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
Gemini 4 Argon (High)
最高得分
1559.00
模型数量
412
数据版本
2026年10月20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 |
|---|---|---|---|---|---|---|
 Gemini 4 Argon (High)Google | 1559.00 | +/-17 | 1,236 | Proprietary | ||
 Claude Fable 5 (High)Anthropic | 1551.00 | +/-7 | 11,128 | Anthropic | Proprietary | |
| Claude Opus 4.7 (High)Anthropic | 1551.00 | +/-6 | 18,580 | Anthropic | Proprietary | |
| 4 |  Muse Wonder (Max)Meta | 1550.00 | +/-17 | 1,234 | Meta | Proprietary |
| 5 | Claude Opus 5.5 (High)Anthropic | 1548.00 | +/-13 | 2,143 | Anthropic | Proprietary |
| 6 | Claude Opus 4.6Anthropic | 1547.00 | +/-5 | 24,104 | Anthropic | Proprietary |
| 7 | Claude Opus 4.6 (high)Anthropic | 1547.00 | +/-5 | 21,348 | Anthropic | Proprietary |
| 8 | Opus 4.7Anthropic | 1546.00 | +/-6 | 18,786 | Anthropic | Proprietary |
| 9 |  GPT-6 Astra (max)OpenAI | 1543.00 | +/-11 | 2,977 | OpenAI | Proprietary |
| 10 | Muse Spark 1.2 (xhigh)Facebook AI研究实验室 | 1542.00 | +/-12 | 2,474 | Facebook AI研究实验室 | Proprietary |
| 11 |  Kimi K3 (max)Moonshot AI | 1539.00 | +/-7 | 8,643 | Moonshot AI | Kimi K3 license |
| 12 | Claude Fable 5.1 (Max)Anthropic | 1539.00 | +/-11 | 3,112 | Anthropic | Proprietary |
| 13 | MiMo-V2.6-ProXiaomi | 1538.00 | +/-18 | 1,102 | Xiaomi | MIT |
| 14 | Muse Spark 1.3 (Max)Meta | 1535.00 | +/-9 | 4,958 | Meta | Proprietary |
| 15 | GPT-6.1 Sol (Max)OpenAI | 1534.00 | +/-16 | 1,462 | OpenAI | Proprietary |
| 16 | Claude Opus 5 (high)Anthropic | 1534.00 | +/-6 | 17,823 | Anthropic | Proprietary |
| 17 | GPT-5.6 Sol (xhigh)OpenAI | 1534.00 | +/-7 | 11,144 | OpenAI | Proprietary |
| 18 | Claude Opus 4.8 (High)Anthropic | 1533.00 | +/-6 | 17,413 | Anthropic | Proprietary |
| 19 | Muse Spark 1.1Facebook AI研究实验室 | 1533.00 | +/-6 | 12,370 | Facebook AI研究实验室 | Proprietary |
| 20 | Claude Opus 4.5 (High, 32K, 20251101)Anthropic | 1531.00 | +/-7 | 7,787 | Anthropic | Proprietary |
| 21 | Claude Sonnet 5.5 (xHigh)Anthropic | 1530.00 | +/-14 | 1,914 | Anthropic | Proprietary |
| 22 | Claude Opus 5 (max)Anthropic | 1530.00 | +/-7 | 8,413 | Anthropic | Proprietary |
| 23 | Claude Opus 4.8Anthropic | 1529.00 | +/-6 | 18,073 | Anthropic | Proprietary |
| 24 | Muse SparkFacebook AI研究实验室 | 1529.00 | +/-10 | 3,941 | Facebook AI研究实验室 | Proprietary |
| 25 | Gemini 3.8 Flash (High)Google | 1529.00 | +/-7 | 10,731 | Proprietary | |
| 26 | Claude Sonnet 4.6Anthropic | 1528.00 | +/-6 | 19,732 | Anthropic | Proprietary |
| 27 |  DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek | 1524.00 | +/-10 | 3,680 | DeepSeek | MIT |
| 28 |  GLM-5.3-FlashZ.ai | 1524.00 | +/-7 | 9,192 | Z.ai | MIT |
| 29 |  Qwen3.7-Max-Preview阿里巴巴 | 1523.00 | +/-18 | 1,163 | 阿里巴巴 | Proprietary |
| 30 | Qwen3.8-MaxAlibaba | 1523.00 | +/-7 | 8,078 | Alibaba | Proprietary |
| 31 | Claude Opus 4.5 (20251101)Anthropic | 1523.00 | +/-5 | 17,969 | Anthropic | Proprietary |
| 32 | Gemini 3.1 Pro PreviewGoogle DeepMind | 1521.00 | +/-5 | 35,474 | Google DeepMind | Proprietary |
| 33 | MiMo-V2.5-Pro小米 | 1521.00 | +/-5 | 20,773 | 小米 | MIT |
| 34 | GLM-5.3 (max)智谱AI | 1521.00 | +/-8 | 5,699 | 智谱AI | MIT |
| 35 | GPT-5.4 (High)OpenAI | 1520.00 | +/-6 | 17,594 | OpenAI | Proprietary |
| 36 | GPT-6 Sol (Max)OpenAI | 1520.00 | +/-11 | 3,167 | OpenAI | Proprietary |
| 37 | Claude Sonnet 5 (High)Anthropic | 1519.00 | +/-6 | 13,564 | Anthropic | Proprietary |
| 38 | Claude Sonnet 4.5 (High, 32K, 20250929)Anthropic | 1519.00 | +/-5 | 19,940 | Anthropic | Proprietary |
| 39 | GPT-5.5 (high)OpenAI | 1519.00 | +/-6 | 19,152 | OpenAI | Proprietary |
| 40 | Gemini 3.7 Flash (high)Google DeepMind | 1519.00 | +/-8 | 7,905 | Google DeepMind | Proprietary |
| 41 | Gemini 3.6 Flash (High)Google | 1518.00 | +/-7 | 10,360 | Proprietary | |
| 42 | GPT-5.6 Terra (xhigh)OpenAI | 1517.00 | +/-6 | 11,966 | OpenAI | Proprietary |
| 43 | Gemini 3 ProGoogle | 1517.00 | +/-7 | 8,805 | Proprietary | |
| 44 | Kimi K2.6Moonshot AI | 1516.00 | +/-7 | 11,093 | Moonshot AI | Modified MIT |
| 45 | GLM-5.2 (max)智谱AI | 1515.00 | +/-6 | 13,716 | 智谱AI | MIT |
| 46 | GPT-5.2 Chat (20260210)OpenAI | 1514.00 | +/-7 | 9,635 | OpenAI | Proprietary |
| 47 |  Dola Seed 2.0 ProBytedance | 1514.00 | +/-5 | 22,067 | Bytedance | Proprietary |
| 48 |  Grok 4.5xAI | 1514.00 | +/-7 | 11,105 | xAI | Proprietary |
