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 (thinking)
最高得分
1555.00
模型数量
355
数据版本
2026年05月28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 (thinking)Anthropic | 1555.00 | +/-9 | 5,578 | Anthropic | Proprietary | |
| Claude Opus 4.6 (thinking)Anthropic | 1551.00 | +/-7 | 8,335 | Anthropic | Proprietary | |
| Claude Opus 4.6Anthropic | 1546.00 | +/-7 | 9,596 | Anthropic | Proprietary | |
| 4 | Opus 4.7Anthropic | 1546.00 | +/-9 | 5,903 | Anthropic | Proprietary |
| 5 | Claude Opus 4 (thinking-32k)Anthropic | 1530.00 | +/-7 | 7,628 | Anthropic | Proprietary |
| 6 | GLM 5.1智谱AI | 1527.00 | +/-10 | 3,756 | 智谱AI | MIT |
| 7 | Muse SparkFacebook AI研究实验室 | 1526.00 | +/-11 | 3,260 | Facebook AI研究实验室 | Proprietary |
| 8 |  qwen3.7-max-previewAlibaba | 1525.00 | +/-18 | 1,137 | Alibaba | Proprietary |
| 9 |  Gemini 3.1 Pro PreviewGoogle Deep Mind | 1525.00 | +/-7 | 11,296 | Google Deep Mind | Proprietary |
| 10 |  gpt-5.5-highOpenAI | 1522.00 | +/-10 | 4,494 | OpenAI | Proprietary |
| 11 | Claude Sonnet 4.6Anthropic | 1522.00 | +/-8 | 7,216 | Anthropic | Proprietary |
| 12 | gpt-5.4-highOpenAI | 1521.00 | +/-8 | 7,181 | OpenAI | Proprietary |
| 13 | Claude Opus 4Anthropic | 1521.00 | +/-6 | 15,711 | Anthropic | Proprietary |
| 14 | Claude Sonnet 4.5 (thinking-32k)Anthropic | 1520.00 | +/-5 | 17,763 | Anthropic | Proprietary |
| 15 | mimo-v2.5-proXiaomi | 1520.00 | +/-10 | 4,275 | Xiaomi | MIT |
| 16 | Gemini 3.0 Pro (Preview 11-2025)Google Deep Mind | 1519.00 | +/-7 | 8,575 | Google Deep Mind | Proprietary |
| 17 | gpt-5.2-chat-latest-20260210OpenAI | 1518.00 | +/-7 | 8,304 | OpenAI | Proprietary |
| 18 |  ernie-5.1Baidu | 1515.00 | +/-10 | 3,943 | Baidu | Proprietary |
| 19 | Claude Sonnet 4.5Anthropic | 1515.00 | +/-5 | 17,609 | Anthropic | Proprietary |
| 20 | gpt-5.5-instantOpenAI | 1515.00 | +/-8 | 7,212 | OpenAI | Proprietary |
| 21 |  grok-4.20-multi-agent-beta-0309xAI | 1515.00 | +/-7 | 7,631 | xAI | Proprietary |
| 22 | qwen3.5-max-previewAlibaba | 1514.00 | +/-8 | 5,491 | Alibaba | Proprietary |
| 23 |  kimi-k2.6Moonshot | 1514.00 | +/-10 | 4,237 | Moonshot | Modified MIT |
| 24 | GPT-5.4OpenAI | 1513.00 | +/-8 | 7,884 | OpenAI | Proprietary |
| 25 | Opus 4.1 (thinking-16k)Anthropic | 1513.00 | +/-7 | 9,848 | Anthropic | Proprietary |
| 26 | grok-4.20-beta-0309-reasoningxAI | 1512.00 | +/-8 | 7,705 | xAI | Proprietary |
| 27 |  dola-seed-2.0-proBytedance | 1511.00 | +/-7 | 10,045 | Bytedance | Proprietary |
| 28 | grok-4.20-beta1xAI | 1509.00 | +/-8 | 6,203 | xAI | Proprietary |
| 29 | Gemini 3.0 FlashGoogle Deep Mind | 1509.00 | +/-8 | 6,383 | Google Deep Mind | Proprietary |
| 30 | GPT-5.5OpenAI | 1508.00 | +/-9 | 4,672 | OpenAI | Proprietary |
| 31 | gemini-3.5-flashGoogle | 1506.00 | +/-12 | 2,592 | Proprietary | |
| 32 | qwen3.6-max-previewAlibaba | 1506.00 | +/-16 | 1,327 | Alibaba | Proprietary |
| 33 | kimi-k2.5-instantMoonshot | 1505.00 | +/-14 | 1,803 | Moonshot | Modified MIT |
| 34 | Opus 4.1Anthropic | 1505.00 | +/-5 | 15,538 | Anthropic | Proprietary |
| 35 | Kimi K2 ThinkingMoonshot AI | 1503.00 | +/-7 | 9,469 | Moonshot AI | Modified MIT |
| 36 | mimo-v2-proXiaomi | 1503.00 | +/-8 | 6,196 | Xiaomi | Proprietary |
| 37 | longcat-flash-chat-2602-expMeituan | 1503.00 | +/-8 | 6,475 | Meituan | Proprietary |
| 38 |  deepseek-v4-proDeepSeek | 1500.00 | +/-9 | 4,940 | DeepSeek | MIT |
| 39 | Grok 4.1 ThinkingxAI | 1499.00 | +/-6 | 14,270 | xAI | Proprietary |
| 40 | gpt-5.4-mini-highOpenAI | 1499.00 | +/-8 | 6,903 | OpenAI | Proprietary |
| 41 | gemma-4-31bGoogle | 1498.00 | +/-15 | 1,355 | Apache 2.0 | |
| 42 | Claude Opus 4 (thinking-16k)Anthropic | 1498.00 | +/-8 | 6,674 | Anthropic | Proprietary |
| 43 | gpt-5.3-chat-latestOpenAI | 1497.00 | +/-8 | 7,910 | OpenAI | Proprietary |
