LMArena Coding Arena Leaderboard
The latest AI coding model leaderboard based on LMArena Coding Arena anonymous user voting. Covers Elo scores, confidence intervals, and vote counts for Claude, GPT, Gemini, DeepSeek, Qwen, and more.
Top Model
claude-fable-5
Top Score
1566.00
Model Count
361
Data version
2026年06月10日
Data source: LM Arena
About This Leaderboard
This leaderboard ranks AI models by coding ability. Data comes from LMArena (formerly LMSYS Chatbot Arena)'s Coding sub-track, evaluated through anonymous blind testing by real users on programming tasks.
Methodology Overview
Blind testing: Users submit coding questions, two anonymous models generate code answers, and users vote for the better response — eliminating brand bias.
Elo scoring: Uses the Bradley-Terry model to calculate Elo scores. Higher scores mean users more frequently prefer that model's code solutions.
Broad scenario coverage: Testing spans code generation, bug fixing, algorithm implementation, code explanation, and more real-world programming scenarios.
DataLearner provides in-depth analysis on top of the raw data, linking leaderboard models to the DataLearner model database so you can quickly access model details, API pricing, benchmark scores, and more.
Ranking Table
| Rank | Model | Score | 95% CI | Votes | Organization | License |
|---|---|---|---|---|---|---|
 claude-fable-5Anthropic | 1566.00 | +/-22 | 752 | Anthropic | Proprietary | |
| Opus 4.7 (thinking)Anthropic | 1553.00 | +/-8 | 8,171 | Anthropic | Proprietary | |
| Claude Opus 4.6 (thinking)Anthropic | 1551.00 | +/-7 | 10,773 | Anthropic | Proprietary | |
| 4 | claude-opus-4-8-thinkingAnthropic | 1550.00 | +/-13 | 2,442 | Anthropic | Proprietary |
| 5 | Opus 4.7Anthropic | 1548.00 | +/-8 | 8,508 | Anthropic | Proprietary |
| 6 | Claude Opus 4.6Anthropic | 1548.00 | +/-7 | 12,404 | Anthropic | Proprietary |
| 7 | claude-opus-4-8Anthropic | 1540.00 | +/-12 | 2,565 | Anthropic | Proprietary |
| 8 | Claude Opus 4 (thinking-32k)Anthropic | 1530.00 | +/-7 | 7,620 | Anthropic | Proprietary |
| 9 | GLM 5.1智谱AI | 1529.00 | +/-10 | 4,471 | 智谱AI | MIT |
| 10 | Muse SparkFacebook AI研究实验室 | 1526.00 | +/-10 | 3,743 | Facebook AI研究实验室 | Proprietary |
| 11 | Claude Sonnet 4.6Anthropic | 1526.00 | +/-7 | 9,655 | Anthropic | Proprietary |
| 12 | Qwen3.7-Max-Preview阿里巴巴 | 1525.00 | +/-18 | 1,134 | 阿里巴巴 | Proprietary |
| 13 |  Gemini 3.1 Pro PreviewGoogle Deep Mind | 1525.00 | +/-6 | 14,839 | Google Deep Mind | Proprietary |
| 14 | Claude Opus 4Anthropic | 1523.00 | +/-6 | 17,310 | Anthropic | Proprietary |
| 15 |  GPT-5.4 (high)OpenAI | 1521.00 | +/-7 | 9,742 | OpenAI | Proprietary |
| 16 | Claude Sonnet 4.5 (thinking-32k)Anthropic | 1520.00 | +/-5 | 19,269 | Anthropic | Proprietary |
| 17 | mimo-v2.5-proXiaomi | 1520.00 | +/-8 | 6,370 | Xiaomi | MIT |
| 18 | GPT-5.5 (high)OpenAI | 1520.00 | +/-8 | 6,702 | OpenAI | Proprietary |
| 19 | Gemini 3.0 Pro (Preview 11-2025)Google Deep Mind | 1519.00 | +/-7 | 8,573 | Google Deep Mind | Proprietary |
| 20 | ERNIE-5.1-Preview百度 | 1515.00 | +/-8 | 5,997 | 百度 | Proprietary |
| 21 | GPT-5.2OpenAI | 1515.00 | +/-7 | 9,113 | OpenAI | Proprietary |
| 22 | GPT-5.4OpenAI | 1515.00 | +/-7 | 10,760 | OpenAI | Proprietary |
| 23 |  grok-4.20-multi-agent-beta-0309xAI | 1514.00 | +/-7 | 10,278 | xAI | Proprietary |
| 24 | Claude Sonnet 4.5Anthropic | 1513.00 | +/-5 | 19,140 | Anthropic | Proprietary |
| 25 | Opus 4.1 (thinking-16k)Anthropic | 1513.00 | +/-7 | 9,837 | Anthropic | Proprietary |
| 26 |  minimax-m3MiniMax | 1513.00 | +/-14 | 2,138 | MiniMax | Proprietary |
| 27 | GPT-5.5 InstantOpenAI | 1512.00 | +/-8 | 7,645 | OpenAI | Proprietary |
| 28 |  Kimi K2.6Moonshot AI | 1512.00 | +/-8 | 6,146 | Moonshot AI | Modified MIT |
| 29 | grok-4.20-beta-0309-reasoningxAI | 1512.00 | +/-7 | 10,459 | xAI | Proprietary |
| 30 | Qwen3.5 Max Preview阿里巴巴 | 1512.00 | +/-8 | 6,016 | 阿里巴巴 | Proprietary |
| 31 | DOLA Seed 2.0 Pro字节跳动Seed团队 | 1511.00 | +/-6 | 12,613 | 字节跳动Seed团队 | Proprietary |
| 32 | Gemini 3.0 FlashGoogle Deep Mind | 1509.00 | +/-8 | 6,386 | Google Deep Mind | Proprietary |
| 33 | Grok 4.20 BetaxAI | 1508.00 | +/-8 | 7,171 | xAI | Proprietary |