| 49 | GPT-5.5 InstantOpenAI | 1513.00 | +/-8 | 7,920 | OpenAI | Proprietary |
| 50 | Qwen3.5 Max Preview阿里巴巴 | 1513.00 | +/-8 | 6,362 | 阿里巴巴 | Proprietary |
| 51 | GLM 5.1智谱AI | 1512.00 | +/-5 | 17,433 | 智谱AI | MIT |
| 52 | Claude Sonnet 4.5 (20250929)Anthropic | 1512.00 | +/-5 | 19,757 | Anthropic | Proprietary |
| 53 |  ERNIE 5.1Baidu | 1512.00 | +/-7 | 10,905 | Baidu | Proprietary |
| 54 | Qwen3.6-Max-Preview阿里巴巴 | 1511.00 | +/-15 | 1,615 | 阿里巴巴 | Proprietary |
| 55 | GPT-5.4OpenAI | 1511.00 | +/-6 | 18,925 | OpenAI | Proprietary |
| 56 | Claude Opus 4.1 (Thinking 16K, 20250805)Anthropic | 1511.00 | +/-6 | 9,923 | Anthropic | Proprietary |
| 57 | MiMo-V2.6-FlashXiaomi | 1511.00 | +/-11 | 3,010 | Xiaomi | MIT |
| 58 | GPT-5.5OpenAI | 1511.00 | +/-6 | 20,053 | OpenAI | Proprietary |
| 59 | Grok 4.20 Beta (Reasoning, 0309)SpaceXAI | 1511.00 | +/-6 | 18,367 | SpaceXAI | Proprietary |
| 60 | Grok 4.6 (high)xAI | 1510.00 | +/-8 | 7,668 | xAI | Proprietary |
| 61 |  Step 5 PreviewStepFun | 1509.00 | +/-13 | 2,074 | StepFun | Proprietary |
| 62 | Grok 4.20 Multi-Agent Beta (0309)SpaceXAI | 1508.00 | +/-6 | 18,007 | SpaceXAI | Proprietary |
| 63 | Gemini 3.5 Flash (High)Google | 1508.00 | +/-6 | 13,845 | Proprietary | |
| 64 | Grok 4.20 Beta 1SpaceXAI | 1508.00 | +/-8 | 7,493 | SpaceXAI | Proprietary |
| 65 | Gemini 3.5 Flash (medium)Google DeepMind | 1506.00 | +/-6 | 13,609 | Google DeepMind | Proprietary |
| 66 | Gemini 3.0 FlashGoogle DeepMind | 1506.00 | +/-8 | 6,591 | Google DeepMind | Proprietary |
| 67 | GPT-6 Luna (Max)OpenAI | 1505.00 | +/-6 | 14,401 | OpenAI | Proprietary |
| 68 | DeepSeek-V4-Pro (High, 20260813)DeepSeek | 1505.00 | +/-11 | 2,804 | DeepSeek | MIT |
| 69 | Claude Opus 4.1 (20250805)Anthropic | 1504.00 | +/-5 | 15,694 | Anthropic | Proprietary |
| 70 | Beam 1.0 501B A23BReflection | 1504.00 | +/-18 | 1,019 | Reflection | Apache 2.0 |
| 71 | Kimi K2.5 (Instant)Moonshot | 1504.00 | +/-14 | 1,871 | Moonshot | Modified MIT |
| 72 | MiMo-V2-ProXiaomi | 1503.00 | +/-8 | 7,265 | Xiaomi | Proprietary |
| 73 | Gemma 4 31BGoogle DeepMind | 1502.00 | +/-15 | 1,417 | Google DeepMind | Apache 2.0 |
| 74 |  Hy3腾讯AI实验室 | 1502.00 | +/-10 | 3,471 | 腾讯AI实验室 | Apache 2.0 |
| 75 | Kimi K2.5 (thinking)Moonshot AI | 1502.00 | +/-5 | 20,757 | Moonshot AI | Modified MIT |
| 76 | Gemini 3.5 Flash-LiteGoogle DeepMind | 1502.00 | +/-7 | 9,921 | Google DeepMind | Proprietary |
| 77 | GPT-5.6 Luna (xhigh)OpenAI | 1501.00 | +/-7 | 11,119 | OpenAI | Proprietary |
| 78 | LongCat-Flash-Chat Exp (2602)Meituan | 1501.00 | +/-7 | 8,152 | Meituan | Proprietary |
| 79 | DeepSeek-V4-ProDeepSeek-AI | 1501.00 | +/-6 | 17,137 | DeepSeek-AI | MIT |
| 80 | Qwen3.7-Plus阿里巴巴 | 1500.00 | +/-6 | 12,169 | 阿里巴巴 | Proprietary |
| 81 | Qwen3.8-27BAlibaba | 1500.00 | +/-8 | 6,853 | Alibaba | Apache 2.0 |
| 82 | Grok 4.1 (Thinking)SpaceXAI | 1500.00 | +/-6 | 15,413 | SpaceXAI | Proprietary |
| 83 | Claude Opus 4 (Thinking 16K, 20250514)Anthropic | 1498.00 | +/-8 | 6,596 | Anthropic | Proprietary |
| 84 | Grok 4.7 (xHigh)SpaceXAI | 1498.00 | +/-11 | 2,956 | SpaceXAI | Proprietary |
| 85 | GLM-5智谱AI | 1498.00 | +/-7 | 7,628 | 智谱AI | MIT |
| 86 | GPT-5.3 ChatOpenAI | 1497.00 | +/-7 | 9,184 | OpenAI | Proprietary |
| 87 |  Mistral Large 4Mistral | 1496.00 | +/-13 | 2,115 | Mistral | Proprietary |
| 88 |  MiniMax M3MiniMaxAI | 1496.00 | +/-6 | 18,701 | MiniMaxAI | MiniMax Community License |
| 89 | Qwen 3.6 Plus Preview阿里巴巴 | 1496.00 | +/-6 | 14,675 | 阿里巴巴 | Proprietary |
| 90 | GPT-5.4 mini (High)OpenAI | 1495.00 | +/-6 | 17,241 | OpenAI | Proprietary |
| 91 | InklingThinking Machines Lab | 1493.00 | +/-7 | 11,531 | Thinking Machines Lab | Apache 2.0 |
| 92 | Grok 4.1SpaceXAI | 1492.00 | +/-6 | 16,022 | SpaceXAI | Proprietary |
| 93 | GPT-5.1 (high)OpenAI | 1492.00 | +/-7 | 8,409 | OpenAI | Proprietary |
| 94 | Qwen3.5-397B-A17B阿里巴巴 | 1491.00 | +/-5 | 26,863 | 阿里巴巴 | Apache 2.0 |
| 95 | MiMo-V2.5小米 | 1491.00 | +/-7 | 13,645 | 小米 | MIT |
| 96 | Gemini 3 Flash (Minimal)Google | 1490.00 | +/-5 | 23,971 | Proprietary | |
| 97 | ERNIE 5.0 (0110)Baidu | 1490.00 | +/-7 | 8,954 | Baidu | Proprietary |
| 98 | GPT-5.2 (high)OpenAI | 1489.00 | +/-6 | 12,238 | OpenAI | Proprietary |
| 99 | MiMo-V2-OmniXiaomi | 1488.00 | +/-9 | 5,891 | Xiaomi | Proprietary |
| 100 | DeepSeek-V4-Pro Preview (High)DeepSeek | 1488.00 | +/-6 | 16,006 | DeepSeek | MIT |