| 44 | Gemini 3.0 Flash (minimal)Google Deep Mind | 1495.00 | +/-6 | 12,797 | Google Deep Mind | Proprietary |
| 45 | GLM-5智谱AI | 1495.00 | +/-8 | 5,384 | 智谱AI | MIT |
| 46 | deepseek-v4-pro-thinkingDeepSeek | 1494.00 | +/-9 | 4,535 | DeepSeek | MIT |
| 47 | Qwen3.5-397B-A17B阿里巴巴 | 1493.00 | +/-7 | 8,580 | 阿里巴巴 | Apache 2.0 |
| 48 | grok-4.3xAI | 1493.00 | +/-9 | 4,422 | xAI | Proprietary |
| 49 | ERNIE 5.0百度 | 1492.00 | +/-7 | 8,166 | 百度 | Proprietary |
| 50 | qwen3.6-plusAlibaba | 1492.00 | +/-9 | 5,403 | Alibaba | Proprietary |
| 51 | GPT-5.2 Pro (high)OpenAI | 1491.00 | +/-6 | 11,036 | OpenAI | Proprietary |
| 52 | Grok 4.1xAI | 1490.00 | +/-6 | 14,818 | xAI | Proprietary |
| 53 | GPT-5.1 Pro (high)OpenAI | 1490.00 | +/-7 | 8,210 | OpenAI | Proprietary |
| 54 | mimo-v2.5Xiaomi | 1490.00 | +/-9 | 4,584 | Xiaomi | MIT |
| 55 |  amazon-nova-experimental-chat-26-02-10Amazon | 1488.00 | +/-20 | 841 | Amazon | Proprietary |
| 56 | kimi-k2-thinking-turboMoonshot | 1487.00 | +/-6 | 14,116 | Moonshot | Modified MIT |
| 57 | GLM-4.7智谱AI | 1486.00 | +/-12 | 2,411 | 智谱AI | MIT |
| 58 | GPT-5.2OpenAI | 1483.00 | +/-6 | 11,360 | OpenAI | Proprietary |
| 59 | Qwen3 Max (Preview)阿里巴巴 | 1482.00 | +/-8 | 5,366 | 阿里巴巴 | Proprietary |
| 60 | gemma-4-26b-a4bGoogle | 1480.00 | +/-15 | 1,365 | Apache 2.0 | |
| 61 | claude-haiku-4-5-20251001Anthropic | 1479.00 | +/-5 | 18,302 | Anthropic | Proprietary |
| 62 | amazon-nova-experimental-chat-26-01-10Amazon | 1479.00 | +/-21 | 736 | Amazon | Proprietary |
| 63 | deepseek-v4-flashDeepSeek | 1479.00 | +/-9 | 4,780 | DeepSeek | MIT |
| 64 | deepseek-v4-flash-thinkingDeepSeek | 1478.00 | +/-9 | 4,709 | DeepSeek | MIT |
| 65 | MiniMax-M2.7MiniMaxAI | 1475.00 | +/-8 | 6,572 | MiniMaxAI | Modified MIT |
| 66 | qwen3-max-2025-09-23Alibaba | 1475.00 | +/-13 | 2,042 | Alibaba | Proprietary |
| 67 | DeepSeek V3.2 (thinking)DeepSeek-AI | 1475.00 | +/-7 | 8,193 | DeepSeek-AI | MIT |
| 68 | longcat-flash-chatMeituan | 1474.00 | +/-13 | 2,233 | Meituan | MIT |
| 69 | DeepSeek V3.2-Exp (thinking)DeepSeek-AI | 1474.00 | +/-13 | 1,919 | DeepSeek-AI | MIT |
| 70 | GPT-5.1 InstantOpenAI | 1474.00 | +/-7 | 9,130 | OpenAI | Proprietary |
| 71 | Claude Sonnet 4 (thinking-32k)Anthropic | 1473.00 | +/-8 | 6,414 | Anthropic | Proprietary |
| 72 | Qwen3-235B-A22B-2507阿里巴巴 | 1472.00 | +/-5 | 20,628 | 阿里巴巴 | Apache 2.0 |
| 73 | ERNIE 5.0百度 | 1472.00 | +/-13 | 1,960 | 百度 | Proprietary |
| 74 | chatgpt-4o-latest-20250326OpenAI | 1469.00 | +/-5 | 15,865 | OpenAI | Proprietary |
| 75 | DeepSeek V3.2DeepSeek-AI | 1469.00 | +/-7 | 10,179 | DeepSeek-AI | MIT |
| 76 |  Mistral Large 3MistralAI | 1468.00 | +/-7 | 9,554 | MistralAI | Apache 2.0 |
| 77 | kimi-k2-0905-previewMoonshot | 1467.00 | +/-13 | 2,243 | Moonshot | Modified MIT |
| 78 | GPT-5-Pro (high)OpenAI | 1467.00 | +/-8 | 6,360 | OpenAI | Proprietary |
| 79 | DeepSeek V3.2-ExpDeepSeek-AI | 1466.00 | +/-12 | 2,501 | DeepSeek-AI | MIT |
| 80 | Qwen3-VL-235B-A22B-Instruct阿里巴巴 | 1466.00 | +/-13 | 2,315 | 阿里巴巴 | Apache 2.0 |
| 81 | Gemini 2.5 Pro Experimental 03-25Google Deep Mind | 1465.00 | +/-4 | 25,765 | Google Deep Mind | Proprietary |
| 82 | DeepSeek-R1-0528DeepSeek-AI | 1465.00 | +/-11 | 2,728 | DeepSeek-AI | MIT |
| 83 | mimo-v2-omniXiaomi | 1464.00 | +/-21 | 848 | Xiaomi | Proprietary |
| 84 | Claude Opus 4Anthropic | 1464.00 | +/-7 | 7,903 | Anthropic | Proprietary |
| 85 | GPT-5OpenAI | 1464.00 | +/-8 | 5,991 | OpenAI | Proprietary |
| 86 | deepseek-v3.1-terminus-thinkingDeepSeek | 1463.00 | +/-24 | 636 | DeepSeek | MIT |
| 87 | grok-4-1-fast-reasoningxAI | 1462.00 | +/-6 | 12,670 | xAI | Proprietary |
| 88 |  hunyuan-hy3-previewTencent | 1462.00 | +/-15 | 1,648 | Tencent | tencent-hunyuan-community |
