Updated daily at 05:00 UTC
Benchmark
Code Arena: WebDev (arena.ai)
Measures: Users give a front-end web-development task, two anonymous models build it (including multi-step agentic coding with tools), and the user votes for the better app; votes are turned into an Elo-scale score with a confidence interval.
- Maintainer
- Arena Intelligence (arena.ai; formerly LMArena / LMSYS Chatbot Arena)
- Introduced
- 2024
- Status
- Active
- Saturation
- Headroom
- Typical provenance
- Independent
- In scoring set
- Yes
Leaderboard
Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.
| Model | Arena score (Elo scale) | Score CI (+/-) | Votes | Provenance | Source | Evaluated |
|---|---|---|---|---|---|---|
| Devstral Medium 1.0 | 1075 | — | 842 | Independent | Arena | 25 Sep 2026 |
| Grok 4 Fast SpaceXAI (xAI) · Reasoning effort | 1160 | — | 743 | Independent | Arena | 25 Sep 2026 |
| Grok Code Fast 1 | 1167 | — | 789 | Independent | Arena | 25 Sep 2026 |
| Mercury 2 | 1170 | — | 955 | Independent | Arena | 25 Sep 2026 |
| Granite 4.1 8B | 1191 | — | 1773 | Independent | Arena | 25 Sep 2026 |
| Devstral 2 | 1196 | — | 1182 | Independent | Arena | 25 Sep 2026 |
| Grok 4.1 SpaceXAI (xAI) · Thinking effort | 1214 | — | 961 | Independent | Arena | 25 Sep 2026 |
| Gemini 2.5 Pro | 1227 | — | 2731 | Independent | Arena | 25 Sep 2026 |
| Mistral Large 3 | 1230 | — | 840 | Independent | Arena | 25 Sep 2026 |
| Trinity Large Thinking Arcee AI · Thinking effort | 1238 | — | 1362 | Independent | Arena | 25 Sep 2026 |
| Grok 4.1 Fast SpaceXAI (xAI) · Reasoning effort | 1242 | — | 5490 | Independent | Arena | 25 Sep 2026 |
| Qwen3.5-Flash | 1243 | — | 1329 | Independent | Arena | 25 Sep 2026 |
| GPT-5.1-Codex-Mini | 1244 | — | 1155 | Independent | Arena | 25 Sep 2026 |
| Qwen3.5-35B-A3B | 1254 | — | 1617 | Independent | Arena | 25 Sep 2026 |
| Gemini 3.1 Flash-Lite | 1256 | — | 14412 | Independent | Arena | 25 Sep 2026 |
| Mistral Medium 3.5 | 1263 | — | 2322 | Independent | Arena | 25 Sep 2026 |
| DeepSeek-V3.2-Exp | 1272 | — | 3972 | Independent | Arena | 25 Sep 2026 |
| Qwen3-Coder-480B-A35B-Instruct | 1274 | — | 12720 | Independent | Arena | 25 Sep 2026 |
| MiniMax-M2 | 1297 | — | 6717 | Independent | Arena | 25 Sep 2026 |
| Laguna XS.2 | 1302 | — | 4248 | Independent | Arena | 25 Sep 2026 |
| Kimi K2 Thinking | 1322 | — | 13100 | Independent | Arena | 25 Sep 2026 |
| DeepSeek-V3.2 | 1325 | — | 9388 | Independent | Arena | 25 Sep 2026 |
| Claude Haiku 4.5 | 1330 | — | 29211 | Independent | Arena | 25 Sep 2026 |
| GPT-5.1-Codex | 1337 | — | 5012 | Independent | Arena | 25 Sep 2026 |
| GPT-5.2-Codex | 1339 | — | 6723 | Independent | Arena | 25 Sep 2026 |
| GLM-4.6 | 1339 | — | 6782 | Independent | Arena | 25 Sep 2026 |
| GPT-5.1 | 1341 | — | 10720 | Independent | Arena | 25 Sep 2026 |
| Laguna M.1 | 1348 | — | 5425 | Independent | Arena | 25 Sep 2026 |
| Grok 4.3 | 1357 | — | 15063 | Independent | Arena | 25 Sep 2026 |
| Qwen3.5-27B | 1357 | — | 7783 | Independent | Arena | 25 Sep 2026 |
| Gemma 4 26B A4B | 1358 | — | 1505 | Independent | Arena | 25 Sep 2026 |