| 34 | Qwen3.6-Max-Preview阿里巴巴 | 1508.00 | +/-16 | 1,544 | 阿里巴巴 | Proprietary |
| 35 | Gemini 3.5 FlashGoogle Deep Mind | 1507.00 | +/-12 | 3,015 | Google Deep Mind | Proprietary |
| 36 | Opus 4.1Anthropic | 1505.00 | +/-5 | 15,526 | Anthropic | Proprietary |
| 37 | Kimi K2.5 InstantMoonshot AI | 1505.00 | +/-14 | 1,798 | Moonshot AI | Modified MIT |
| 38 | mimo-v2-proXiaomi | 1504.00 | +/-8 | 6,939 | Xiaomi | Proprietary |
| 39 | Kimi K2 ThinkingMoonshot AI | 1504.00 | +/-6 | 11,797 | Moonshot AI | Modified MIT |
| 40 |  DeepSeek-V4-ProDeepSeek-AI | 1502.00 | +/-8 | 7,438 | DeepSeek-AI | MIT |
| 41 |  longcat-flash-chat-2602-expMeituan | 1502.00 | +/-8 | 7,789 | Meituan | Proprietary |
| 42 | GPT-5.5OpenAI | 1502.00 | +/-8 | 7,056 | OpenAI | Proprietary |
| 43 | Grok 4.1 ThinkingxAI | 1499.00 | +/-6 | 15,080 | xAI | Proprietary |
| 44 | Claude Opus 4 (thinking-16k)Anthropic | 1498.00 | +/-8 | 6,674 | Anthropic | Proprietary |
| 45 | GLM-5智谱AI | 1497.00 | +/-8 | 5,875 | 智谱AI | MIT |
| 46 | Gemma 4 31BDeepMind | 1497.00 | +/-15 | 1,366 | DeepMind | Apache 2.0 |
| 47 | GPT-5.4 mini (high)OpenAI | 1497.00 | +/-7 | 9,551 | OpenAI | Proprietary |
| 48 | GPT-5.3OpenAI | 1497.00 | +/-7 | 8,739 | OpenAI | Proprietary |
| 49 | Qwen3.5-397B-A17B阿里巴巴 | 1495.00 | +/-6 | 11,123 | 阿里巴巴 | Apache 2.0 |
| 50 | Qwen 3.6 Plus Preview阿里巴巴 | 1494.00 | +/-8 | 7,808 | 阿里巴巴 | Proprietary |
| 51 | Gemini 3.0 Flash (minimal)Google Deep Mind | 1492.00 | +/-6 | 15,686 | Google Deep Mind | Proprietary |
| 52 | DeepSeek-V4-Pro (thinking)DeepSeek-AI | 1492.00 | +/-8 | 6,810 | DeepSeek-AI | MIT |
| 53 | Grok 4.1xAI | 1492.00 | +/-6 | 15,618 | xAI | Proprietary |
| 54 | ERNIE 5.0百度 | 1491.00 | +/-7 | 8,555 | 百度 | Proprietary |
| 55 | GPT-5.1 Pro (high)OpenAI | 1490.00 | +/-7 | 8,208 | OpenAI | Proprietary |
| 56 | GPT-5.2 Pro (high)OpenAI | 1490.00 | +/-6 | 11,694 | OpenAI | Proprietary |
| 57 | mimo-v2-omniXiaomi | 1489.00 | +/-12 | 2,607 | Xiaomi | Proprietary |
| 58 | Grok 4.3 BetaxAI | 1488.00 | +/-8 | 6,857 | xAI | Proprietary |
| 59 |  amazon-nova-experimental-chat-26-02-10Amazon | 1487.00 | +/-20 | 841 | Amazon | Proprietary |
| 60 | mimo-v2.5Xiaomi | 1487.00 | +/-8 | 6,854 | Xiaomi | MIT |
| 61 | Kimi K2 Thinking (thinking-turbo)Moonshot AI | 1487.00 | +/-6 | 14,810 | Moonshot AI | Modified MIT |
| 62 | GLM-4.7智谱AI | 1486.00 | +/-12 | 2,412 | 智谱AI | MIT |
| 63 | GPT-5.2OpenAI | 1483.00 | +/-6 | 14,111 | OpenAI | Proprietary |
| 64 | Qwen3 Max (Preview)阿里巴巴 | 1482.00 | +/-8 | 5,362 | 阿里巴巴 | Proprietary |
| 65 | DeepSeek-V4-FlashDeepSeek-AI | 1480.00 | +/-8 | 7,135 | DeepSeek-AI | MIT |
| 66 | Gemma 4 26B A4BDeepMind | 1480.00 | +/-15 | 1,367 | DeepMind | Apache 2.0 |
| 67 | amazon-nova-experimental-chat-26-01-10Amazon | 1480.00 | +/-21 | 735 | Amazon | Proprietary |
| 68 | Haiku 4.5Anthropic | 1479.00 | +/-5 | 20,999 | Anthropic | Proprietary |
| 69 | MiniMax-M2.7MiniMaxAI | 1478.00 | +/-7 | 9,028 | MiniMaxAI | Modified MIT |
| 70 |  mistral-medium-3.5Mistral | 1477.00 | +/-12 | 2,631 | Mistral | Modified MIT |
| 71 | DeepSeek-V4-Flash (thinking)DeepSeek-AI | 1476.00 | +/-8 | 7,129 | DeepSeek-AI | MIT |
| 72 | DeepSeek V3.2 (thinking)DeepSeek-AI | 1475.00 | +/-7 | 8,501 | DeepSeek-AI | MIT |
| 73 | DeepSeek V3.2-Exp (thinking)DeepSeek-AI | 1475.00 | +/-13 | 1,919 | DeepSeek-AI | MIT |
| 74 |  qwen3-max-2025-09-23Alibaba | 1475.00 | +/-13 | 2,041 | Alibaba | Proprietary |
| 75 | longcat-flash-chatMeituan | 1475.00 | +/-13 | 2,232 | Meituan | MIT |
| 76 | GPT-5.1 InstantOpenAI | 1474.00 | +/-7 | 9,124 | OpenAI | Proprietary |
| 77 | Qwen3-235B-A22B-2507阿里巴巴 | 1473.00 | +/-5 | 21,272 | 阿里巴巴 | Apache 2.0 |
| 78 | Claude Sonnet 4 (thinking-32k)Anthropic | 1473.00 | +/-8 | 6,411 | Anthropic | Proprietary |
| 79 | ERNIE 5.0百度 | 1472.00 | +/-13 | 1,955 | 百度 | Proprietary |
| 80 | DeepSeek V3.2DeepSeek-AI | 1470.00 | +/-6 | 10,595 | DeepSeek-AI | MIT |
| 81 | GPT-4o(2025-03-27)OpenAI | 1469.00 | +/-5 | 15,861 | OpenAI | Proprietary |
| 82 | Kimi K2 0905Moonshot AI | 1468.00 | +/-13 | 2,241 | Moonshot AI | Modified MIT |
| 83 | Mistral Large 3MistralAI | 1467.00 | +/-6 | 9,924 | MistralAI | Apache 2.0 |