| 101 | Grok 4.3 BetaxAI | 1488.00 | +/-6 | 19,938 | xAI | Proprietary |
| 102 | GLM-5V-Turbo智谱AI | 1488.00 | +/-11 | 2,941 | 智谱AI | Proprietary |
| 103 | Kimi K2 Thinking TurboMoonshot | 1486.00 | +/-5 | 15,270 | Moonshot | Modified MIT |
| 104 |  amazon-nova-experimental-chat (26-02-10)Amazon | 1486.00 | +/-19 | 884 | Amazon | Proprietary |
| 105 | DeepSeek-V4-FlashDeepSeek-AI | 1484.00 | +/-6 | 15,284 | DeepSeek-AI | MIT |
| 106 | GLM-4.7智谱AI | 1484.00 | +/-12 | 2,480 | 智谱AI | MIT |
| 107 | Gemma 4 26B A4BGoogle DeepMind | 1483.00 | +/-15 | 1,444 | Google DeepMind | Apache 2.0 |
| 108 | GPT-5.2OpenAI | 1482.00 | +/-5 | 22,113 | OpenAI | Proprietary |
| 109 | Claude Haiku 4.5 (20251001)Anthropic | 1482.00 | +/-4 | 38,877 | Anthropic | Proprietary |
| 110 | amazon-nova-experimental-chat (26-01-10)Amazon | 1481.00 | +/-21 | 777 | Amazon | Proprietary |
| 111 | Qwen3 Max (Preview)阿里巴巴 | 1480.00 | +/-8 | 5,369 | 阿里巴巴 | Proprietary |
| 112 | MiniMax-M2.7MiniMaxAI | 1480.00 | +/-5 | 24,504 | MiniMaxAI | Modified MIT |
| 113 | DeepSeek-V4-Flash Preview (High)DeepSeek | 1480.00 | +/-6 | 15,231 | DeepSeek | MIT |
| 114 | Muse GlimmerMeta | 1478.00 | +/-18 | 1,117 | Meta | Apache-2.0 |
| 115 | Mistral Medium 3.5MistralAI | 1478.00 | +/-11 | 3,294 | MistralAI | Modified MIT |
| 116 | GPT-5.1OpenAI | 1476.00 | +/-7 | 9,351 | OpenAI | Proprietary |
| 117 | DeepSeek-V3.2 (Thinking)DeepSeek | 1475.00 | +/-7 | 8,880 | DeepSeek | MIT |
| 118 | Claude Sonnet 4 (Thinking 32K, 20250514)Anthropic | 1474.00 | +/-8 | 6,349 | Anthropic | Proprietary |
| 119 | DeepSeek-V3.2-Exp (Thinking)DeepSeek | 1474.00 | +/-13 | 1,930 | DeepSeek | MIT |
| 120 |  NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)Nvidia | 1473.00 | +/-11 | 3,187 | Nvidia | OpenMDW-1.1 |
| 121 | Qwen3-Max (2025-09-23)Alibaba | 1473.00 | +/-13 | 2,029 | Alibaba | Proprietary |
| 122 | LongCat-Flash-ChatMeituan | 1472.00 | +/-13 | 2,209 | Meituan | MIT |
| 123 | Qwen3-235B-A22B-Instruct (2507)Alibaba | 1472.00 | +/-5 | 21,735 | Alibaba | Apache 2.0 |
| 124 | Inkling-SmallThinky | 1472.00 | +/-7 | 9,277 | Thinky | Apache 2.0 |
| 125 | ERNIE-5.0-Preview (1203)Baidu | 1471.00 | +/-13 | 1,990 | Baidu | Proprietary |
| 126 | GPT-5 (high)OpenAI | 1471.00 | +/-8 | 6,398 | OpenAI | Proprietary |
| 127 | Mistral Large 3MistralAI | 1471.00 | +/-5 | 21,555 | MistralAI | Apache 2.0 |
| 128 | DeepSeek V3.2DeepSeek-AI | 1469.00 | +/-6 | 10,916 | DeepSeek-AI | MIT |
| 129 | Kimi K2 Preview (0905)Moonshot | 1468.00 | +/-13 | 2,233 | Moonshot | Modified MIT |
| 130 | DeepSeek V3.2-ExpDeepSeek-AI | 1467.00 | +/-12 | 2,549 | DeepSeek-AI | MIT |
| 131 | ChatGPT-4o Latest (20250326)OpenAI | 1467.00 | +/-5 | 15,870 | OpenAI | Proprietary |
| 132 | Claude Opus 4 (20250514)Anthropic | 1464.00 | +/-7 | 7,830 | Anthropic | Proprietary |
| 133 | Gemini 2.5 ProGoogle | 1464.00 | +/-4 | 26,942 | Proprietary | |
| 134 | DeepSeek-R1 (0528)DeepSeek | 1464.00 | +/-11 | 2,690 | DeepSeek | MIT |
| 135 | Qwen3-VL-235B-A22B-Instruct阿里巴巴 | 1463.00 | +/-13 | 2,309 | 阿里巴巴 | Apache 2.0 |
| 136 | Solar Pro 4Upstage | 1462.00 | +/-8 | 5,940 | Upstage | Proprietary |
| 137 | GPT-5 ChatOpenAI | 1461.00 | +/-8 | 5,987 | OpenAI | Proprietary |
| 138 | Grok 4.1 Fast (reasoning)xAI | 1461.00 | +/-6 | 13,904 | xAI | Proprietary |
| 139 | o3 (2025-04-16)OpenAI | 1460.00 | +/-6 | 11,584 | OpenAI | Proprietary |
| 140 | GPT-5.4 nano (High)OpenAI | 1460.00 | +/-6 | 17,655 | OpenAI | Proprietary |
| 141 | DeepSeek-V3.1-Terminus (Thinking)DeepSeek | 1460.00 | +/-24 | 633 | DeepSeek | MIT |
| 142 | Kimi K2 Preview (0711)Moonshot | 1459.00 | +/-8 | 5,197 | Moonshot | Modified MIT |
| 143 | Qwen3.5-122B-A10B阿里巴巴 | 1458.00 | +/-7 | 8,187 | 阿里巴巴 | Apache 2.0 |
| 144 | GLM-4.6智谱AI | 1458.00 | +/-7 | 7,598 | 智谱AI | MIT |
| 145 | GPT-4.5 Preview (2025-02-27)OpenAI | 1458.00 | +/-13 | 1,939 | OpenAI | Proprietary |
| 146 | Gemini 3.1 Flash-LiteGoogle DeepMind | 1458.00 | +/-6 | 17,848 | Google DeepMind | Proprietary |
| 147 | Grok 4 Fast (Non-Reasoning)SpaceXAI | 1457.00 | +/-17 | 1,185 | SpaceXAI | Proprietary |
| 148 | Qwen3-Coder-480B-A35B阿里巴巴 | 1457.00 | +/-9 | 4,806 | 阿里巴巴 | Apache 2.0 |
| 149 | GPT-4.1 (2025-04-14)OpenAI | 1456.00 | +/-7 | 9,239 | OpenAI | Proprietary |
