 智谱AI | Proprietary |
| 287 | nemotron-4-340b-instructNvidia | 1308.00 | +/-11 | 3,254 | Nvidia | NVIDIA Open Model |
| 288 | llama-3.1-tulu-3-70bAi2 | 1308.00 | +/-24 | 450 | Ai2 | Llama 3.1 |
| 289 | Gemma-3n-E4BGoogle Deep Mind | 1307.00 | +/-10 | 3,488 | Google Deep Mind | Gemma |
| 290 |  Phi-4-reasoningMicrosoft Azure | 1306.00 | +/-10 | 3,305 | Microsoft Azure | MIT |
| 291 | Llama3-70B-InstructFacebook AI研究实验室 | 1306.00 | +/-7 | 28,126 | Facebook AI研究实验室 | Llama 3 Community |
| 292 | amazon-nova-lite-v1.0Amazon | 1306.00 | +/-10 | 3,060 | Amazon | Proprietary |
| 293 | gemma-2-27b-itGoogle | 1305.00 | +/-6 | 12,088 | Gemma license | |
| 294 | Claude3-HaikuAnthropic | 1301.00 | +/-7 | 20,898 | Anthropic | Proprietary |
| 295 | hunyuan-standard-256kTencent | 1301.00 | +/-24 | 497 | Tencent | Proprietary |
| 296 | Qwen2-72B-Instruct阿里巴巴 | 1297.00 | +/-9 | 6,249 | 阿里巴巴 | Qianwen LICENSE |
| 297 | mistral-large-2402Mistral | 1295.00 | +/-9 | 10,418 | Mistral | Proprietary |
| 298 | C4AI Aya Vision 32BCohereAI | 1292.00 | +/-9 | 4,685 | CohereAI | CC-BY-NC-4.0 |
| 299 | reka-flash-20240904 Proprietary | 1291.00 | +/-15 | 1,207 | — | — |
| 300 | amazon-nova-micro-v1.0Amazon | 1288.00 | +/-10 | 2,981 | Amazon | Proprietary |
| 301 | Llama3.1-8B-InstructFacebook AI研究实验室 | 1288.00 | +/-26 | 478 | Facebook AI研究实验室 | Apache 2.0 |
| 302 | command-r-08-2024Cohere | 1281.00 | +/-13 | 1,783 | Cohere | CC-BY-NC-4.0 |
| 303 | command-r-plus-08-2024Cohere | 1280.00 | +/-14 | 1,675 | Cohere | CC-BY-NC-4.0 |
| 304 | olmo-2-0325-32b-instructAi2 | 1280.00 | +/-27 | 427 | Ai2 | Apache-2.0 |
| 305 | Qwen1.5-110B-Chat阿里巴巴 | 1280.00 | +/-10 | 4,763 | 阿里巴巴 | Qianwen LICENSE |
| 306 | reka-flash-21b-20240226-online Proprietary | 1278.00 | +/-13 | 2,879 | — | — |
| 307 | Mixtral-8x22B-Instruct-v0.1MistralAI | 1277.00 | +/-9 | 8,780 | MistralAI | Apache 2.0 |
| 308 | Qwen1.5-72B-Chat阿里巴巴 | 1275.00 | +/-10 | 6,370 | 阿里巴巴 | Qianwen LICENSE |
| 309 | gpt-3.5-turbo-0125OpenAI | 1275.00 | +/-8 | 11,130 | OpenAI | Proprietary |
| 310 | ministral-8b-2410Mistral | 1274.00 | +/-19 | 838 | Mistral | MRL |
| 311 | Gemma 3 - 4B (IT)Google Deep Mind | 1274.00 | +/-24 | 605 | Google Deep Mind | Gemma |
| 312 | C4AI Command R+CohereAI | 1273.00 | +/-8 | 13,937 | CohereAI | CC-BY-NC-4.0 |
| 313 | gemini-1.5-flash-8b-001Google | 1272.00 | +/-8 | 6,069 | Proprietary | |