| 84 | GPT-5-Pro (high)OpenAI | 1467.00 | +/-8 | 6,356 | OpenAI | Proprietary |
| 85 | DeepSeek V3.2-ExpDeepSeek-AI | 1466.00 | +/-12 | 2,499 | DeepSeek-AI | MIT |
| 86 | Qwen3-VL-235B-A22B-Instruct阿里巴巴 | 1466.00 | +/-13 | 2,316 | 阿里巴巴 | Apache 2.0 |
| 87 | Gemini 2.5 Pro Experimental 03-25Google Deep Mind | 1465.00 | +/-4 | 26,514 | Google Deep Mind | Proprietary |
| 88 | DeepSeek-R1-0528DeepSeek-AI | 1465.00 | +/-11 | 2,729 | DeepSeek-AI | MIT |
| 89 | Claude Opus 4Anthropic | 1464.00 | +/-7 | 7,898 | Anthropic | Proprietary |
| 90 | GPT-5OpenAI | 1464.00 | +/-8 | 5,987 | OpenAI | Proprietary |
| 91 | DeepSeek-V3.1 Terminus (thinking)DeepSeek-AI | 1464.00 | +/-24 | 636 | DeepSeek-AI | MIT |
| 92 | Grok 4.1 Fast (fast-reasoning)xAI | 1462.00 | +/-6 | 13,558 | xAI | Proprietary |
| 93 | Kimi K2Moonshot AI | 1460.00 | +/-8 | 5,243 | Moonshot AI | Modified MIT |
| 94 |  hunyuan-hy3-previewTencent | 1460.00 | +/-14 | 1,946 | Tencent | tencent-hunyuan-community |
| 95 | GLM-4.6智谱AI | 1460.00 | +/-7 | 7,480 | 智谱AI | MIT |
| 96 | GPT-4.5OpenAI | 1459.00 | +/-13 | 1,939 | OpenAI | Proprietary |
| 97 | Qwen3.5-122B-A10B阿里巴巴 | 1459.00 | +/-7 | 7,755 | 阿里巴巴 | Apache 2.0 |
| 98 | OpenAI o3OpenAI | 1459.00 | +/-6 | 11,749 | OpenAI | Proprietary |
| 99 | Grok 4 FastxAI | 1459.00 | +/-16 | 1,249 | xAI | Proprietary |
| 100 | GPT-5.4 nano (high)OpenAI | 1459.00 | +/-7 | 9,667 | OpenAI | Proprietary |
| 101 | Qwen3-Coder-480B-A35B阿里巴巴 | 1457.00 | +/-9 | 4,850 | 阿里巴巴 | Apache 2.0 |
| 102 | DeepSeek-V3.1 (thinking)DeepSeek-AI | 1457.00 | +/-13 | 1,901 | DeepSeek-AI | MIT |
| 103 | gemini-3.1-flash-lite-previewGoogle | 1457.00 | +/-7 | 12,099 | Proprietary | |
| 104 | GPT-4.1OpenAI | 1456.00 | +/-7 | 9,313 | OpenAI | Proprietary |
| 105 | Magistral-Medium-2506MistralAI | 1456.00 | +/-5 | 21,096 | MistralAI | Proprietary |
| 106 | Qwen3-VL-235B-A22B-Instruct (thinking)阿里巴巴 | 1456.00 | +/-14 | 1,624 | 阿里巴巴 | Apache 2.0 |
| 107 | GLM-4.5智谱AI | 1455.00 | +/-9 | 4,771 | 智谱AI | MIT |
| 108 |  nvidia-nemotron-3-ultra-550b-a55b-nvfp4Nvidia | 1452.00 | +/-20 | 930 | Nvidia | OpenMDW-1.1 |
| 109 | Claude Sonnet 3.7 (thinking-32k)Anthropic | 1451.00 | +/-8 | 6,191 | Anthropic | Proprietary |
| 110 |  Step 3.5 FlashStepFunAI | 1451.00 | +/-7 | 10,325 | StepFunAI | Apache 2.0 |
| 111 | Qwen3.5-27B阿里巴巴 | 1450.00 | +/-7 | 7,483 | 阿里巴巴 | Apache 2.0 |
| 112 | Claude Sonnet 4Anthropic | 1449.00 | +/-7 | 7,394 | Anthropic | Proprietary |
| 113 | DeepSeek-V3.1DeepSeek-AI | 1448.00 | +/-12 | 2,622 | DeepSeek-AI | MIT |
| 114 | qwen3-235b-a22b-no-thinkingAlibaba | 1447.00 | +/-8 | 6,974 | Alibaba | Apache 2.0 |
| 115 | Qwen3-Next阿里巴巴 | 1446.00 | +/-9 | 4,790 | 阿里巴巴 | Apache 2.0 |
| 116 | mimo-v2-flash (non-thinking)Xiaomi | 1446.00 | +/-6 | 11,984 | Xiaomi | MIT |
| 117 | DeepSeek-R1DeepSeek-AI | 1445.00 | +/-12 | 2,317 | DeepSeek-AI | MIT |
| 118 | MiniMax M2.5MiniMaxAI | 1444.00 | +/-7 | 10,841 | MiniMaxAI | Modified MIT |
| 119 | Grok 3xAI | 1443.00 | +/-8 | 5,398 | xAI | Proprietary |
| 120 | qwen3-235b-a22b-thinking-2507Alibaba | 1442.00 | +/-15 | 1,610 | Alibaba | Apache 2.0 |
| 121 | trinity-large-previewArcee AI | 1441.00 | +/-8 | 7,599 | Arcee AI | Apache 2.0 |
| 122 | Qwen3-30B-A3B-2507阿里巴巴 | 1440.00 | +/-9 | 4,659 | 阿里巴巴 | Apache 2.0 |
| 123 | M2.1MiniMaxAI | 1439.00 | +/-10 | 3,425 | MiniMaxAI | MIT |
| 124 | DeepSeek-V3.1 TerminusDeepSeek-AI | 1439.00 | +/-21 | 778 | DeepSeek-AI | MIT |
| 125 | hunyuan-vision-1.5-thinkingTencent | 1438.00 | +/-27 | 435 | Tencent | Proprietary |
| 126 | Grok 4 Fast (fast-reasoning)xAI | 1437.00 | +/-9 | 3,955 | xAI | Proprietary |
| 127 | Grok 4xAI | 1436.00 | +/-7 | 8,154 | xAI | Proprietary |
| 128 | Qwen3.5-35B-A3B阿里巴巴 | 1435.00 | +/-7 | 7,946 | 阿里巴巴 | Apache 2.0 |
| 129 | amazon-nova-experimental-chat-12-10Amazon | 1435.00 | +/-21 | 704 | Amazon | Proprietary |
| 130 | OpenAI o3-mini (high)OpenAI | 1435.00 | +/-12 | 2,596 | OpenAI | Proprietary |
| 131 | Claude 3.5 SonnetAnthropic | 1434.00 | +/-6 | 14,960 | Anthropic | Proprietary |
| 132 | Qwen3-235B-A22B阿里巴巴 | 1434.00 | +/-9 | 4,341 | 阿里巴巴 | Apache 2.0 |
| 133 | GPT-4.1 miniOpenAI | 1434.00 | +/-7 | 6,917 | OpenAI | Proprietary |