| 89 | gpt-5.4-nano-highOpenAI | 1460.00 | +/-8 | 6,894 | OpenAI | Proprietary |
| 90 | Kimi K2Moonshot AI | 1460.00 | +/-8 | 5,244 | Moonshot AI | Modified MIT |
| 91 | GLM-4.6智谱AI | 1460.00 | +/-7 | 7,481 | 智谱AI | MIT |
| 92 | GPT-4.5OpenAI | 1459.00 | +/-13 | 1,939 | OpenAI | Proprietary |
| 93 | gemini-3.1-flash-lite-previewGoogle | 1459.00 | +/-7 | 9,137 | Proprietary | |
| 94 | Grok 4 FastxAI | 1459.00 | +/-16 | 1,249 | xAI | Proprietary |
| 95 | OpenAI o3OpenAI | 1459.00 | +/-6 | 11,756 | OpenAI | Proprietary |
| 96 | qwen3-coder-480b-a35b-instructAlibaba | 1457.00 | +/-9 | 4,849 | Alibaba | Apache 2.0 |
| 97 | DeepSeek-V3.1 (thinking)DeepSeek-AI | 1457.00 | +/-13 | 1,904 | DeepSeek-AI | MIT |
| 98 | gpt-4.1-2025-04-14OpenAI | 1456.00 | +/-7 | 9,316 | OpenAI | Proprietary |
| 99 | Magistral-Medium-2506MistralAI | 1456.00 | +/-5 | 20,392 | MistralAI | Proprietary |
| 100 | qwen3-vl-235b-a22b-thinkingAlibaba | 1455.00 | +/-14 | 1,625 | Alibaba | Apache 2.0 |
| 101 | qwen3.5-122b-a10bAlibaba | 1455.00 | +/-8 | 7,029 | Alibaba | Apache 2.0 |
| 102 | GLM-4.5智谱AI | 1454.00 | +/-9 | 4,772 | 智谱AI | MIT |
| 103 | Claude Sonnet 3.7 (thinking-32k)Anthropic | 1451.00 | +/-8 | 6,191 | Anthropic | Proprietary |
| 104 | Claude Sonnet 4Anthropic | 1449.00 | +/-7 | 7,396 | Anthropic | Proprietary |
| 105 | qwen3.5-27bAlibaba | 1448.00 | +/-8 | 6,863 | Alibaba | Apache 2.0 |
| 106 | DeepSeek-V3.1DeepSeek-AI | 1448.00 | +/-12 | 2,624 | DeepSeek-AI | MIT |
| 107 |  Step 3.5 FlashStepFunAI | 1447.00 | +/-7 | 8,364 | StepFunAI | Apache 2.0 |
| 108 | qwen3-next-80b-a3b-instructAlibaba | 1446.00 | +/-9 | 4,794 | Alibaba | Apache 2.0 |
| 109 | qwen3-235b-a22b-no-thinkingAlibaba | 1446.00 | +/-8 | 6,975 | Alibaba | Apache 2.0 |
| 110 | mimo-v2-flash (non-thinking)Xiaomi | 1445.00 | +/-6 | 11,214 | Xiaomi | MIT |
| 111 | DeepSeek-R1DeepSeek-AI | 1444.00 | +/-12 | 2,317 | DeepSeek-AI | MIT |
| 112 | MiniMax M2.5MiniMaxAI | 1444.00 | +/-7 | 9,266 | MiniMaxAI | Modified MIT |
| 113 | Grok 3xAI | 1443.00 | +/-8 | 5,400 | xAI | Proprietary |
| 114 | qwen3-235b-a22b-thinking-2507Alibaba | 1442.00 | +/-15 | 1,611 | Alibaba | Apache 2.0 |
| 115 | trinity-large-previewArcee AI | 1441.00 | +/-8 | 6,942 | Arcee AI | Apache 2.0 |
| 116 | qwen3-30b-a3b-instruct-2507Alibaba | 1440.00 | +/-9 | 4,660 | Alibaba | Apache 2.0 |
| 117 |  minimax-m2.1-previewMiniMax | 1439.00 | +/-10 | 3,426 | MiniMax | MIT |
| 118 | DeepSeek-V3.1 TerminusDeepSeek-AI | 1439.00 | +/-21 | 778 | DeepSeek-AI | MIT |
| 119 | hunyuan-vision-1.5-thinkingTencent | 1438.00 | +/-27 | 437 | Tencent | Proprietary |
| 120 | grok-4-fast-reasoningxAI | 1437.00 | +/-9 | 3,956 | xAI | Proprietary |
| 121 | qwen3.5-35b-a3bAlibaba | 1437.00 | +/-8 | 7,198 | Alibaba | Apache 2.0 |
| 122 | grok-4-0709xAI | 1436.00 | +/-7 | 8,155 | xAI | Proprietary |
| 123 | amazon-nova-experimental-chat-12-10Amazon | 1435.00 | +/-21 | 704 | Amazon | Proprietary |
| 124 | o3-mini-highOpenAI | 1435.00 | +/-12 | 2,596 | OpenAI | Proprietary |
| 125 | claude-3-5-sonnet-20241022Anthropic | 1434.00 | +/-6 | 14,964 | Anthropic | Proprietary |
| 126 | qwen3-235b-a22bAlibaba | 1433.00 | +/-9 | 4,339 | Alibaba | Apache 2.0 |
| 127 | ERNIE 5.0百度 | 1433.00 | +/-19 | 916 | 百度 | Proprietary |
| 128 | gpt-4.1-mini-2025-04-14OpenAI | 1433.00 | +/-7 | 6,918 | OpenAI | Proprietary |
| 129 | mistral-medium-2505Mistral | 1433.00 | +/-8 | 5,900 | Mistral | Proprietary |
| 130 | o1-2024-12-17OpenAI | 1433.00 | +/-10 | 3,973 | OpenAI | Proprietary |
| 131 | qwen3.5-flashAlibaba | 1432.00 | +/-7 | 8,187 | Alibaba | Proprietary |
| 132 | o4-mini-2025-04-16OpenAI | 1432.00 | +/-7 | 8,721 | OpenAI | Proprietary |
| 133 | mimo-v2-flash (thinking)Xiaomi | 1432.00 | +/-12 | 2,444 | Xiaomi | MIT |