| Qwen3.5-122B-A10B | 1360 | — | 8239 | Independent | Arena | 25 Sep 2026 |
| DeepSeek-V3.2 DeepSeek · Thinking effort | 1362 | — | 6922 | Independent | Arena | 25 Sep 2026 |
| Gemma 4 31B | 1363 | — | 12479 | Independent | Arena | 25 Sep 2026 |
| Solar Pro 4 | 1372 | — | 4813 | Independent | Arena | 25 Sep 2026 |
| Grok 4.20 SpaceXAI (xAI) · Reasoning effort | 1374 | — | 15502 | Independent | Arena | 25 Sep 2026 |
| Claude Sonnet 4.5 | 1384 | — | 15728 | Independent | Arena | 25 Sep 2026 |
| MiniMax-M2.5 | 1386 | — | 7637 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 4.1 | 1390 | — | 6933 | Independent | Arena | 25 Sep 2026 |
| GPT-5.4 | 1394 | — | 3484 | Independent | Arena | 25 Sep 2026 |
| GPT-5.1 OpenAI · Medium effort | 1394 | — | 4915 | Independent | Arena | 25 Sep 2026 |
| MiniMax-M2.7 | 1397 | — | 16103 | Independent | Arena | 25 Sep 2026 |
| GPT-5.4 mini OpenAI · High effort | 1397 | — | 12008 | Independent | Arena | 25 Sep 2026 |
| Qwen3.5-397B-A17B | 1400 | — | 21305 | Independent | Arena | 25 Sep 2026 |
| GLM-5V-Turbo | 1400 | — | 2426 | Independent | Arena | 25 Sep 2026 |
| Inkling Small | 1408 | — | 5441 | Independent | Arena | 25 Sep 2026 |
| Inkling | 1411 | — | 12520 | Independent | Arena | 25 Sep 2026 |
| GPT-5.2 | 1415 | — | 1083 | Independent | Arena | 25 Sep 2026 |
| GPT-5 OpenAI · Medium effort | 1418 | — | 3090 | Independent | Arena | 25 Sep 2026 |
| MiMo-V2-Pro | 1433 | — | 7247 | Independent | Arena | 25 Sep 2026 |
| GLM-5 | 1434 | — | 7504 | Independent | Arena | 25 Sep 2026 |
| GLM-4.7 | 1435 | — | 4007 | Independent | Arena | 25 Sep 2026 |
| Kimi K2.5 Moonshot AI · Thinking effort | 1436 | — | 20171 | Independent | Arena | 25 Sep 2026 |
| MiMo-V2.5 | 1438 | — | 15041 | Independent | Arena | 25 Sep 2026 |
| Gemini 3 Flash | 1439 | — | 10900 | Independent | Arena | 25 Sep 2026 |
| Gemini 3 Pro | 1439 | — | 14103 | Independent | Arena | 25 Sep 2026 |
| Gemini 3.5 Flash-Lite | 1439 | — | 242 | Independent | Arena | 25 Sep 2026 |
| DeepSeek-V4-Pro | 1446 | — | 14064 | Independent | Arena | 25 Sep 2026 |
| Gemini 3.1 Pro | 1446 | — | 24363 | Independent | Arena | 25 Sep 2026 |
| Qwen3.6-Plus | 1461 | — | 18718 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 4.5 | 1468 | — | 13430 | Independent | Arena | 25 Sep 2026 |
| Kimi K2.7 Code | 1473 | — | 5004 | Independent | Arena | 25 Sep 2026 |
| MiMo-V2.5-Pro | 1477 | — | 19401 | Independent | Arena | 25 Sep 2026 |
| Qwen3.6-Max-Preview | 1481 | — | 2713 | Independent | Arena | 25 Sep 2026 |
| MiniMax-M3 | 1483 | — | 16349 | Independent | Arena | 25 Sep 2026 |
| Gemini 3.5 Flash Google DeepMind · Medium effort | 1490 | — | 12270 | Independent | Arena | 25 Sep 2026 |
| Gemini 3.5 Flash Google DeepMind · High effort | 1499 | — | 9530 | Independent | Arena | 25 Sep 2026 |
| GLM-5.1 | 1508 | — | 10822 | Independent | Arena | 25 Sep 2026 |
| Kimi K2.6 | 1509 | — | 10202 | Independent | Arena | 25 Sep 2026 |
| Hy3 | 1509 | — | 5302 | Independent | Arena | 25 Sep 2026 |
| Qwen3.7-Max | 1515 | — | 8931 | Independent | Arena | 25 Sep 2026 |