| 314 | gemma-2-9b-it-simpo MIT | 1271.00 | +/-15 | 1,471 | — | — |
| 315 | gemma-2-9b-itGoogle | 1270.00 | +/-7 | 8,921 | Gemma license | |
| 316 | reka-flash-21b-20240226 Proprietary | 1267.00 | +/-11 | 4,748 | — | — |
| 317 | jamba-1.5-mini Jamba Open | 1265.00 | +/-15 | 1,352 | — | — |
| 318 | mistral-mediumMistral | 1262.00 | +/-10 | 5,149 | Mistral | Proprietary |
| 319 | gpt-3.5-turbo-1106OpenAI | 1262.00 | +/-16 | 2,121 | OpenAI | Proprietary |
| 320 | qwen1.5-32b-chatAlibaba | 1262.00 | +/-11 | 3,930 | Alibaba | Qianwen LICENSE |
| 321 | Llama3.1-8B-InstructFacebook AI研究实验室 | 1260.00 | +/-8 | 8,582 | Facebook AI研究实验室 | Llama 3.1 Community |
| 322 | C4AI Aya Vision 8BCohereAI | 1255.00 | +/-15 | 1,567 | CohereAI | CC-BY-NC-4.0 |
| 323 | llama-3.1-tulu-3-8bAi2 | 1253.00 | +/-25 | 476 | Ai2 | Llama 3.1 |
| 324 | Llama3-8B-InstructFacebook AI研究实验室 | 1253.00 | +/-8 | 18,374 | Facebook AI研究实验室 | Llama 3 Community |
| 325 | dbrx-instruct-preview DBRX LICENSE | 1251.00 | +/-11 | 5,502 | — | — |
| 326 | granite-3.1-2b-instructIBM | 1249.00 | +/-25 | 508 | IBM | Apache 2.0 |
| 327 | Gemini-proDeepMind | 1249.00 | +/-24 | 678 | DeepMind | Proprietary |
| 328 |  InternLM2-Base-20B上海人工智能实验室 | 1249.00 | +/-14 | 1,684 | 上海人工智能实验室 | — |
| 329 |  Yi-1.5-34B零一万物 | 1248.00 | +/-10 | 3,841 | 零一万物 | — |
| 330 | zephyr-orpo-141b-A35b-v0.1 Apache 2.0 | 1245.00 | +/-21 | 831 | — | — |
| 331 | command-rCohere | 1243.00 | +/-9 | 9,645 | Cohere | CC-BY-NC-4.0 |
| 332 | granite-3.0-8b-instructIBM | 1240.00 | +/-18 | 1,108 | IBM | Apache 2.0 |
| 333 | Qwen1.5-14B-Chat阿里巴巴 | 1239.00 | +/-13 | 3,208 | 阿里巴巴 | Qianwen LICENSE |
| 334 | mixtral-8x7b-instruct-v0.1Mistral | 1239.00 | +/-8 | 11,784 | Mistral | Apache 2.0 |
| 335 | gemini-pro-dev-apiGoogle | 1239.00 | +/-14 | 2,681 | Proprietary | |
| 336 | starling-lm-7b-beta Apache-2.0 | 1235.00 | +/-13 | 2,948 | — | — |
| 337 | Phi-3-medium 14B-previewMicrosoft Azure | 1231.00 | +/-10 | 3,973 | Microsoft Azure | MIT |
| 338 | openchat-3.5-0106 Apache-2.0 | 1230.00 | +/-14 | 2,005 | — | — |
| 339 | snowflake-arctic-instruct Apache 2.0 | 1224.00 | +/-11 | 5,734 | — | — |
| 340 | DeepSeek LLM 67B ChatDeepSeek-AI | 1218.00 | +/-23 | 649 | DeepSeek-AI | DeepSeek License |
| 341 |  Gemma 1.1-7B-ITGoogle Research | 1216.00 | +/-10 | 4,332 | Google Research | Gemma license |
| 342 | LLaMA2 70BFacebook AI研究实验室 | 1215.00 | +/-21 | 805 | Facebook AI研究实验室 | — |