| 134 | mistral-medium-2505Mistral | 1433.00 | +/-8 | 5,898 | Mistral | Proprietary |
| 135 | ERNIE 5.0百度 | 1433.00 | +/-19 | 916 | 百度 | Proprietary |
| 136 | OpenAI o1OpenAI | 1433.00 | +/-10 | 3,973 | OpenAI | Proprietary |
| 137 | OpenAI o4 - miniOpenAI | 1432.00 | +/-7 | 8,720 | OpenAI | Proprietary |
| 138 | mimo-v2-flash (thinking)Xiaomi | 1432.00 | +/-12 | 2,443 | Xiaomi | MIT |
| 139 | Step 3.5 FlashStepFunAI | 1431.00 | +/-7 | 10,577 | StepFunAI | Proprietary |
| 140 | GPT-5-mini (high)OpenAI | 1430.00 | +/-8 | 5,498 | OpenAI | Proprietary |
| 141 | Claude Sonnet 3.7Anthropic | 1430.00 | +/-7 | 7,144 | Anthropic | Proprietary |
| 142 | DeepSeek-V3-0324DeepSeek-AI | 1429.00 | +/-7 | 8,365 | DeepSeek-AI | MIT |
| 143 | Gemini 2.5 Flash-Preview-09-2025Google Deep Mind | 1429.00 | +/-8 | 6,842 | Google Deep Mind | Proprietary |
| 144 | GLM-4.5-Air智谱AI | 1427.00 | +/-8 | 6,102 | 智谱AI | MIT |
| 145 | Gemini 2.5 FlashGoogle Deep Mind | 1424.00 | +/-4 | 25,876 | Google Deep Mind | Proprietary |
| 146 | GLM-4.7-Flash智谱AI | 1424.00 | +/-11 | 2,691 | 智谱AI | MIT |
| 147 | Qwen3-Next (thinking)阿里巴巴 | 1421.00 | +/-11 | 2,677 | 阿里巴巴 | Apache 2.0 |
| 148 | amazon-nova-experimental-chat-11-10Amazon | 1420.00 | +/-8 | 5,316 | Amazon | Proprietary |
| 149 | GLM-4.6V智谱AI | 1418.00 | +/-25 | 534 | 智谱AI | MIT |
| 150 | OpenAI o1OpenAI | 1417.00 | +/-9 | 5,123 | OpenAI | Proprietary |
| 151 | minimax-m1MiniMax | 1416.00 | +/-8 | 6,485 | MiniMax | Apache 2.0 |
| 152 | OpenAI o3-miniOpenAI | 1416.00 | +/-6 | 9,460 | OpenAI | Proprietary |
| 153 | trinity-large-thinkingArcee AI | 1414.00 | +/-8 | 8,155 | Arcee AI | Apache 2.0 |
| 154 | Mistral-Small-3.2MistralAI | 1413.00 | +/-10 | 3,359 | MistralAI | Apache 2.0 |
| 155 | ling-flash-2.0Ant Group | 1413.00 | +/-15 | 1,527 | Ant Group | MIT |
| 156 | amazon-nova-experimental-chat-10-20Amazon | 1411.00 | +/-12 | 2,293 | Amazon | Proprietary |
| 157 | nvidia-nemotron-3-super-120b-a12bNvidia | 1411.00 | +/-14 | 1,782 | Nvidia | NVIDIA Open Model |
| 158 | intellect-3Prime Intellect | 1410.00 | +/-19 | 973 | Prime Intellect | MIT |
| 159 | Step3StepFunAI | 1408.00 | +/-17 | 1,233 | StepFunAI | Apache 2.0 |
| 160 | Qwen3-32B阿里巴巴 | 1408.00 | +/-24 | 513 | 阿里巴巴 | Apache 2.0 |
| 161 | nvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia | 1405.00 | +/-22 | 659 | Nvidia | Nvidia Open |
| 162 | GLM-4.5V智谱AI | 1405.00 | +/-18 | 991 | 智谱AI | MIT |
| 163 | Qwen2.5-Max阿里巴巴 | 1403.00 | +/-8 | 5,100 | 阿里巴巴 | Proprietary |
| 164 | hunyuan-turbos-20250226Tencent | 1400.00 | +/-31 | 275 | Tencent | Proprietary |
| 165 | Hunyuan-T1腾讯AI实验室 | 1399.00 | +/-20 | 804 | 腾讯AI实验室 | Proprietary |
| 166 | Claude 3.5 SonnetAnthropic | 1398.00 | +/-7 | 13,607 | Anthropic | Proprietary |
| 167 | Gemini 2.5 Flash-Lite-Preview-09-2025 (no-thinking)Google Deep Mind | 1398.00 | +/-7 | 9,678 | Google Deep Mind | Proprietary |
| 168 | Nova 2 Lite亚马逊 | 1397.00 | +/-12 | 2,515 | 亚马逊 | Proprietary |
| 169 | mercury-2Inception AI | 1397.00 | +/-21 | 768 | Inception AI | Proprietary |
| 170 | hunyuan-turbos-20250416Tencent | 1395.00 | +/-14 | 1,776 | Tencent | Proprietary |
| 171 | llama-3.1-nemotron-ultra-253b-v1Nvidia | 1392.00 | +/-30 | 367 | Nvidia | Nvidia Open Model |
| 172 | ring-flash-2.0Ant Group | 1391.00 | +/-15 | 1,540 | Ant Group | MIT |
| 173 | GPT OSS 120BOpenAI | 1391.00 | +/-8 | 6,488 | OpenAI | Apache 2.0 |
| 174 | OpenAI o3-mini (high)OpenAI | 1390.00 | +/-10 | 3,296 | OpenAI | Proprietary |
| 175 |  C4AI Command A (202503)CohereAI | 1390.00 | +/-6 | 10,219 | CohereAI | CC-BY-NC-4.0 |
| 176 | amazon-nova-experimental-chat-10-09Amazon | 1389.00 | +/-24 | 552 | Amazon | Proprietary |
| 177 | DeepSeek-V3DeepSeek-AI | 1388.00 | +/-10 | 3,280 | DeepSeek-AI | DeepSeek |
| 178 | OpenAI o1-miniOpenAI | 1388.00 | +/-7 | 8,478 | OpenAI | Proprietary |
| 179 | Qwen3-30B-A3B阿里巴巴 | 1387.00 | +/-9 | 4,526 | 阿里巴巴 | Apache 2.0 |
| 180 | grok-3-mini-betaxAI | 1387.00 | +/-9 | 4,255 | xAI | Proprietary |
| 181 | Magistral-Medium-2506MistralAI | 1386.00 | +/-12 | 2,247 | MistralAI | Proprietary |
| 182 | QwQ-32B阿里巴巴 | 1385.00 | +/-9 | 4,047 | 阿里巴巴 | Apache 2.0 |