| 150 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)Nvidia | 1456.00 | +/-19 | 960 | Nvidia | OpenMDW-1.1 |
| 151 | DeepSeek-V3.1 (thinking)DeepSeek-AI | 1455.00 | +/-13 | 1,873 | DeepSeek-AI | MIT |
| 152 | GLM-4.5智谱AI | 1455.00 | +/-9 | 4,741 | 智谱AI | MIT |
| 153 | Mistral Medium 3.1 (2508)Mistral | 1453.00 | +/-5 | 21,549 | Mistral | Proprietary |
| 154 | Hy3 previewTencent | 1453.00 | +/-13 | 2,056 | Tencent | tencent-hunyuan-community |
| 155 | Qwen3-VL-235B-A22B-Instruct (thinking)阿里巴巴 | 1452.00 | +/-14 | 1,638 | 阿里巴巴 | Apache 2.0 |
| 156 | Claude 3.7 Sonnet (Thinking 32K, 20250219)Anthropic | 1452.00 | +/-8 | 6,134 | Anthropic | Proprietary |
| 157 | Qwen3.5-27B阿里巴巴 | 1451.00 | +/-7 | 7,936 | 阿里巴巴 | Apache 2.0 |
| 158 | Step 3.5 FlashStepFunAI | 1449.00 | +/-6 | 15,185 | StepFunAI | Apache 2.0 |
| 159 | Claude Sonnet 4 (20250514)Anthropic | 1449.00 | +/-7 | 7,307 | Anthropic | Proprietary |
| 160 | DeepSeek-V3.1DeepSeek-AI | 1448.00 | +/-12 | 2,604 | DeepSeek-AI | MIT |
| 161 | MiMo-V2-Flash (Non-Thinking)Xiaomi | 1447.00 | +/-6 | 12,452 | Xiaomi | MIT |
| 162 | MiniMax M2.5MiniMaxAI | 1446.00 | +/-6 | 11,341 | MiniMaxAI | Modified MIT |
| 163 | Qwen3-235B-A22B (Non-Thinking)Alibaba | 1444.00 | +/-8 | 6,915 | Alibaba | Apache 2.0 |
| 164 | Qwen3-Next阿里巴巴 | 1444.00 | +/-9 | 4,816 | 阿里巴巴 | Apache 2.0 |
| 165 | DeepSeek-R1DeepSeek-AI | 1444.00 | +/-12 | 2,317 | DeepSeek-AI | MIT |
| 166 | Trinity Large Preview Apache 2.0 | 1443.00 | +/-7 | 7,983 | — | — |
| 167 | Grok 3 Preview (02-24)SpaceXAI | 1442.00 | +/-8 | 5,359 | SpaceXAI | Proprietary |
| 168 | Qwen3-235B-A22B-Thinking (2507)Alibaba | 1441.00 | +/-15 | 1,590 | Alibaba | Apache 2.0 |
| 169 | DeepSeek-V3.1 TerminusDeepSeek-AI | 1440.00 | +/-21 | 771 | DeepSeek-AI | MIT |
| 170 | Grok 4 Fast (reasoning)xAI | 1439.00 | +/-9 | 3,939 | xAI | Proprietary |
| 171 | Qwen3-30B-A3B-Instruct (2507)Alibaba | 1437.00 | +/-9 | 4,615 | Alibaba | Apache 2.0 |
| 172 | MiniMax-M2.1 PreviewMiniMax | 1437.00 | +/-10 | 3,479 | MiniMax | MIT |
| 173 | Hunyuan Vision 1.5 ThinkingTencent | 1436.00 | +/-27 | 419 | Tencent | Proprietary |
| 174 | Claude 3.5 Sonnet (20241022)Anthropic | 1436.00 | +/-6 | 14,908 | Anthropic | Proprietary |
| 175 | Step 3.5 FlashStepFunAI | 1435.00 | +/-6 | 17,723 | StepFunAI | Proprietary |
| 176 | Grok 4 (0709)SpaceXAI | 1435.00 | +/-7 | 8,036 | SpaceXAI | Proprietary |
| 177 | Qwen3.5-35B-A3B阿里巴巴 | 1434.00 | +/-7 | 8,392 | 阿里巴巴 | Apache 2.0 |
| 178 | o3-mini (High)OpenAI | 1434.00 | +/-12 | 2,596 | OpenAI | Proprietary |
| 179 | amazon-nova-experimental-chat (12-10)Amazon | 1434.00 | +/-21 | 724 | Amazon | Proprietary |
| 180 | o4-mini (2025-04-16)OpenAI | 1433.00 | +/-7 | 8,649 | OpenAI | Proprietary |
| 181 | GPT-4.1 mini (2025-04-14)OpenAI | 1433.00 | +/-8 | 6,820 | OpenAI | Proprietary |
| 182 | o1 (2024-12-17)OpenAI | 1433.00 | +/-10 | 3,973 | OpenAI | Proprietary |
| 183 | MiMo-V2-Flash (Thinking)Xiaomi | 1432.00 | +/-12 | 2,488 | Xiaomi | MIT |
| 184 |  Phi-3-medium 14B-preview微软 | 1432.00 | +/-8 | 5,844 | 微软 | Proprietary |
| 185 | ERNIE-5.0-Preview (1022)Baidu | 1432.00 | +/-18 | 932 | Baidu | Proprietary |
| 186 | GPT-5-mini (high)OpenAI | 1432.00 | +/-8 | 5,516 | OpenAI | Proprietary |
| 187 | Qwen3-235B-A22B阿里巴巴 | 1432.00 | +/-9 | 4,322 | 阿里巴巴 | Apache 2.0 |
| 188 | Claude 3.7 Sonnet (20250219)Anthropic | 1431.00 | +/-7 | 7,075 | Anthropic | Proprietary |
| 189 | DeepSeek-V3 (0324)DeepSeek | 1428.00 | +/-7 | 8,334 | DeepSeek | MIT |
| 190 | Gemini 2.5 Flash Preview (09-2025)Google | 1427.00 | +/-7 | 6,913 | Proprietary | |
| 191 | GLM-4.5-Air智谱AI | 1427.00 | +/-8 | 6,101 | 智谱AI | MIT |
| 192 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)Nvidia | 1426.00 | +/-9 | 5,262 | Nvidia | OpenMDW-1.1 |
| 193 | Gemini 2.5 FlashGoogle DeepMind | 1424.00 | +/-4 | 26,365 | Google DeepMind | Proprietary |
| 194 | GLM-4.7-Flash智谱AI | 1423.00 | +/-11 | 2,794 | 智谱AI | MIT |
| 195 | Qwen3-Next (thinking)阿里巴巴 | 1421.00 | +/-11 | 2,668 | 阿里巴巴 | Apache 2.0 |
| 196 | amazon-nova-experimental-chat (11-10)Amazon | 1420.00 | +/-8 | 5,515 | Amazon | Proprietary |
| 197 | OpenAI o3-miniOpenAI | 1416.00 | +/-6 | 9,399 | OpenAI | Proprietary |
| 198 | MiniMax-M1MiniMax | 1416.00 | +/-8 | 6,399 | MiniMax | Apache 2.0 |
| 199 | OpenAI o1OpenAI | 1415.00 | +/-9 | 5,123 | OpenAI | Proprietary |
| 200 | GLM-4.6V智谱AI | 1415.00 | +/-25 | 543 | 智谱AI | MIT |