| 343 | Qwen1.5-7B-Chat阿里巴巴 | 1209.00 | +/-21 | 772 | 阿里巴巴 | Qianwen LICENSE |
| 344 | Qwen3-VL-2B阿里巴巴 | 1209.00 | +/-17 | 1,134 | 阿里巴巴 | Apache 2.0 |
| 345 | starling-lm-7b-alpha CC-BY-NC-4.0 | 1207.00 | +/-16 | 1,397 | — | — |
| 346 | Yi-34B零一万物 | 1205.00 | +/-13 | 2,345 | 零一万物 | — |
| 347 | Phi-3-small 7BMicrosoft Azure | 1205.00 | +/-12 | 3,219 | Microsoft Azure | MIT |
| 348 | openchat-3.5 Apache-2.0 | 1202.00 | +/-20 | 971 | — | — |
| 349 | Qwen-14B-Chat阿里巴巴 | 1197.00 | +/-24 | 599 | 阿里巴巴 | Qianwen LICENSE |
| 350 | Phi-3-mini 3.8BMicrosoft Azure | 1197.00 | +/-14 | 1,841 | Microsoft Azure | MIT |
| 351 |  Vicuna 33BLM-SYS | 1193.00 | +/-13 | 2,866 | LM-SYS | — |
| 352 |  WizardLM-70B-V1.0WizardLM Team | 1193.00 | +/-20 | 988 | WizardLM Team | Llama 2 Community |
| 353 | gemma-2-2b-itGoogle | 1192.00 | +/-8 | 7,298 | Gemma license | |
| 354 | Phi-3-mini 3.8BMicrosoft Azure | 1187.00 | +/-12 | 3,449 | Microsoft Azure | MIT |
| 355 | openhermes-2.5-mistral-7b Apache-2.0 | 1186.00 | +/-23 | 589 | — | — |
| 356 | Mistral-7B-Instruct-v0.2MistralAI | 1186.00 | +/-12 | 3,114 | MistralAI | Apache-2.0 |
| 357 | solar-10.7b-instruct-v1.0 CC-BY-NC-4.0 | 1183.00 | +/-27 | 482 | — | — |
| 358 | llama-2-70b-chatMeta | 1179.00 | +/-10 | 5,717 | Meta | Llama 2 Community |
| 359 | llama-3.2-3b-instructMeta | 1176.00 | +/-16 | 1,351 | Meta | Llama 3.2 |
| 360 | nous-hermes-2-mixtral-8x7b-dpo Apache-2.0 | 1175.00 | +/-23 | 575 | — | — |
| 361 | QwQ-32B-Preview阿里巴巴 | 1174.00 | +/-24 | 566 | 阿里巴巴 | Apache 2.0 |
| 362 | Gemma 1.1-2B-ITGoogle Research | 1171.00 | +/-14 | 1,963 | Google Research | Gemma license |
| 363 | mpt-30b-chat CC-BY-NC-SA-4.0 | 1168.00 | +/-34 | 258 | — | — |
| 364 | Gemma 7B - ItGoogle Research | 1167.00 | +/-17 | 1,381 | Google Research | Gemma license |
| 365 | zephyr-7b-alpha MIT | 1167.00 | +/-39 | 201 | — | — |
| 366 | vicuna-13b Llama 2 Community | 1163.00 | +/-14 | 2,389 | — | — |
| 367 |  Baichuan2-13B-Chat百川智能 | 1162.00 | +/-13 | 2,626 | 百川智能 | Llama 2 Community |
| 368 | smollm2-1.7b-instruct Apache 2.0 | 1160.00 | +/-33 | 352 | — | — |
| 369 | CodeLLaMA-34BFacebook AI研究实验室 | 1159.00 | +/-20 | 853 | Facebook AI研究实验室 | Llama 2 Community |
| 370 | Phi-3-mini 3.8BMicrosoft Azure | 1154.00 | +/-13 | 3,886 | Microsoft Azure | MIT |
| 371 | PaLM 2Google Research | 1153.00 | +/-21 | 917 | Google Research | Proprietary |