| 134 | gpt-5-mini-highOpenAI | 1430.00 | +/-8 | 5,502 | OpenAI | Proprietary |
| 135 | Claude Sonnet 3.7Anthropic | 1429.00 | +/-7 | 7,146 | Anthropic | Proprietary |
| 136 | DeepSeek-V3-0324DeepSeek-AI | 1429.00 | +/-7 | 8,372 | DeepSeek-AI | MIT |
| 137 | gemini-2.5-flash-preview-09-2025Google | 1429.00 | +/-8 | 6,846 | Proprietary | |
| 138 |  glm-4.5-airZ.ai | 1427.00 | +/-8 | 6,104 | Z.ai | MIT |
| 139 | Gemini 2.5 FlashGoogle Deep Mind | 1424.00 | +/-4 | 25,169 | Google Deep Mind | Proprietary |
| 140 | glm-4.7-flashZ.ai | 1423.00 | +/-11 | 2,687 | Z.ai | MIT |
| 141 | qwen3-next-80b-a3b-thinkingAlibaba | 1421.00 | +/-11 | 2,677 | Alibaba | Apache 2.0 |
| 142 | GLM-4.6V智谱AI | 1420.00 | +/-25 | 536 | 智谱AI | MIT |
| 143 | amazon-nova-experimental-chat-11-10Amazon | 1420.00 | +/-8 | 5,322 | Amazon | Proprietary |
| 144 | o1-previewOpenAI | 1417.00 | +/-9 | 5,123 | OpenAI | Proprietary |
| 145 | trinity-large-thinkingArcee AI | 1416.00 | +/-8 | 6,447 | Arcee AI | Apache 2.0 |
| 146 | minimax-m1MiniMax | 1416.00 | +/-8 | 6,489 | MiniMax | Apache 2.0 |
| 147 | o3-miniOpenAI | 1416.00 | +/-6 | 9,460 | OpenAI | Proprietary |
| 148 | mistral-small-2506Mistral | 1413.00 | +/-10 | 3,360 | Mistral | Apache 2.0 |
| 149 | ling-flash-2.0Ant Group | 1412.00 | +/-15 | 1,528 | Ant Group | MIT |
| 150 | amazon-nova-experimental-chat-10-20Amazon | 1411.00 | +/-12 | 2,293 | Amazon | Proprietary |
| 151 | intellect-3Prime Intellect | 1409.00 | +/-19 | 973 | Prime Intellect | MIT |
| 152 |  nvidia-nemotron-3-super-120b-a12bNvidia | 1409.00 | +/-14 | 1,747 | Nvidia | NVIDIA Open Model |
| 153 | step-3StepFun | 1408.00 | +/-17 | 1,233 | StepFun | Apache 2.0 |
| 154 | qwen3-32bAlibaba | 1408.00 | +/-24 | 513 | Alibaba | Apache 2.0 |
| 155 | nvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia | 1405.00 | +/-22 | 659 | Nvidia | Nvidia Open |
| 156 | glm-4.5vZ.ai | 1405.00 | +/-18 | 991 | Z.ai | MIT |
| 157 | qwen2.5-maxAlibaba | 1403.00 | +/-8 | 5,101 | Alibaba | Proprietary |
| 158 | hunyuan-t1-20250711Tencent | 1400.00 | +/-20 | 805 | Tencent | Proprietary |
| 159 | hunyuan-turbos-20250226Tencent | 1400.00 | +/-31 | 275 | Tencent | Proprietary |
| 160 | claude-3-5-sonnet-20240620Anthropic | 1398.00 | +/-7 | 13,607 | Anthropic | Proprietary |
| 161 | gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle | 1397.00 | +/-7 | 9,678 | Proprietary | |
| 162 | nova-2-liteAmazon | 1397.00 | +/-12 | 2,519 | Amazon | Proprietary |
| 163 | mercury-2Inception AI | 1396.00 | +/-21 | 768 | Inception AI | Proprietary |
| 164 | hunyuan-turbos-20250416Tencent | 1394.00 | +/-14 | 1,776 | Tencent | Proprietary |
| 165 | llama-3.1-nemotron-ultra-253b-v1Nvidia | 1391.00 | +/-30 | 367 | Nvidia | Nvidia Open Model |
| 166 | GPT OSS 120BOpenAI | 1391.00 | +/-8 | 6,494 | OpenAI | Apache 2.0 |
| 167 | ring-flash-2.0Ant Group | 1391.00 | +/-15 | 1,539 | Ant Group | MIT |
| 168 | grok-3-mini-highxAI | 1390.00 | +/-10 | 3,296 | xAI | Proprietary |
| 169 |  command-a-03-2025Cohere | 1390.00 | +/-6 | 10,219 | Cohere | CC-BY-NC-4.0 |
| 170 | amazon-nova-experimental-chat-10-09Amazon | 1389.00 | +/-24 | 552 | Amazon | Proprietary |
| 171 | o1-miniOpenAI | 1388.00 | +/-7 | 8,478 | OpenAI | Proprietary |
| 172 | deepseek-v3DeepSeek | 1388.00 | +/-10 | 3,280 | DeepSeek | DeepSeek |
| 173 | qwen3-30b-a3bAlibaba | 1387.00 | +/-9 | 4,531 | Alibaba | Apache 2.0 |
| 174 | grok-3-mini-betaxAI | 1387.00 | +/-9 | 4,255 | xAI | Proprietary |
| 175 | magistral-medium-2506Mistral | 1386.00 | +/-12 | 2,250 | Mistral | Proprietary |
| 176 | qwq-32bAlibaba | 1385.00 | +/-9 | 4,046 | Alibaba | Apache 2.0 |
| 177 | claude-3-5-haiku-20241022Anthropic | 1384.00 | +/-6 | 11,248 | Anthropic | Proprietary |