| 201 | INTELLECT-3 MIT | 1415.00 | +/-18 | 1,005 | — | — |
| 202 | Trinity Large Thinking Apache 2.0 | 1413.00 | +/-7 | 8,550 | — | — |
| 203 | Mistral Small 3.2 (2506)Mistral | 1411.00 | +/-10 | 3,336 | Mistral | Apache 2.0 |
| 204 | amazon-nova-experimental-chat (10-20)Amazon | 1410.00 | +/-12 | 2,339 | Amazon | Proprietary |
| 205 | Step3StepFunAI | 1410.00 | +/-17 | 1,212 | StepFunAI | Apache 2.0 |
| 206 | Ling-flash-2.0 AntGroup | 1409.00 | +/-15 | 1,542 | Group | MIT |
| 207 | NVIDIA-Nemotron-3-Super-120B-A12BNvidia | 1407.00 | +/-13 | 1,882 | Nvidia | NVIDIA Open Model |
| 208 | Qwen3-32B阿里巴巴 | 1406.00 | +/-24 | 513 | 阿里巴巴 | Apache 2.0 |
| 209 | Llama 3.3 Nemotron Super 49B v1.5Nvidia | 1403.00 | +/-22 | 653 | Nvidia | Nvidia Open |
| 210 | GLM-4.5V智谱AI | 1402.00 | +/-19 | 964 | 智谱AI | MIT |
| 211 | Qwen2.5-Max阿里巴巴 | 1402.00 | +/-8 | 5,089 | 阿里巴巴 | Proprietary |
| 212 | Hunyuan T1 (20250711)Tencent | 1401.00 | +/-20 | 804 | Tencent | Proprietary |
| 213 | Granite 4.2 30BIBM | 1400.00 | +/-21 | 850 | IBM | Apache 2.0 |
| 214 | Claude 3.5 Sonnet (20240620)Anthropic | 1399.00 | +/-7 | 13,607 | Anthropic | Proprietary |
| 215 | Hunyuan TurboS (20250226)Tencent | 1399.00 | +/-30 | 275 | Tencent | Proprietary |
| 216 | Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)Google | 1397.00 | +/-6 | 9,854 | Proprietary | |
| 217 | Hunyuan TurboS (20250416)Tencent | 1394.00 | +/-14 | 1,764 | Tencent | Proprietary |
| 218 | Grok 3 Mini (High)SpaceXAI | 1392.00 | +/-10 | 3,163 | SpaceXAI | Proprietary |
| 219 | Amazon Nova 2 LiteAmazon | 1392.00 | +/-12 | 2,581 | Amazon | Proprietary |
| 220 | Mercury 2 InceptionAI | 1392.00 | +/-20 | 801 | AI | Proprietary |
| 221 | amazon-nova-experimental-chat (10-09)Amazon | 1391.00 | +/-24 | 544 | Amazon | Proprietary |
| 222 | Llama 3.1 Nemotron Ultra 253B v1Nvidia | 1391.00 | +/-30 | 367 | Nvidia | Nvidia Open Model |
| 223 | Ring-flash-2.0 AntGroup | 1390.00 | +/-15 | 1,505 | Group | MIT |
| 224 | GPT OSS 120BOpenAI | 1389.00 | +/-8 | 6,410 | OpenAI | Apache 2.0 |
| 225 |  Command A (03-2025)Cohere | 1389.00 | +/-6 | 10,237 | Cohere | CC-BY-NC-4.0 |
| 226 | Magistral Medium (2506)Mistral | 1387.00 | +/-12 | 2,245 | Mistral | Proprietary |
| 227 | DeepSeek-V3DeepSeek-AI | 1387.00 | +/-10 | 3,280 | DeepSeek-AI | DeepSeek |
| 228 | Grok 3 Mini BetaSpaceXAI | 1386.00 | +/-9 | 4,094 | SpaceXAI | Proprietary |
| 229 | OpenAI o1-miniOpenAI | 1386.00 | +/-7 | 8,478 | OpenAI | Proprietary |
| 230 | Claude 3.5 Haiku (20241022)Anthropic | 1386.00 | +/-6 | 11,145 | Anthropic | Proprietary |
| 231 | Qwen3-30B-A3B阿里巴巴 | 1385.00 | +/-9 | 4,505 | 阿里巴巴 | Apache 2.0 |
| 232 | GPT-5 nano (High)OpenAI | 1385.00 | +/-15 | 1,665 | OpenAI | Proprietary |
| 233 | QwQ-32B阿里巴巴 | 1383.00 | +/-9 | 4,016 | 阿里巴巴 | Apache 2.0 |
| 234 | MiniMax M2MiniMaxAI | 1383.00 | +/-15 | 1,550 | MiniMaxAI | Apache 2.0 |
| 235 | Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)Google | 1382.00 | +/-8 | 5,978 | Proprietary | |
| 236 | Olmo 3.1 32B InstructAi2 | 1382.00 | +/-12 | 2,461 | Ai2 | Apache 2.0 |
| 237 | Granite 4.2 3BIBM | 1380.00 | +/-22 | 831 | IBM | Apache 2.0 |
| 238 | Qwen-Plus (0125)Alibaba | 1379.00 | +/-18 | 893 | Alibaba | Proprietary |
| 239 | Llama 3.1 405B Instruct (BF16)Meta | 1376.00 | +/-8 | 6,249 | Meta | Llama 3.1 Community |
| 240 | DeepSeek-V2.5 (1210)DeepSeek | 1374.00 | +/-17 | 1,079 | DeepSeek | DeepSeek |
| 241 | GPT-4.1 nano (2025-04-14)OpenAI | 1373.00 | +/-19 | 807 | OpenAI | Proprietary |
| 242 | Llama 4 Maverick 17B 128E InstructMeta | 1372.00 | +/-7 | 6,939 | Meta | Llama 4 |
| 243 | Step-2 16K Exp (202412)StepFun | 1370.00 | +/-20 | 737 | StepFun | Proprietary |
| 244 | Granite 4.2 8BIBM | 1370.00 | +/-21 | 829 | IBM | Apache 2.0 |
| 245 | Hunyuan Turbo (0110)Tencent | 1370.00 | +/-30 | 299 | Tencent | Proprietary |
| 246 | Llama 3.1 405B Instruct (FP8)Meta | 1369.00 | +/-7 | 9,714 | Meta | Llama 3.1 Community |
| 247 | GPT-4o (2024-05-13)OpenAI | 1369.00 | +/-6 | 19,526 | OpenAI | Proprietary |
| 248 | Athene V2 Chat NexusFlow | 1368.00 | +/-9 | 4,019 | — | — |
| 249 | Yi Lightning Proprietary | 1368.00 | +/-10 | 4,316 | — | — |
| 250 | gpt-oss-20bOpenAI | 1368.00 | +/-13 | 2,112 | OpenAI | Apache 2.0 |
| 251 | DeepSeek V2.5DeepSeek-AI | 1368.00 | +/-9 | 4,252 | DeepSeek-AI | DeepSeek |