| 183 | Claude 3.5 HaikuAnthropic | 1385.00 | +/-6 | 11,246 | Anthropic | Proprietary |
| 184 | MiniMax M2MiniMaxAI | 1385.00 | +/-15 | 1,543 | MiniMaxAI | Apache 2.0 |
| 185 | olmo-3.1-32b-instructAi2 | 1384.00 | +/-12 | 2,511 | Ai2 | Apache 2.0 |
| 186 | Gemini 2.5 Flash-Lite (thinking)Google Deep Mind | 1384.00 | +/-8 | 6,001 | Google Deep Mind | Proprietary |
| 187 | GPT-5-Nano (high)OpenAI | 1383.00 | +/-15 | 1,684 | OpenAI | Proprietary |
| 188 | qwen-plus-0125Alibaba | 1380.00 | +/-18 | 893 | Alibaba | Proprietary |
| 189 |  llama-3.1-405b-instruct-bf16Meta | 1375.00 | +/-8 | 6,249 | Meta | Llama 3.1 Community |
| 190 | deepseek-v2.5-1210DeepSeek | 1375.00 | +/-17 | 1,079 | DeepSeek | DeepSeek |
| 191 | GPT-4.1 nanoOpenAI | 1374.00 | +/-19 | 807 | OpenAI | Proprietary |
| 192 | Llama 4 Maverick InstructFacebook AI研究实验室 | 1373.00 | +/-7 | 6,994 | Facebook AI研究实验室 | Llama 4 |
| 193 | hunyuan-turbo-0110Tencent | 1372.00 | +/-30 | 299 | Tencent | Proprietary |
| 194 | step-2-16k-exp-202412StepFun | 1372.00 | +/-20 | 737 | StepFun | Proprietary |
| 195 | GPT OSS 20BOpenAI | 1370.00 | +/-13 | 2,167 | OpenAI | Apache 2.0 |
| 196 | athene-v2-chatNexusFlow | 1370.00 | +/-9 | 4,019 | NexusFlow | NexusFlow |
| 197 | yi-lightning01 AI | 1369.00 | +/-10 | 4,316 | 01 AI | Proprietary |
| 198 | GPT-4oOpenAI | 1369.00 | +/-6 | 19,526 | OpenAI | Proprietary |
| 199 | DeepSeek V2.5DeepSeek-AI | 1369.00 | +/-9 | 4,252 | DeepSeek-AI | DeepSeek |
| 200 | llama-3.1-405b-instruct-fp8Meta | 1368.00 | +/-7 | 9,714 | Meta | Llama 3.1 Community |
| 201 | mercuryInception AI | 1367.00 | +/-29 | 394 | Inception AI | Proprietary |
| 202 | hunyuan-large-2025-02-10Tencent | 1367.00 | +/-25 | 519 | Tencent | Proprietary |
| 203 | Gemini 2.0 Flash ExperimentalDeepMind | 1365.00 | +/-7 | 6,996 | DeepMind | Proprietary |
| 204 | olmo-3-32b-thinkAi2 | 1364.00 | +/-18 | 1,056 | Ai2 | Apache 2.0 |
| 205 | llama-3.3-nemotron-49b-super-v1Nvidia | 1363.00 | +/-31 | 286 | Nvidia | Nvidia |
| 206 | nvidia-nemotron-3-nano-30b-a3b-bf16Nvidia | 1363.00 | +/-10 | 3,281 | Nvidia | NVIDIA Open Model |
| 207 | Llama 4 Scout InstructFacebook AI研究实验室 | 1362.00 | +/-9 | 5,253 | Facebook AI研究实验室 | Llama |
| 208 | Mistral-Small-3.1-24B-Instruct-2503MistralAI | 1362.00 | +/-8 | 6,137 | MistralAI | Apache 2.0 |
| 209 | GPT-4oOpenAI | 1361.00 | +/-8 | 7,318 | OpenAI | Proprietary |
| 210 | Grok 2xAI | 1359.00 | +/-7 | 10,368 | xAI | Proprietary |
| 211 | Gemma 3 - 27B (IT)Google Deep Mind | 1358.00 | +/-7 | 8,074 | Google Deep Mind | Gemma |
| 212 | qwen2.5-plus-1127Alibaba | 1357.00 | +/-14 | 1,553 | Alibaba | Proprietary |
| 213 | Gemini 1.5 ProGoogle Deep Mind | 1356.00 | +/-7 | 9,175 | Google Deep Mind | Proprietary |
| 214 | hunyuan-large-visionTencent | 1356.00 | +/-19 | 963 | Tencent | Proprietary |
| 215 | Qwen2.5-VL-72B-Instruct阿里巴巴 | 1356.00 | +/-8 | 6,688 | 阿里巴巴 | Qwen |
| 216 | Claude3-OpusAnthropic | 1354.00 | +/-6 | 33,748 | Anthropic | Proprietary |
| 217 | mistral-large-2407Mistral | 1354.00 | +/-8 | 7,589 | Mistral | Mistral Research |
| 218 | step-1o-turbo-202506StepFun | 1354.00 | +/-15 | 1,505 | StepFun | Proprietary |
| 219 | qwen-max-0919Alibaba | 1353.00 | +/-11 | 2,756 | Alibaba | Qwen |
| 220 | granite-4.1-8bIBM | 1353.00 | +/-20 | 1,075 | IBM | Apache 2.0 |
| 221 | glm-4-plusZhipu AI | 1353.00 | +/-9 | 4,449 | Zhipu AI | Proprietary |
| 222 | athene-70b-0725NexusFlow | 1350.00 | +/-11 | 3,122 | NexusFlow | CC-BY-NC-4.0 |
| 223 | GPT-4o miniOpenAI | 1349.00 | +/-7 | 10,927 | OpenAI | Proprietary |
| 224 | gpt-4-turbo-2024-04-09OpenAI | 1347.00 | +/-7 | 17,104 | OpenAI | Proprietary |
| 225 | Gemini 1.5 ProGoogle Deep Mind | 1347.00 | +/-8 | 12,747 | Google Deep Mind | Proprietary |
| 226 | mistral-large-2411Mistral | 1346.00 | +/-9 | 4,212 | Mistral | MRL |
| 227 | Llama3.3-70B-InstructFacebook AI研究实验室 | 1345.00 | +/-7 | 8,746 | Facebook AI研究实验室 | Llama-3.3 |
| 228 | Gemini 2.0 Flash-LiteDeepMind | 1343.00 | +/-10 | 3,474 | DeepMind | Proprietary |
| 229 | amazon-nova-pro-v1.0Amazon | 1343.00 | +/-9 | 3,853 | Amazon | Proprietary |
| 230 | Qwen2.5-Coder-32B-Instruct阿里巴巴 | 1342.00 | +/-19 | 873 | 阿里巴巴 | Apache 2.0 |