| 178 | minimax-m2MiniMax | 1384.00 | +/-15 | 1,547 | MiniMax | Apache 2.0 |
| 179 | gemini-2.5-flash-lite-preview-06-17-thinkingGoogle | 1384.00 | +/-8 | 6,001 | Proprietary | |
| 180 | olmo-3.1-32b-instructAi2 | 1384.00 | +/-12 | 2,513 | Ai2 | Apache 2.0 |
| 181 | gpt-5-nano-highOpenAI | 1382.00 | +/-15 | 1,684 | OpenAI | Proprietary |
| 182 | qwen-plus-0125Alibaba | 1380.00 | +/-18 | 893 | Alibaba | Proprietary |
| 183 |  llama-3.1-405b-instruct-bf16Meta | 1375.00 | +/-7 | 6,249 | Meta | Llama 3.1 Community |
| 184 | deepseek-v2.5-1210DeepSeek | 1375.00 | +/-17 | 1,079 | DeepSeek | DeepSeek |
| 185 | gpt-4.1-nano-2025-04-14OpenAI | 1374.00 | +/-19 | 807 | OpenAI | Proprietary |
| 186 | llama-4-maverick-17b-128e-instructMeta | 1373.00 | +/-7 | 6,997 | Meta | Llama 4 |
| 187 | hunyuan-turbo-0110Tencent | 1372.00 | +/-30 | 299 | Tencent | Proprietary |
| 188 | step-2-16k-exp-202412StepFun | 1371.00 | +/-20 | 737 | StepFun | Proprietary |
| 189 | GPT OSS 20BOpenAI | 1370.00 | +/-13 | 2,167 | OpenAI | Apache 2.0 |
| 190 | athene-v2-chatNexusFlow | 1369.00 | +/-9 | 4,019 | NexusFlow | NexusFlow |
| 191 | yi-lightning01 AI | 1369.00 | +/-10 | 4,316 | 01 AI | Proprietary |
| 192 | gpt-4o-2024-05-13OpenAI | 1369.00 | +/-6 | 19,526 | OpenAI | Proprietary |
| 193 | deepseek-v2.5DeepSeek | 1368.00 | +/-9 | 4,252 | DeepSeek | DeepSeek |
| 194 | llama-3.1-405b-instruct-fp8Meta | 1368.00 | +/-7 | 9,714 | Meta | Llama 3.1 Community |
| 195 | mercuryInception AI | 1367.00 | +/-29 | 394 | Inception AI | Proprietary |
| 196 | hunyuan-large-2025-02-10Tencent | 1367.00 | +/-25 | 519 | Tencent | Proprietary |
| 197 | gemini-2.0-flash-001Google | 1365.00 | +/-7 | 6,996 | Proprietary | |
| 198 | olmo-3-32b-thinkAi2 | 1364.00 | +/-18 | 1,055 | Ai2 | Apache 2.0 |
| 199 | llama-3.3-nemotron-49b-super-v1Nvidia | 1363.00 | +/-31 | 286 | Nvidia | Nvidia |
| 200 | nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia | 1363.00 | +/-10 | 3,277 | Nvidia | NVIDIA Open Model |
| 201 | llama-4-scout-17b-16e-instructMeta | 1362.00 | +/-9 | 5,255 | Meta | Llama |
| 202 | mistral-small-3.1-24b-instruct-2503Mistral | 1362.00 | +/-8 | 6,136 | Mistral | Apache 2.0 |
| 203 | gpt-4o-2024-08-06OpenAI | 1360.00 | +/-8 | 7,318 | OpenAI | Proprietary |
| 204 | granite-4.1-8bIBM | 1360.00 | +/-21 | 944 | IBM | Apache 2.0 |
| 205 | grok-2-2024-08-13xAI | 1359.00 | +/-7 | 10,368 | xAI | Proprietary |
| 206 | gemma-3-27b-itGoogle | 1358.00 | +/-7 | 8,077 | Gemma | |
| 207 | qwen2.5-plus-1127Alibaba | 1357.00 | +/-14 | 1,553 | Alibaba | Proprietary |
| 208 | gemini-1.5-pro-002Google | 1356.00 | +/-7 | 9,175 | Proprietary | |
| 209 | hunyuan-large-visionTencent | 1356.00 | +/-19 | 964 | Tencent | Proprietary |
| 210 | qwen2.5-72b-instructAlibaba | 1355.00 | +/-8 | 6,688 | Alibaba | Qwen |
| 211 | Claude3-OpusAnthropic | 1353.00 | +/-6 | 33,748 | Anthropic | Proprietary |
| 212 | mistral-large-2407Mistral | 1353.00 | +/-8 | 7,589 | Mistral | Mistral Research |
| 213 | step-1o-turbo-202506StepFun | 1353.00 | +/-15 | 1,504 | StepFun | Proprietary |
| 214 | qwen-max-0919Alibaba | 1353.00 | +/-11 | 2,756 | Alibaba | Qwen |
| 215 | glm-4-plusZ.ai | 1352.00 | +/-9 | 4,449 | Z.ai | Proprietary |
| 216 | athene-70b-0725NexusFlow | 1350.00 | +/-11 | 3,122 | NexusFlow | CC-BY-NC-4.0 |
| 217 | gpt-4o-mini-2024-07-18OpenAI | 1349.00 | +/-7 | 10,927 | OpenAI | Proprietary |
| 218 | gemini-1.5-pro-001Google | 1347.00 | +/-8 | 12,747 | Proprietary | |
| 219 | gpt-4-turbo-2024-04-09OpenAI | 1347.00 | +/-7 | 17,104 | OpenAI | Proprietary |
| 220 | mistral-large-2411Mistral | 1346.00 | +/-9 | 4,212 | Mistral | MRL |
| 221 | llama-3.3-70b-instructMeta | 1345.00 | +/-7 | 8,748 | Meta | Llama-3.3 |
| 222 | gemini-2.0-flash-lite-preview-02-05Google | 1343.00 | +/-10 | 3,474 | Proprietary | |