| 252 | Hunyuan Large (2025-02-10)Tencent | 1366.00 | +/-25 | 519 | Tencent | Proprietary |
| 253 | Mercury InceptionAI | 1364.00 | +/-28 | 413 | AI | Proprietary |
| 254 | Gemini 2.0 Flash (001)Google | 1363.00 | +/-7 | 6,961 | Proprietary | |
| 255 | Llama 4 Scout 17B 16E InstructMeta | 1363.00 | +/-9 | 5,228 | Meta | Llama |
| 256 | Llama 3.3 Nemotron Super 49B v1Nvidia | 1362.00 | +/-31 | 286 | Nvidia | Nvidia |
| 257 | Mistral Small 3.1 24B Instruct (2503)Mistral | 1361.00 | +/-8 | 6,111 | Mistral | Apache 2.0 |
| 258 | NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)Nvidia | 1361.00 | +/-10 | 3,330 | Nvidia | NVIDIA Open Model |
| 259 | Olmo 3 32B ThinkAi2 | 1360.00 | +/-18 | 1,042 | Ai2 | Apache 2.0 |
| 260 | GPT-4o (2024-08-06)OpenAI | 1360.00 | +/-8 | 7,318 | OpenAI | Proprietary |
| 261 | Hunyuan Large VisionTencent | 1358.00 | +/-19 | 957 | Tencent | Proprietary |
| 262 | Grok 2 (2024-08-13)SpaceXAI | 1358.00 | +/-7 | 10,368 | SpaceXAI | Proprietary |
| 263 | Gemma 3 27B ITGoogle | 1358.00 | +/-7 | 8,024 | Gemma | |
| 264 | Qwen2.5-Plus (1127)Alibaba | 1356.00 | +/-14 | 1,553 | Alibaba | Proprietary |
| 265 | Gemini 1.5 Pro (002)Google | 1356.00 | +/-7 | 9,175 | Proprietary | |
| 266 | Claude 3 Opus (20240229)Anthropic | 1355.00 | +/-6 | 33,748 | Anthropic | Proprietary |
| 267 | Qwen2.5-VL-72B-Instruct阿里巴巴 | 1355.00 | +/-8 | 6,688 | 阿里巴巴 | Qwen |
| 268 | Mistral Large 2 (2407)Mistral | 1354.00 | +/-8 | 7,589 | Mistral | Mistral Research |
| 269 | Granite 4.1 8BIBM | 1353.00 | +/-20 | 1,099 | IBM | Apache 2.0 |
| 270 | Qwen-Max (0919)Alibaba | 1352.00 | +/-11 | 2,756 | Alibaba | Qwen |
| 271 | GLM-4-PlusZhipu AI | 1352.00 | +/-9 | 4,449 | Zhipu AI | Proprietary |
| 272 | Step-1o Turbo (202506)StepFun | 1351.00 | +/-15 | 1,494 | StepFun | Proprietary |
| 273 | Athene 70B (0725) CC-BY-NC-4.0 | 1349.00 | +/-11 | 3,122 | — | — |
| 274 | GPT-4o mini (2024-07-18)OpenAI | 1348.00 | +/-7 | 10,928 | OpenAI | Proprietary |
| 275 | GPT-4 Turbo (2024-04-09)OpenAI | 1347.00 | +/-7 | 17,104 | OpenAI | Proprietary |
| 276 | Gemini 1.5 Pro (001)Google | 1346.00 | +/-8 | 12,747 | Proprietary | |
| 277 | Mistral Large (2411)Mistral | 1346.00 | +/-9 | 4,212 | Mistral | MRL |
| 278 | Llama 3.3 70B InstructMeta | 1346.00 | +/-7 | 8,735 | Meta | Llama-3.3 |
| 279 | Amazon Nova Pro 1.0Amazon | 1343.00 | +/-9 | 3,853 | Amazon | Proprietary |
| 280 | Gemini 2.0 Flash-Lite Preview (02-05)Google | 1342.00 | +/-10 | 3,474 | Proprietary | |
| 281 | DeepSeek-Coder-V2DeepSeek | 1342.00 | +/-12 | 2,671 | DeepSeek | DeepSeek License |
| 282 | Qwen2.5-Coder-32B-Instruct阿里巴巴 | 1342.00 | +/-18 | 873 | 阿里巴巴 | Apache 2.0 |
| 283 | Olmo 3.1 32B ThinkAi2 | 1341.00 | +/-15 | 1,554 | Ai2 | Apache 2.0 |
| 284 | GPT-4 Turbo Preview (1106)OpenAI | 1340.00 | +/-7 | 15,605 | OpenAI | Proprietary |
| 285 | Gemini Advanced (0514)Google | 1337.00 | +/-9 | 8,138 | Proprietary | |
| 286 | Grok 2 mini (2024-08-13)SpaceXAI | 1334.00 | +/-7 | 8,652 | SpaceXAI | Proprietary |
| 287 | Llama 3.1 70B InstructMeta | 1333.00 | +/-7 | 9,389 | Meta | Llama 3.1 Community |
| 288 | GPT-4 Turbo Preview (0125)OpenAI | 1332.00 | +/-8 | 15,289 | OpenAI | Proprietary |
| 289 | Hunyuan Standard (2025-02-10)Tencent | 1331.00 | +/-24 | 549 | Tencent | Proprietary |
| 290 | GLM-4-Plus (0111)Z.ai | 1330.00 | +/-18 | 894 | Z.ai | Proprietary |
| 291 | GPT-4 (0314)OpenAI | 1330.00 | +/-9 | 8,306 | OpenAI | Proprietary |
| 292 | Granite-4.0-H-SmallIBM | 1330.00 | +/-17 | 1,286 | IBM | Apache 2.0 |
| 293 | Llama 3.1 Nemotron 70B InstructNvidia | 1328.00 | +/-15 | 1,312 | Nvidia | Llama 3.1 |
| 294 | Claude 3 Sonnet (20240229)Anthropic | 1318.00 | +/-7 | 18,888 | Anthropic | Proprietary |
| 295 | Gemini 1.5 Flash (002)Google | 1316.00 | +/-8 | 5,892 | Proprietary | |
| 296 | Gemma 3 12B ITGoogle | 1316.00 | +/-23 | 543 | Gemma | |
| 297 | Reka Core (20240904) Proprietary | 1315.00 | +/-15 | 1,216 | — | — |
| 298 | GPT-4 (0613)OpenAI | 1315.00 | +/-8 | 13,719 | OpenAI | Proprietary |
| 299 | Llama 3.1 Nemotron 51B InstructNvidia | 1312.00 | +/-22 | 665 | Nvidia | Llama 3.1 |
| 300 | Mistral Small 24B Instruct (2501)Mistral | 1312.00 | +/-12 | 2,083 | Mistral | Apache 2.0 |
| 301 | Jamba 1.5 Large Jamba Open | 1312.00 | +/-15 | 1,440 | — | — |
| 302 | GLM-4 (0520)Z.ai | 1309.00 | +/-14 | 1,718 | Z.ai | Proprietary |