| 231 | deepseek-coder-v2DeepSeek | 1342.00 | +/-12 | 2,671 | DeepSeek | DeepSeek License |
| 232 | GPT-4OpenAI | 1339.00 | +/-7 | 15,605 | OpenAI | Proprietary |
| 233 | olmo-3.1-32b-thinkAi2 | 1339.00 | +/-15 | 1,568 | Ai2 | Apache 2.0 |
| 234 | gemini-advanced-0514Google | 1338.00 | +/-9 | 8,138 | Proprietary | |
| 235 | grok-2-mini-2024-08-13xAI | 1336.00 | +/-7 | 8,652 | xAI | Proprietary |
| 236 | 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 |
| 237 | hunyuan-standard-2025-02-10Tencent | 1332.00 | +/-24 | 549 | Tencent | Proprietary |
| 238 | GPT-4OpenAI | 1331.00 | +/-8 | 15,289 | OpenAI | Proprietary |
| 239 | glm-4-plus-0111Zhipu | 1331.00 | +/-18 | 894 | Zhipu | Proprietary |
| 240 | Llama3.1-70B-InstructFacebook AI研究实验室 | 1329.00 | +/-15 | 1,312 | Facebook AI研究实验室 | Llama 3.1 |
| 241 | ibm-granite-h-smallIBM | 1329.00 | +/-17 | 1,267 | IBM | Apache 2.0 |
| 242 | GPT-4OpenAI | 1328.00 | +/-9 | 8,306 | OpenAI | Proprietary |
| 243 | Claude3-SonnetAnthropic | 1317.00 | +/-7 | 18,888 | Anthropic | Proprietary |
| 244 | Gemma 3 - 12B (IT)Google Deep Mind | 1317.00 | +/-23 | 543 | Google Deep Mind | Gemma |
| 245 | gemini-1.5-flash-002Google | 1316.00 | +/-8 | 5,892 | Proprietary | |
| 246 | reka-core-20240904Reka AI | 1315.00 | +/-15 | 1,216 | Reka AI | Proprietary |
| 247 | GPT-4OpenAI | 1313.00 | +/-8 | 13,719 | OpenAI | Proprietary |
| 248 | Mistral Small 24B Instruct 2501MistralAI | 1312.00 | +/-12 | 2,083 | MistralAI | Apache 2.0 |
| 249 | jamba-1.5-largeAI21 Labs | 1312.00 | +/-15 | 1,440 | AI21 Labs | Jamba Open |
| 250 | llama-3.1-nemotron-51b-instructNvidia | 1311.00 | +/-22 | 665 | Nvidia | Llama 3.1 |
| 251 | gemini-1.5-flash-001Google | 1310.00 | +/-8 | 10,680 | Proprietary | |
| 252 | Gemma-3n-E4BGoogle Deep Mind | 1309.00 | +/-10 | 3,528 | Google Deep Mind | Gemma |
| 253 | GLM4智谱AI | 1308.00 | +/-14 | 1,718 | 智谱AI | Proprietary |
| 254 | llama-3.1-tulu-3-70bAi2 | 1308.00 | +/-24 | 450 | Ai2 | Llama 3.1 |
| 255 | nemotron-4-340b-instructNvidia | 1307.00 | +/-11 | 3,254 | Nvidia | NVIDIA Open Model |
| 256 |  Phi 4 - 14BMicrosoft Azure | 1307.00 | +/-10 | 3,305 | Microsoft Azure | MIT |
| 257 | amazon-nova-lite-v1.0Amazon | 1306.00 | +/-10 | 3,060 | Amazon | Proprietary |
| 258 | Llama3-70B-InstructFacebook AI研究实验室 | 1305.00 | +/-7 | 28,126 | Facebook AI研究实验室 | Llama 3 Community |
| 259 | gemma-2-27b-itGoogle | 1305.00 | +/-6 | 12,088 | Gemma license | |
| 260 | hunyuan-standard-256kTencent | 1301.00 | +/-25 | 497 | Tencent | Proprietary |
| 261 | Claude3-HaikuAnthropic | 1300.00 | +/-7 | 20,898 | Anthropic | Proprietary |
| 262 | Qwen2-72B-Instruct阿里巴巴 | 1296.00 | +/-9 | 6,249 | 阿里巴巴 | Qianwen LICENSE |
| 263 | mistral-large-2402Mistral | 1294.00 | +/-9 | 10,418 | Mistral | Proprietary |
| 264 | C4AI Aya Vision 32BCohereAI | 1292.00 | +/-9 | 4,685 | CohereAI | CC-BY-NC-4.0 |
| 265 | reka-flash-20240904Reka AI | 1291.00 | +/-15 | 1,207 | Reka AI | Proprietary |
| 266 | amazon-nova-micro-v1.0Amazon | 1288.00 | +/-10 | 2,981 | Amazon | Proprietary |
| 267 | Llama3.1-8B-InstructFacebook AI研究实验室 | 1287.00 | +/-26 | 478 | Facebook AI研究实验室 | Apache 2.0 |
| 268 | command-r-08-2024Cohere | 1280.00 | +/-13 | 1,783 | Cohere | CC-BY-NC-4.0 |
| 269 | olmo-2-0325-32b-instructAi2 | 1280.00 | +/-27 | 427 | Ai2 | Apache-2.0 |
| 270 | command-r-plus-08-2024Cohere | 1279.00 | +/-14 | 1,675 | Cohere | CC-BY-NC-4.0 |
| 271 | Qwen1.5-110B-Chat阿里巴巴 | 1279.00 | +/-10 | 4,763 | 阿里巴巴 | Qianwen LICENSE |
| 272 | reka-flash-21b-20240226-onlineReka AI | 1277.00 | +/-13 | 2,879 | Reka AI | Proprietary |
| 273 | Mixtral-8x22B-Instruct-v0.1MistralAI | 1276.00 | +/-9 | 8,780 | MistralAI | Apache 2.0 |
| 274 | ministral-8b-2410Mistral | 1275.00 | +/-19 | 838 | Mistral | MRL |
| 275 | Gemma 3 - 4B (IT)Google Deep Mind | 1274.00 | +/-24 | 605 | Google Deep Mind | Gemma |
| 276 | Qwen1.5-72B-Chat阿里巴巴 | 1274.00 | +/-10 | 6,370 | 阿里巴巴 | Qianwen LICENSE |
| 277 | gpt-3.5-turbo-0125OpenAI | 1274.00 | +/-8 | 11,130 | OpenAI | Proprietary |
| 278 | gemini-1.5-flash-8b-001Google | 1272.00 | +/-8 | 6,069 | Proprietary | |
| 279 | gemma-2-9b-it-simpoPrinceton | 1272.00 | +/-15 | 1,471 | Princeton | MIT |