| 223 | amazon-nova-pro-v1.0Amazon | 1343.00 | +/-9 | 3,853 | Amazon | Proprietary |
| 224 | qwen2.5-coder-32b-instructAlibaba | 1342.00 | +/-19 | 873 | Alibaba | Apache 2.0 |
| 225 | deepseek-coder-v2DeepSeek | 1342.00 | +/-12 | 2,671 | DeepSeek | DeepSeek License |
| 226 | gpt-4-1106-previewOpenAI | 1339.00 | +/-7 | 15,605 | OpenAI | Proprietary |
| 227 | olmo-3.1-32b-thinkAi2 | 1338.00 | +/-15 | 1,569 | Ai2 | Apache 2.0 |
| 228 | gemini-advanced-0514Google | 1338.00 | +/-9 | 8,138 | Proprietary | |
| 229 | grok-2-mini-2024-08-13xAI | 1335.00 | +/-7 | 8,652 | xAI | Proprietary |
| 230 | llama-3.1-70b-instructMeta | 1333.00 | +/-7 | 9,389 | Meta | Llama 3.1 Community |
| 231 | hunyuan-standard-2025-02-10Tencent | 1332.00 | +/-24 | 549 | Tencent | Proprietary |
| 232 | gpt-4-0125-previewOpenAI | 1331.00 | +/-8 | 15,289 | OpenAI | Proprietary |
| 233 | glm-4-plus-0111Z.ai | 1331.00 | +/-18 | 894 | Z.ai | Proprietary |
| 234 | ibm-granite-h-smallIBM | 1329.00 | +/-17 | 1,264 | IBM | Apache 2.0 |
| 235 | llama-3.1-nemotron-70b-instructNvidia | 1329.00 | +/-15 | 1,312 | Nvidia | Llama 3.1 |
| 236 | gpt-4-0314OpenAI | 1328.00 | +/-9 | 8,306 | OpenAI | Proprietary |
| 237 | gemma-3-12b-itGoogle | 1317.00 | +/-23 | 543 | Gemma | |
| 238 | claude-3-sonnet-20240229Anthropic | 1317.00 | +/-7 | 18,888 | Anthropic | Proprietary |
| 239 | gemini-1.5-flash-002Google | 1316.00 | +/-8 | 5,892 | Proprietary | |
| 240 | reka-core-20240904Reka AI | 1315.00 | +/-15 | 1,216 | Reka AI | Proprietary |
| 241 | gpt-4-0613OpenAI | 1313.00 | +/-8 | 13,719 | OpenAI | Proprietary |
| 242 | mistral-small-24b-instruct-2501Mistral | 1312.00 | +/-12 | 2,083 | Mistral | Apache 2.0 |
| 243 | jamba-1.5-largeAI21 Labs | 1312.00 | +/-15 | 1,440 | AI21 Labs | Jamba Open |
| 244 | llama-3.1-nemotron-51b-instructNvidia | 1311.00 | +/-22 | 665 | Nvidia | Llama 3.1 |
| 245 | gemini-1.5-flash-001Google | 1310.00 | +/-8 | 10,680 | Proprietary | |
| 246 | gemma-3n-e4b-itGoogle | 1309.00 | +/-10 | 3,530 | Gemma | |
| 247 | glm-4-0520Z.ai | 1308.00 | +/-14 | 1,718 | Z.ai | Proprietary |
| 248 | llama-3.1-tulu-3-70bAi2 | 1307.00 | +/-24 | 450 | Ai2 | Llama 3.1 |
| 249 | nemotron-4-340b-instructNvidia | 1307.00 | +/-11 | 3,254 | Nvidia | NVIDIA Open Model |
| 250 |  Phi 4 - 14BMicrosoft Azure | 1306.00 | +/-10 | 3,305 | Microsoft Azure | MIT |
| 251 | amazon-nova-lite-v1.0Amazon | 1305.00 | +/-10 | 3,060 | Amazon | Proprietary |
| 252 | llama-3-70b-instructMeta | 1305.00 | +/-7 | 28,126 | Meta | Llama 3 Community |
| 253 | gemma-2-27b-itGoogle | 1305.00 | +/-6 | 12,088 | Gemma license | |
| 254 | hunyuan-standard-256kTencent | 1300.00 | +/-25 | 497 | Tencent | Proprietary |
| 255 | claude-3-haiku-20240307Anthropic | 1300.00 | +/-7 | 20,898 | Anthropic | Proprietary |
| 256 | qwen2-72b-instructAlibaba | 1296.00 | +/-9 | 6,249 | Alibaba | Qianwen LICENSE |
| 257 | mistral-large-2402Mistral | 1294.00 | +/-9 | 10,418 | Mistral | Proprietary |
| 258 | c4ai-aya-expanse-32bCohere | 1292.00 | +/-9 | 4,685 | Cohere | CC-BY-NC-4.0 |
| 259 | reka-flash-20240904Reka AI | 1290.00 | +/-15 | 1,207 | Reka AI | Proprietary |
| 260 | amazon-nova-micro-v1.0Amazon | 1288.00 | +/-10 | 2,981 | Amazon | Proprietary |
| 261 | granite-3.1-8b-instructIBM | 1287.00 | +/-26 | 478 | IBM | Apache 2.0 |
| 262 | command-r-08-2024Cohere | 1280.00 | +/-13 | 1,783 | Cohere | CC-BY-NC-4.0 |
| 263 | olmo-2-0325-32b-instructAi2 | 1279.00 | +/-27 | 427 | Ai2 | Apache-2.0 |
| 264 | command-r-plus-08-2024Cohere | 1279.00 | +/-14 | 1,675 | Cohere | CC-BY-NC-4.0 |
| 265 | qwen1.5-110b-chatAlibaba | 1279.00 | +/-10 | 4,763 | Alibaba | Qianwen LICENSE |
| 266 | reka-flash-21b-20240226-onlineReka AI | 1276.00 | +/-13 | 2,879 | Reka AI | Proprietary |