| 303 | Gemini 1.5 Flash (001)Google | 1309.00 | +/-8 | 10,680 | Proprietary | |
| 304 | Nemotron-4 340B InstructNvidia | 1309.00 | +/-11 | 3,254 | Nvidia | NVIDIA Open Model |
| 305 | Llama 3.1 Tulu 3 70BAi2 | 1308.00 | +/-24 | 450 | Ai2 | Llama 3.1 |
| 306 | Gemma 3n E4B ITGoogle | 1307.00 | +/-10 | 3,487 | Gemma | |
| 307 | Llama 3 70B InstructMeta | 1306.00 | +/-7 | 28,126 | Meta | Llama 3 Community |
| 308 | Phi-4-reasoning微软 | 1306.00 | +/-10 | 3,305 | 微软 | MIT |
| 309 | Amazon Nova Lite 1.0Amazon | 1306.00 | +/-10 | 3,060 | Amazon | Proprietary |
| 310 | Gemma 2 27B ITGoogle | 1304.00 | +/-6 | 12,088 | Gemma license | |
| 311 | Claude 3 Haiku (20240307)Anthropic | 1301.00 | +/-7 | 20,898 | Anthropic | Proprietary |
| 312 | Hunyuan Standard 256KTencent | 1300.00 | +/-24 | 497 | Tencent | Proprietary |
| 313 | Qwen2-72B-Instruct阿里巴巴 | 1297.00 | +/-9 | 6,249 | 阿里巴巴 | Qianwen LICENSE |
| 314 | Mistral Large (2402)Mistral | 1296.00 | +/-8 | 10,418 | Mistral | Proprietary |
| 315 | Aya Expanse 32BCohere | 1292.00 | +/-9 | 4,685 | Cohere | CC-BY-NC-4.0 |
| 316 | Reka Flash (20240904) Proprietary | 1292.00 | +/-15 | 1,207 | — | — |
| 317 | Amazon Nova Micro 1.0Amazon | 1288.00 | +/-10 | 2,981 | Amazon | Proprietary |
| 318 | Granite 3.1 8B InstructIBM | 1288.00 | +/-26 | 478 | IBM | Apache 2.0 |
| 319 | Command R (08-2024)Cohere | 1281.00 | +/-13 | 1,783 | Cohere | CC-BY-NC-4.0 |
| 320 | Command R+ (08-2024)Cohere | 1280.00 | +/-14 | 1,675 | Cohere | CC-BY-NC-4.0 |
| 321 | Qwen1.5-110B-Chat阿里巴巴 | 1280.00 | +/-10 | 4,763 | 阿里巴巴 | Qianwen LICENSE |
| 322 | OLMo 2 32B Instruct (0325)Ai2 | 1280.00 | +/-27 | 427 | Ai2 | Apache-2.0 |
| 323 | Reka Flash 21B (Online, 20240226) Proprietary | 1278.00 | +/-13 | 2,879 | — | — |
| 324 | Mixtral 8x22B Instruct v0.1Mistral | 1278.00 | +/-9 | 8,780 | Mistral | Apache 2.0 |
| 325 | Qwen1.5-72B-Chat阿里巴巴 | 1275.00 | +/-10 | 6,370 | 阿里巴巴 | Qianwen LICENSE |
| 326 | GPT-3.5 Turbo (0125)OpenAI | 1275.00 | +/-8 | 11,130 | OpenAI | Proprietary |
| 327 | Ministral 8B (2410)Mistral | 1274.00 | +/-19 | 838 | Mistral | MRL |
| 328 | Gemma 3 4B ITGoogle | 1273.00 | +/-24 | 605 | Gemma | |
| 329 | Command R+Cohere | 1273.00 | +/-8 | 13,937 | Cohere | CC-BY-NC-4.0 |
| 330 | Gemini 1.5 Flash-8B (001)Google | 1271.00 | +/-8 | 6,069 | Proprietary | |
| 331 | Gemma 2 9B IT SimPO MIT | 1271.00 | +/-15 | 1,471 | — | — |
| 332 | Gemma 2 9B ITGoogle | 1270.00 | +/-7 | 8,921 | Gemma license | |
| 333 | Reka Flash 21B (20240226) Proprietary | 1267.00 | +/-11 | 4,748 | — | — |
| 334 | Jamba 1.5 Mini Jamba Open | 1264.00 | +/-15 | 1,352 | — | — |
| 335 | Mistral MediumMistral | 1263.00 | +/-10 | 5,149 | Mistral | Proprietary |
| 336 | GPT-3.5 Turbo (1106)OpenAI | 1263.00 | +/-15 | 2,121 | OpenAI | Proprietary |
| 337 | Qwen1.5-32B-ChatAlibaba | 1262.00 | +/-11 | 3,930 | Alibaba | Qianwen LICENSE |
| 338 | Llama 3.1 8B InstructMeta | 1260.00 | +/-7 | 8,582 | Meta | Llama 3.1 Community |
| 339 | Aya Expanse 8BCohere | 1255.00 | +/-15 | 1,567 | Cohere | CC-BY-NC-4.0 |
| 340 | Llama 3 8B InstructMeta | 1253.00 | +/-8 | 18,374 | Meta | Llama 3 Community |
| 341 | Llama 3.1 Tulu 3 8BAi2 | 1253.00 | +/-25 | 476 | Ai2 | Llama 3.1 |
| 342 | DBRX Instruct Preview DBRX LICENSE | 1251.00 | +/-11 | 5,502 | — | — |
| 343 | Granite 3.1 2B InstructIBM | 1249.00 | +/-24 | 508 | IBM | Apache 2.0 |
| 344 | InternLM2.5 20B Chat Other | 1249.00 | +/-14 | 1,684 | — | — |
| 345 | Gemini ProGoogle | 1249.00 | +/-24 | 678 | Proprietary | |
| 346 | Yi 1.5 34B Chat Apache-2.0 | 1248.00 | +/-10 | 3,841 | — | — |
| 347 | Zephyr ORPO 141B A35B v0.1 Apache 2.0 | 1245.00 | +/-21 | 831 | — | — |
| 348 | Command RCohere | 1244.00 | +/-9 | 9,645 | Cohere | CC-BY-NC-4.0 |
| 349 | Granite 3.0 8B InstructIBM | 1241.00 | +/-18 | 1,108 | IBM | Apache 2.0 |
| 350 | Qwen1.5-14B-Chat阿里巴巴 | 1240.00 | +/-13 | 3,208 | 阿里巴巴 | Qianwen LICENSE |
| 351 | Mixtral 8x7B Instruct v0.1Mistral | 1240.00 | +/-8 | 11,784 | Mistral | Apache 2.0 |
| 352 | Gemini Pro (Dev API)Google | 1239.00 | +/-14 | 2,681 | Proprietary | |
| 353 | Starling LM 7B Beta Apache-2.0 | 1236.00 | +/-13 | 2,948 | — | — |
| 354 |  Phi-3 Medium 4K InstructMicrosoft | 1231.00 | +/-10 | 3,973 | Microsoft | MIT |
| 355 | OpenChat 3.5 (0106) Apache-2.0 | 1230.00 | +/-14 | 2,005 | — | — |
| 356 | Snowflake Arctic Instruct Apache 2.0 | 1225.00 | +/-11 | 5,734 | — | — |