| 280 | C4AI Command R+CohereAI | 1272.00 | +/-8 | 13,937 | CohereAI | CC-BY-NC-4.0 |
| 281 | gemma-2-9b-itGoogle | 1271.00 | +/-7 | 8,921 | Gemma license | |
| 282 | reka-flash-21b-20240226Reka AI | 1266.00 | +/-11 | 4,748 | Reka AI | Proprietary |
| 283 | jamba-1.5-miniAI21 Labs | 1265.00 | +/-15 | 1,352 | AI21 Labs | Jamba Open |
| 284 | mistral-mediumMistral | 1261.00 | +/-10 | 5,149 | Mistral | Proprietary |
| 285 | gpt-3.5-turbo-1106OpenAI | 1261.00 | +/-16 | 2,121 | OpenAI | Proprietary |
| 286 | qwen1.5-32b-chatAlibaba | 1261.00 | +/-11 | 3,930 | Alibaba | Qianwen LICENSE |
| 287 | Llama3.1-8B-InstructFacebook AI研究实验室 | 1260.00 | +/-7 | 8,582 | Facebook AI研究实验室 | Llama 3.1 Community |
| 288 | C4AI Aya Vision 8BCohereAI | 1255.00 | +/-15 | 1,567 | CohereAI | CC-BY-NC-4.0 |
| 289 | llama-3.1-tulu-3-8bAi2 | 1253.00 | +/-25 | 476 | Ai2 | Llama 3.1 |
| 290 | Llama3-8B-InstructFacebook AI研究实验室 | 1252.00 | +/-8 | 18,374 | Facebook AI研究实验室 | Llama 3 Community |
| 291 | DBRX Instructdatabricks | 1250.00 | +/-11 | 5,502 | databricks | DBRX LICENSE |
| 292 | granite-3.1-2b-instructIBM | 1248.00 | +/-25 | 508 | IBM | Apache 2.0 |
| 293 | Gemini-proDeepMind | 1248.00 | +/-24 | 678 | DeepMind | Proprietary |
| 294 | InternLM2-Base-20B上海人工智能实验室 | 1248.00 | +/-14 | 1,684 | 上海人工智能实验室 | Other |
| 295 | Yi-1.5-34B零一万物 | 1248.00 | +/-10 | 3,841 | 零一万物 | Apache-2.0 |
| 296 | zephyr-orpo-141b-A35b-v0.1HuggingFace | 1244.00 | +/-21 | 831 | HuggingFace | Apache 2.0 |
| 297 | command-rCohere | 1242.00 | +/-9 | 9,645 | Cohere | CC-BY-NC-4.0 |
| 298 | granite-3.0-8b-instructIBM | 1239.00 | +/-18 | 1,108 | IBM | Apache 2.0 |
| 299 | gemini-pro-dev-apiGoogle | 1239.00 | +/-14 | 2,681 | Proprietary | |
| 300 | Qwen1.5-14B-Chat阿里巴巴 | 1239.00 | +/-13 | 3,208 | 阿里巴巴 | Qianwen LICENSE |
| 301 | mixtral-8x7b-instruct-v0.1Mistral | 1238.00 | +/-8 | 11,784 | Mistral | Apache 2.0 |
| 302 | starling-lm-7b-betaNexusflow | 1234.00 | +/-13 | 2,948 | Nexusflow | Apache-2.0 |
| 303 | Phi-3-medium 14B-previewMicrosoft Azure | 1230.00 | +/-10 | 3,973 | Microsoft Azure | MIT |
| 304 | openchat-3.5-0106OpenChat | 1228.00 | +/-14 | 2,005 | OpenChat | Apache-2.0 |
| 305 | snowflake-arctic-instructSnowflake | 1223.00 | +/-11 | 5,734 | Snowflake | Apache 2.0 |
| 306 | DeepSeek LLM 67B ChatDeepSeek-AI | 1217.00 | +/-24 | 649 | DeepSeek-AI | DeepSeek License |
| 307 | Gemma 1.1-7B-ITGoogle Research | 1217.00 | +/-10 | 4,332 | Google Research | Gemma license |
| 308 | tulu-2-dpo-70bAllenAI/UW | 1214.00 | +/-21 | 805 | AllenAI/UW | AI2 ImpACT Low-risk |
| 309 | Qwen1.5-7B-Chat阿里巴巴 | 1209.00 | +/-21 | 772 | 阿里巴巴 | Qianwen LICENSE |
| 310 | Qwen3-VL-2B阿里巴巴 | 1208.00 | +/-18 | 1,134 | 阿里巴巴 | Apache 2.0 |
| 311 | starling-lm-7b-alphaUC Berkeley | 1206.00 | +/-16 | 1,397 | UC Berkeley | CC-BY-NC-4.0 |
| 312 | Yi-34B零一万物 | 1205.00 | +/-13 | 2,345 | 零一万物 | Yi License |
| 313 | Phi-3-small 7BMicrosoft Azure | 1204.00 | +/-12 | 3,219 | Microsoft Azure | MIT |
| 314 | openchat-3.5OpenChat | 1201.00 | +/-20 | 971 | OpenChat | Apache-2.0 |
| 315 | Qwen-14B-Chat阿里巴巴 | 1196.00 | +/-24 | 599 | 阿里巴巴 | Qianwen LICENSE |
| 316 | Phi-3-mini 3.8BMicrosoft Azure | 1196.00 | +/-14 | 1,841 | Microsoft Azure | MIT |
| 317 | gemma-2-2b-itGoogle | 1193.00 | +/-8 | 7,298 | Gemma license | |
| 318 | Vicuna 33BLM-SYS | 1192.00 | +/-13 | 2,866 | LM-SYS | Non-commercial |
| 319 | WizardLM-70B-V1.0WizardLM Team | 1192.00 | +/-20 | 988 | WizardLM Team | Llama 2 Community |
| 320 | Phi-3-mini 3.8BMicrosoft Azure | 1186.00 | +/-12 | 3,449 | Microsoft Azure | MIT |
| 321 | openhermes-2.5-mistral-7bNousResearch | 1185.00 | +/-23 | 589 | NousResearch | Apache-2.0 |
| 322 | Mistral-7B-Instruct-v0.2MistralAI | 1185.00 | +/-12 | 3,114 | MistralAI | Apache-2.0 |
| 323 | solar-10.7b-instruct-v1.0Upstage AI | 1182.00 | +/-27 | 482 | Upstage AI | CC-BY-NC-4.0 |
| 324 | llama-2-70b-chatMeta | 1178.00 | +/-10 | 5,717 | Meta | Llama 2 Community |
| 325 | llama-3.2-3b-instructMeta | 1176.00 | +/-16 | 1,351 | Meta | Llama 3.2 |
| 326 | nous-hermes-2-mixtral-8x7b-dpoNousResearch | 1174.00 | +/-24 | 575 | NousResearch | Apache-2.0 |