| 267 | mixtral-8x22b-instruct-v0.1Mistral | 1276.00 | +/-9 | 8,780 | Mistral | Apache 2.0 |
| 268 | gemma-3-4b-itGoogle | 1275.00 | +/-24 | 605 | Gemma | |
| 269 | ministral-8b-2410Mistral | 1274.00 | +/-19 | 838 | Mistral | MRL |
| 270 | qwen1.5-72b-chatAlibaba | 1274.00 | +/-10 | 6,370 | Alibaba | Qianwen LICENSE |
| 271 | gpt-3.5-turbo-0125OpenAI | 1273.00 | +/-8 | 11,130 | OpenAI | Proprietary |
| 272 | gemini-1.5-flash-8b-001Google | 1272.00 | +/-8 | 6,069 | Proprietary | |
| 273 | gemma-2-9b-it-simpoPrinceton | 1272.00 | +/-15 | 1,471 | Princeton | MIT |
| 274 | command-r-plusCohere | 1271.00 | +/-8 | 13,937 | Cohere | CC-BY-NC-4.0 |
| 275 | gemma-2-9b-itGoogle | 1271.00 | +/-7 | 8,921 | Gemma license | |
| 276 | reka-flash-21b-20240226Reka AI | 1266.00 | +/-11 | 4,748 | Reka AI | Proprietary |
| 277 | jamba-1.5-miniAI21 Labs | 1265.00 | +/-15 | 1,352 | AI21 Labs | Jamba Open |
| 278 | mistral-mediumMistral | 1261.00 | +/-10 | 5,149 | Mistral | Proprietary |
| 279 | gpt-3.5-turbo-1106OpenAI | 1261.00 | +/-16 | 2,121 | OpenAI | Proprietary |
| 280 | qwen1.5-32b-chatAlibaba | 1261.00 | +/-11 | 3,930 | Alibaba | Qianwen LICENSE |
| 281 | llama-3.1-8b-instructMeta | 1259.00 | +/-7 | 8,582 | Meta | Llama 3.1 Community |
| 282 | c4ai-aya-expanse-8bCohere | 1255.00 | +/-15 | 1,567 | Cohere | CC-BY-NC-4.0 |
| 283 | llama-3.1-tulu-3-8bAi2 | 1253.00 | +/-25 | 476 | Ai2 | Llama 3.1 |
| 284 | llama-3-8b-instructMeta | 1252.00 | +/-8 | 18,374 | Meta | Llama 3 Community |
| 285 | dbrx-instruct-previewDatabricks | 1250.00 | +/-11 | 5,502 | Databricks | DBRX LICENSE |
| 286 | granite-3.1-2b-instructIBM | 1248.00 | +/-25 | 508 | IBM | Apache 2.0 |
| 287 | gemini-proGoogle | 1248.00 | +/-24 | 678 | Proprietary | |
| 288 | internlm2_5-20b-chatInternLM | 1247.00 | +/-14 | 1,684 | InternLM | Other |
| 289 | yi-1.5-34b-chat01 AI | 1247.00 | +/-10 | 3,841 | 01 AI | Apache-2.0 |
| 290 | zephyr-orpo-141b-A35b-v0.1HuggingFace | 1244.00 | +/-21 | 831 | HuggingFace | Apache 2.0 |
| 291 | command-rCohere | 1242.00 | +/-9 | 9,645 | Cohere | CC-BY-NC-4.0 |
| 292 | granite-3.0-8b-instructIBM | 1239.00 | +/-18 | 1,108 | IBM | Apache 2.0 |
| 293 | gemini-pro-dev-apiGoogle | 1238.00 | +/-14 | 2,681 | Proprietary | |
| 294 | qwen1.5-14b-chatAlibaba | 1238.00 | +/-13 | 3,208 | Alibaba | Qianwen LICENSE |
| 295 | mixtral-8x7b-instruct-v0.1Mistral | 1238.00 | +/-8 | 11,784 | Mistral | Apache 2.0 |
| 296 | starling-lm-7b-betaNexusflow | 1234.00 | +/-13 | 2,948 | Nexusflow | Apache-2.0 |
| 297 | phi-3-medium-4k-instructMicrosoft | 1230.00 | +/-10 | 3,973 | Microsoft | MIT |
| 298 | openchat-3.5-0106OpenChat | 1228.00 | +/-14 | 2,005 | OpenChat | Apache-2.0 |
| 299 | snowflake-arctic-instructSnowflake | 1223.00 | +/-11 | 5,734 | Snowflake | Apache 2.0 |
| 300 | gemma-1.1-7b-itGoogle | 1216.00 | +/-10 | 4,332 | Gemma license | |
| 301 | deepseek-llm-67b-chatDeepSeek | 1216.00 | +/-24 | 649 | DeepSeek | DeepSeek License |
| 302 | tulu-2-dpo-70bAllenAI/UW | 1213.00 | +/-21 | 805 | AllenAI/UW | AI2 ImpACT Low-risk |
| 303 | qwen1.5-7b-chatAlibaba | 1208.00 | +/-21 | 772 | Alibaba | Qianwen LICENSE |
| 304 | granite-3.0-2b-instructIBM | 1208.00 | +/-18 | 1,134 | IBM | Apache 2.0 |
| 305 | starling-lm-7b-alphaUC Berkeley | 1206.00 | +/-16 | 1,397 | UC Berkeley | CC-BY-NC-4.0 |
| 306 | yi-34b-chat01 AI | 1204.00 | +/-13 | 2,345 | 01 AI | Yi License |
| 307 | phi-3-small-8k-instructMicrosoft | 1203.00 | +/-12 | 3,219 | Microsoft | MIT |
| 308 | openchat-3.5OpenChat | 1201.00 | +/-20 | 971 | OpenChat | Apache-2.0 |
| 309 | qwen-14b-chatAlibaba | 1196.00 | +/-24 | 599 | Alibaba | Qianwen LICENSE |
| 310 | phi-3-mini-4k-instruct-june-2024Microsoft | 1196.00 | +/-14 | 1,841 | Microsoft | MIT |