| 372 | zephyr-7b-beta MIT | 1152.00 | +/-18 | 1,250 | — | — |
| 373 | wizardlm-13bMicrosoft | 1151.00 | +/-22 | 735 | Microsoft | Llama 2 Community |
| 374 | llama-3.2-1b-instructMeta | 1149.00 | +/-16 | 1,346 | Meta | Llama 3.2 |
| 375 | llama2-70b-steerlm-chatNvidia | 1145.00 | +/-28 | 467 | Nvidia | Llama 2 Community |
| 376 | Mistral 7B InstructMistralAI | 1144.00 | +/-20 | 1,032 | MistralAI | Apache 2.0 |
| 377 | Gemma 2B - ItGoogle Research | 1136.00 | +/-22 | 742 | Google Research | Gemma license |
| 378 | vicuna-7b Llama 2 Community | 1131.00 | +/-23 | 726 | — | — |
| 379 | Qwen1.5-4B-Chat阿里巴巴 | 1131.00 | +/-17 | 1,283 | 阿里巴巴 | Qianwen LICENSE |
| 380 | stripedhyena-nous-7b Apache 2.0 | 1127.00 | +/-22 | 704 | — | — |
| 381 | guanaco-33b Non-commercial | 1113.00 | +/-35 | 263 | — | — |
| 382 | olmo-7b-instructAi2 | 1107.00 | +/-22 | 772 | Ai2 | Apache-2.0 |
| 383 | Baichuan2-7B-Chat百川智能 | 1103.00 | +/-14 | 1,956 | 百川智能 | Llama 2 Community |
| 384 | ChatGLM3-6B智谱AI | 1090.00 | +/-26 | 535 | 智谱AI | — |
| 385 |  Koala达摩院 | 1066.00 | +/-24 | 747 | 达摩院 | — |
| 386 | mpt-7b-chat CC-BY-NC-SA-4.0 | 1066.00 | +/-31 | 397 | — | — |
| 387 | RWKV-4-Raven-14B Apache 2.0 | 1059.00 | +/-27 | 505 | — | — |
| 388 | oasst-pythia-12b Apache 2.0 | 1050.00 | +/-25 | 714 | — | — |
| 389 | ChatGLM-6B智谱AI | 1035.00 | +/-27 | 551 | 智谱AI | — |
| 390 | ChatGLM2-6B智谱AI | 1030.00 | +/-35 | 293 | 智谱AI | — |
| 391 | stablelm-tuned-alpha-7b CC-BY-NC-SA-4.0 | 1005.00 | +/-32 | 363 | — | — |
| 392 | alpaca-13b Non-commercial | 999.00 | +/-27 | 626 | — | — |
| 393 | dolly-v2-12b MIT | 962.00 | +/-34 | 396 | — | — |
| 394 | fastchat-t5-3b Apache 2.0 | 908.00 | +/-30 | 428 | — | — |
| 395 | LLaMA 13BFacebook AI研究实验室 | 883.00 | +/-39 | 304 | Facebook AI研究实验室 | Non-commercial |
数据仅供参考，以官方来源为准。模型名称旁的链接可跳转到 DataLearner 模型详情页。
常见问题 (FAQ)
01
什么是 LMArena Coding Arena？
LMArena Coding Arena 是 LMArena 旗下专注于代码能力的匿名评测平台。用户提交真实编程任务（如调试、代码生成、算法实现），系统将不同模型的输出并排展示（隐藏模型名称），由用户投票选出更好的答案，最终通过 Elo 算法汇总形成动态排行榜。
02
Coding Arena 与 SWE-bench、HumanEval 等静态基准有什么区别？
SWE-bench、HumanEval、MBPP 等静态基准使用固定测试集和自动化评分，可重现性强但容易被针对性优化（"刷榜"）。Coding Arena 来自真实用户的开放式需求，测试内容不固定，更能反映模型在实际编程场景中的表现，两者互为补充。
03
国产大模型在代码能力方面表现如何？
DeepSeek、Qwen 等国产模型在 Coding Arena 表现亮眼，已跻身全球前列。DeepSeek 以 MIT 协议开源，Qwen 系列支持中文编程场景，是开发者选择开源代码模型的重要参考。
04
如何用 AI 辅助日常编程工作？
常见场景包括：代码补全与生成、调试、代码审查、单元测试生成，以及跨语言翻译。