| 327 | QwQ-32B-Preview阿里巴巴 | 1173.00 | +/-24 | 566 | 阿里巴巴 | Apache 2.0 |
| 328 | Gemma 1.1-2B-ITGoogle Research | 1171.00 | +/-14 | 1,963 | Google Research | Gemma license |
| 329 | Gemma 7B - ItGoogle Research | 1167.00 | +/-17 | 1,381 | Google Research | Gemma license |
| 330 | MPT-30B-ChatMosaicML | 1167.00 | +/-35 | 258 | MosaicML | CC-BY-NC-SA-4.0 |
| 331 | zephyr-7b-alphaHuggingFace | 1166.00 | +/-40 | 201 | HuggingFace | MIT |
| 332 | Vicuna 13BLM-SYS | 1162.00 | +/-14 | 2,389 | LM-SYS | Llama 2 Community |
| 333 | Baichuan2-13B-Chat百川智能 | 1161.00 | +/-13 | 2,626 | 百川智能 | Llama 2 Community |
| 334 | smollm2-1.7b-instructHuggingFace | 1159.00 | +/-33 | 352 | HuggingFace | Apache 2.0 |
| 335 | CodeLLaMA-34BFacebook AI研究实验室 | 1158.00 | +/-20 | 853 | Facebook AI研究实验室 | Llama 2 Community |
| 336 | Phi-3-mini 3.8BMicrosoft Azure | 1153.00 | +/-13 | 3,886 | Microsoft Azure | MIT |
| 337 | PaLM 2Google Research | 1152.00 | +/-21 | 917 | Google Research | Proprietary |
| 338 | zephyr-7b-betaHuggingFace | 1151.00 | +/-18 | 1,250 | HuggingFace | MIT |
| 339 | wizardlm-13bMicrosoft | 1150.00 | +/-22 | 735 | Microsoft | Llama 2 Community |
| 340 | llama-3.2-1b-instructMeta | 1148.00 | +/-16 | 1,346 | Meta | Llama 3.2 |
| 341 | llama2-70b-steerlm-chatNvidia | 1144.00 | +/-28 | 467 | Nvidia | Llama 2 Community |
| 342 | Mistral 7B InstructMistralAI | 1143.00 | +/-20 | 1,032 | MistralAI | Apache 2.0 |
| 343 | Gemma 2B - ItGoogle Research | 1136.00 | +/-22 | 742 | Google Research | Gemma license |
| 344 | Vicuna 7BLM-SYS | 1130.00 | +/-23 | 726 | LM-SYS | Llama 2 Community |
| 345 | Qwen1.5-4B-Chat阿里巴巴 | 1130.00 | +/-17 | 1,283 | 阿里巴巴 | Qianwen LICENSE |
| 346 | stripedhyena-nous-7bTogether AI | 1126.00 | +/-22 | 704 | Together AI | Apache 2.0 |
| 347 | guanaco-33bUW | 1112.00 | +/-36 | 263 | UW | Non-commercial |
| 348 | olmo-7b-instructAi2 | 1106.00 | +/-22 | 772 | Ai2 | Apache-2.0 |
| 349 | Baichuan2-7B-Chat百川智能 | 1102.00 | +/-14 | 1,956 | 百川智能 | Llama 2 Community |
| 350 | ChatGLM3-6B智谱AI | 1089.00 | +/-26 | 535 | 智谱AI | Apache-2.0 |
| 351 | MPT-7B-ChatMosaicML | 1065.00 | +/-31 | 397 | MosaicML | CC-BY-NC-SA-4.0 |
| 352 | Koala达摩院 | 1065.00 | +/-24 | 747 | 达摩院 | Non-commercial |
| 353 | RWKV-4-Raven-14BRWKV | 1058.00 | +/-27 | 505 | RWKV | Apache 2.0 |
| 354 | oasst-pythia-12bOpenAssistant | 1049.00 | +/-25 | 714 | OpenAssistant | Apache 2.0 |
| 355 | ChatGLM-6B智谱AI | 1034.00 | +/-27 | 551 | 智谱AI | Non-commercial |
| 356 | ChatGLM2-6B智谱AI | 1029.00 | +/-35 | 293 | 智谱AI | Apache-2.0 |
| 357 | stablelm-tuned-alpha-7bStability AI | 1003.00 | +/-33 | 363 | Stability AI | CC-BY-NC-SA-4.0 |
| 358 | alpaca-13bStanford | 998.00 | +/-27 | 626 | Stanford | Non-commercial |
| 359 | dolly-v2-12bDatabricks | 961.00 | +/-34 | 396 | Databricks | MIT |
| 360 | fastchat-t5-3bLMSYS | 907.00 | +/-30 | 428 | LMSYS | Apache 2.0 |
| 361 | LLaMA 13BFacebook AI研究实验室 | 882.00 | +/-39 | 304 | Facebook AI研究实验室 | Non-commercial |
Data is for reference only. Official sources are authoritative. Click model names to view DataLearner model profiles.
FAQ
01
What is LMArena Coding Arena?
LMArena Coding Arena is an anonymous evaluation track focused on coding ability. Users submit real programming tasks such as debugging, code generation, and algorithm implementation; two hidden model answers are shown side by side, and user votes are aggregated into an Elo leaderboard.
02
How is Coding Arena different from SWE-bench or HumanEval?
Static benchmarks use fixed test sets and automated scoring, which makes them reproducible but easier to over-optimize for. Coding Arena uses open-ended user tasks and human preference votes, so it better reflects practical coding experience. The two approaches are complementary.
03
How do China-developed models perform on coding tasks?
Models such as DeepSeek and Qwen rank competitively on coding leaderboards. They are especially relevant when open deployment, Chinese-language developer workflows, or cost control matter.
04
How can AI help with day-to-day programming?
Common workflows include code completion and generation, debugging, code review, unit test generation, and cross-language translation.