| 311 | gemma-2-2b-itGoogle | 1193.00 | +/-8 | 7,298 | Gemma license | |
| 312 | vicuna-33bLMSYS | 1192.00 | +/-13 | 2,866 | LMSYS | Non-commercial |
| 313 | wizardlm-70bMicrosoft | 1192.00 | +/-20 | 988 | Microsoft | Llama 2 Community |
| 314 | phi-3-mini-4k-instructMicrosoft | 1186.00 | +/-12 | 3,449 | Microsoft | MIT |
| 315 | openhermes-2.5-mistral-7bNousResearch | 1185.00 | +/-23 | 589 | NousResearch | Apache-2.0 |
| 316 | mistral-7b-instruct-v0.2Mistral | 1184.00 | +/-12 | 3,114 | Mistral | Apache-2.0 |
| 317 | solar-10.7b-instruct-v1.0Upstage AI | 1182.00 | +/-27 | 482 | Upstage AI | CC-BY-NC-4.0 |
| 318 | llama-2-70b-chatMeta | 1177.00 | +/-10 | 5,717 | Meta | Llama 2 Community |
| 319 | llama-3.2-3b-instructMeta | 1175.00 | +/-16 | 1,351 | Meta | Llama 3.2 |
| 320 | nous-hermes-2-mixtral-8x7b-dpoNousResearch | 1174.00 | +/-24 | 575 | NousResearch | Apache-2.0 |
| 321 | qwq-32b-previewAlibaba | 1173.00 | +/-24 | 566 | Alibaba | Apache 2.0 |
| 322 | gemma-1.1-2b-itGoogle | 1171.00 | +/-14 | 1,963 | Gemma license | |
| 323 | gemma-7b-itGoogle | 1167.00 | +/-17 | 1,381 | Gemma license | |
| 324 | mpt-30b-chatMosaicML | 1166.00 | +/-35 | 258 | MosaicML | CC-BY-NC-SA-4.0 |
| 325 | zephyr-7b-alphaHuggingFace | 1165.00 | +/-40 | 201 | HuggingFace | MIT |
| 326 | vicuna-13bLMSYS | 1162.00 | +/-14 | 2,389 | LMSYS | Llama 2 Community |
| 327 | llama-2-13b-chatMeta | 1161.00 | +/-13 | 2,626 | Meta | Llama 2 Community |
| 328 | smollm2-1.7b-instructHuggingFace | 1159.00 | +/-33 | 352 | HuggingFace | Apache 2.0 |
| 329 | codellama-34b-instructMeta | 1158.00 | +/-20 | 853 | Meta | Llama 2 Community |
| 330 | phi-3-mini-128k-instructMicrosoft | 1153.00 | +/-13 | 3,886 | Microsoft | MIT |
| 331 | palm-2Google | 1152.00 | +/-21 | 917 | Proprietary | |
| 332 | zephyr-7b-betaHuggingFace | 1151.00 | +/-18 | 1,250 | HuggingFace | MIT |
| 333 | wizardlm-13bMicrosoft | 1150.00 | +/-22 | 735 | Microsoft | Llama 2 Community |
| 334 | llama-3.2-1b-instructMeta | 1148.00 | +/-16 | 1,346 | Meta | Llama 3.2 |
| 335 | llama2-70b-steerlm-chatNvidia | 1144.00 | +/-28 | 467 | Nvidia | Llama 2 Community |
| 336 | mistral-7b-instructMistral | 1143.00 | +/-20 | 1,032 | Mistral | Apache 2.0 |
| 337 | gemma-2b-itGoogle | 1136.00 | +/-22 | 742 | Gemma license | |
| 338 | vicuna-7bLMSYS | 1130.00 | +/-23 | 726 | LMSYS | Llama 2 Community |
| 339 | qwen1.5-4b-chatAlibaba | 1130.00 | +/-17 | 1,283 | Alibaba | Qianwen LICENSE |
| 340 | stripedhyena-nous-7bTogether AI | 1126.00 | +/-22 | 704 | Together AI | Apache 2.0 |
| 341 | guanaco-33bUW | 1112.00 | +/-36 | 263 | UW | Non-commercial |
| 342 | olmo-7b-instructAi2 | 1106.00 | +/-22 | 772 | Ai2 | Apache-2.0 |
| 343 | llama-2-7b-chatMeta | 1101.00 | +/-14 | 1,956 | Meta | Llama 2 Community |
| 344 | chatglm3-6bTsinghua | 1089.00 | +/-26 | 535 | Tsinghua | Apache-2.0 |
| 345 | mpt-7b-chatMosaicML | 1064.00 | +/-31 | 397 | MosaicML | CC-BY-NC-SA-4.0 |
| 346 | koala-13bUC Berkeley | 1064.00 | +/-24 | 747 | UC Berkeley | Non-commercial |
| 347 | RWKV-4-Raven-14BRWKV | 1058.00 | +/-27 | 505 | RWKV | Apache 2.0 |
| 348 | oasst-pythia-12bOpenAssistant | 1049.00 | +/-25 | 714 | OpenAssistant | Apache 2.0 |
| 349 | chatglm-6bTsinghua | 1034.00 | +/-27 | 551 | Tsinghua | Non-commercial |
| 350 | chatglm2-6bTsinghua | 1029.00 | +/-35 | 293 | Tsinghua | Apache-2.0 |
| 351 | stablelm-tuned-alpha-7bStability AI | 1003.00 | +/-33 | 363 | Stability AI | CC-BY-NC-SA-4.0 |
| 352 | alpaca-13bStanford | 998.00 | +/-27 | 626 | Stanford | Non-commercial |
| 353 | dolly-v2-12bDatabricks | 961.00 | +/-34 | 396 | Databricks | MIT |
| 354 | fastchat-t5-3bLMSYS | 906.00 | +/-30 | 428 | LMSYS | Apache 2.0 |
| 355 | llama-13bMeta | 881.00 | +/-39 | 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。