| 357 | DeepSeek LLM 67B ChatDeepSeek | 1218.00 | +/-23 | 649 | DeepSeek | DeepSeek License |
| 358 | Gemma 1.1 7B ITGoogle | 1216.00 | +/-10 | 4,332 | Gemma license | |
| 359 | Tulu 2 DPO 70B AI2 ImpACT Low-risk | 1215.00 | +/-21 | 805 | — | — |
| 360 | Qwen1.5-7B-Chat阿里巴巴 | 1210.00 | +/-21 | 772 | 阿里巴巴 | Qianwen LICENSE |
| 361 | Granite 3.0 2B InstructIBM | 1210.00 | +/-17 | 1,134 | IBM | Apache 2.0 |
| 362 | Starling LM 7B Alpha CC-BY-NC-4.0 | 1208.00 | +/-16 | 1,397 | — | — |
| 363 | Yi 34B Chat Yi License | 1206.00 | +/-13 | 2,345 | — | — |
| 364 | Phi-3 Small 8K InstructMicrosoft | 1205.00 | +/-12 | 3,219 | Microsoft | MIT |
| 365 | OpenChat 3.5 Apache-2.0 | 1203.00 | +/-19 | 971 | — | — |
| 366 | Qwen-14B-Chat阿里巴巴 | 1198.00 | +/-23 | 599 | 阿里巴巴 | Qianwen LICENSE |
| 367 | Phi-3 Mini 4K Instruct (June 2024)Microsoft | 1197.00 | +/-14 | 1,841 | Microsoft | MIT |
| 368 | Vicuna 33B Non-commercial | 1194.00 | +/-13 | 2,866 | — | — |
| 369 | WizardLM 70BMicrosoft | 1194.00 | +/-20 | 988 | Microsoft | Llama 2 Community |
| 370 | Gemma 2 2B ITGoogle | 1192.00 | +/-8 | 7,298 | Gemma license | |
| 371 | Phi-3 Mini 4K InstructMicrosoft | 1188.00 | +/-12 | 3,449 | Microsoft | MIT |
| 372 | OpenHermes 2.5 Mistral 7B Apache-2.0 | 1187.00 | +/-23 | 589 | — | — |
| 373 | Mistral 7B Instruct v0.2Mistral | 1186.00 | +/-12 | 3,114 | Mistral | Apache-2.0 |
| 374 | SOLAR 10.7B Instruct v1.0Upstage | 1184.00 | +/-27 | 482 | Upstage | CC-BY-NC-4.0 |
| 375 | Llama 2 70B ChatMeta | 1179.00 | +/-10 | 5,717 | Meta | Llama 2 Community |
| 376 | Llama 3.2 3B InstructMeta | 1177.00 | +/-16 | 1,351 | Meta | Llama 3.2 |
| 377 | Nous Hermes 2 Mixtral 8x7B DPO Apache-2.0 | 1176.00 | +/-23 | 575 | — | — |
| 378 | QwQ-32B-Preview阿里巴巴 | 1174.00 | +/-24 | 566 | 阿里巴巴 | Apache 2.0 |
| 379 | Gemma 1.1 2B ITGoogle | 1171.00 | +/-14 | 1,963 | Gemma license | |
| 380 | MPT 30B Chat CC-BY-NC-SA-4.0 | 1168.00 | +/-34 | 258 | — | — |
| 381 | Zephyr 7B Alpha MIT | 1167.00 | +/-39 | 201 | — | — |
| 382 | Gemma 7B ITGoogle | 1167.00 | +/-17 | 1,381 | Gemma license | |
| 383 | Vicuna 13B Llama 2 Community | 1164.00 | +/-14 | 2,389 | — | — |
| 384 | Llama 2 13B ChatMeta | 1163.00 | +/-13 | 2,626 | Meta | Llama 2 Community |
| 385 | SmolLM2 1.7B Instruct Apache 2.0 | 1160.00 | +/-32 | 352 | — | — |
| 386 | Code Llama 34B InstructMeta | 1160.00 | +/-20 | 853 | Meta | Llama 2 Community |
| 387 | Phi-3 Mini 128K InstructMicrosoft | 1155.00 | +/-13 | 3,886 | Microsoft | MIT |
| 388 | PaLM 2Google | 1153.00 | +/-21 | 917 | Proprietary | |
| 389 | Zephyr 7B Beta MIT | 1153.00 | +/-18 | 1,250 | — | — |
| 390 | WizardLM 13BMicrosoft | 1152.00 | +/-22 | 735 | Microsoft | Llama 2 Community |
| 391 | Llama 3.2 1B InstructMeta | 1149.00 | +/-16 | 1,346 | Meta | Llama 3.2 |
| 392 | Llama 2 70B SteerLM ChatNvidia | 1146.00 | +/-28 | 467 | Nvidia | Llama 2 Community |
| 393 | Mistral 7B InstructMistral | 1145.00 | +/-20 | 1,032 | Mistral | Apache 2.0 |
| 394 | Gemma 2B ITGoogle | 1136.00 | +/-22 | 742 | Gemma license | |
| 395 | Vicuna 7B Llama 2 Community | 1132.00 | +/-23 | 726 | — | — |
| 396 | Qwen1.5-4B-Chat阿里巴巴 | 1132.00 | +/-17 | 1,283 | 阿里巴巴 | Qianwen LICENSE |
| 397 | StripedHyena Nous 7B Apache 2.0 | 1128.00 | +/-22 | 704 | — | — |
| 398 | Guanaco 33B Non-commercial | 1114.00 | +/-35 | 263 | — | — |
| 399 | OLMo 7B InstructAi2 | 1107.00 | +/-22 | 772 | Ai2 | Apache-2.0 |
| 400 | Llama 2 7B ChatMeta | 1103.00 | +/-14 | 1,956 | Meta | Llama 2 Community |
| 401 | ChatGLM3 6B Apache-2.0 | 1090.00 | +/-26 | 535 | — | — |
| 402 | Koala 13B Non-commercial | 1066.00 | +/-24 | 747 | — | — |
| 403 | MPT 7B Chat CC-BY-NC-SA-4.0 | 1066.00 | +/-31 | 397 | — | — |
| 404 | RWKV-4 Raven 14B Apache 2.0 | 1060.00 | +/-27 | 505 | — | — |
| 405 | OpenAssistant Pythia 12B Apache 2.0 | 1050.00 | +/-25 | 714 | — | — |
| 406 | ChatGLM 6B Non-commercial | 1036.00 | +/-27 | 551 | — | — |
| 407 | ChatGLM2 6B Apache-2.0 | 1031.00 | +/-34 | 293 | — | — |
| 408 | StableLM Tuned Alpha 7B CC-BY-NC-SA-4.0 | 1005.00 | +/-32 | 363 | — | — |
| 409 | Alpaca 13B Non-commercial | 999.00 | +/-27 | 626 | — | — |
| 410 | Dolly 2.0 12B MIT | 962.00 | +/-33 | 396 | — | — |
| 411 | FastChat-T5 3B Apache 2.0 | 908.00 | +/-30 | 428 | — | — |
| 412 | LLaMA 13BMeta | 883.00 | +/-38 | 304 | Meta | 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。