| Claude Sonnet 4.6 | 1521 | — | 22980 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 4.8 | 1535 | — | 16576 | Independent | Arena | 25 Sep 2026 |
| Gemini 3.6 Flash Google DeepMind · High effort | 1536 | — | 8857 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 4.6 | 1537 | — | 20788 | Independent | Arena | 25 Sep 2026 |
| Claude Sonnet 5 Anthropic · High effort | 1539 | — | 12862 | Independent | Arena | 25 Sep 2026 |
| Muse Spark 1.1 | 1541 | — | 8102 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 4.6 Anthropic · High effort | 1546 | — | 19527 | Independent | Arena | 25 Sep 2026 |
| Grok 4.5 | 1552 | — | 11302 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 4.8 Anthropic · High effort | 1555 | — | 17611 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 4.7 | 1556 | — | 16945 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 4.7 Anthropic · High effort | 1557 | — | 17538 | Independent | Arena | 25 Sep 2026 |
| Step 5 Preview StepFun · High effort | 1565 | — | 1247 | Independent | Arena | 25 Sep 2026 |
| Gemini 3.8 Flash Google DeepMind · High effort | 1580 | — | 7338 | Independent | Arena | 25 Sep 2026 |
| DeepSeek-V4-Flash DeepSeek · High effort | 1581 | — | 5067 | Independent | Arena | 25 Sep 2026 |
| DeepSeek-V4-Pro | 1582 | — | 4897 | Independent | Arena | 25 Sep 2026 |
| Qwen3.8-27B | 1591 | — | 10236 | Independent | Arena | 25 Sep 2026 |
| GPT-6 Luna OpenAI · Max effort | 1593 | — | 1903 | Independent | Arena | 25 Sep 2026 |
| Gemini 3.7 Flash Google DeepMind · High effort | 1593 | — | 8086 | Independent | Arena | 25 Sep 2026 |
| GLM-5.2 Z.ai (Zhipu AI) · Max effort | 1602 | — | 13601 | Independent | Arena | 25 Sep 2026 |
| GLM-5.3-Flash | 1613 | — | 6665 | Independent | Arena | 25 Sep 2026 |
| MiMo-V2.6-Pro | 1618 | — | 2591 | Independent | Arena | 25 Sep 2026 |
| GLM-5.3 Z.ai (Zhipu AI) · Max effort | 1619 | — | 6410 | Independent | Arena | 25 Sep 2026 |
| Grok 4.6 SpaceXAI (xAI) · High effort | 1621 | — | 7040 | Independent | Arena | 25 Sep 2026 |
| DeepSeek-V4.1-Flash DeepSeek · Max effort | 1621 | — | 3815 | Independent | Arena | 25 Sep 2026 |
| Claude Fable 5 Anthropic · High effort | 1627 | — | 13086 | Independent | Arena | 25 Sep 2026 |
| Grok 4.7 SpaceXAI (xAI) · Xhigh effort | 1629 | — | 2047 | Independent | Arena | 25 Sep 2026 |
| Hy4 preview | 1631 | — | 4954 | Independent | Arena | 25 Sep 2026 |
| Qwen3.8-Flash-Next | 1636 | — | 4980 | Independent | Arena | 25 Sep 2026 |
| Muse Spark 1.3 Meta · Max effort | 1656 | — | 5945 | Independent | Arena | 25 Sep 2026 |
| Kimi K3 Moonshot AI · Max effort | 1660 | — | 14739 | Independent | Arena | 25 Sep 2026 |
| Qwen3.8-Max | 1662 | — | 6203 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 5 Anthropic · High effort | 1662 | — | 18930 | Independent | Arena | 25 Sep 2026 |
| Qwen3.8-Max Alibaba Group · Max effort | 1672 | — | 3469 | Independent | Arena | 25 Sep 2026 |
| GPT-6 Sol OpenAI · Max effort | 1681 | — | 2019 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 5 Anthropic · Max effort | 1693 | — | 15627 | Independent | Arena | 25 Sep 2026 |
| Claude Fable 5.1 Anthropic · Max effort | 1751 | — | 5313 | Independent | Arena | 25 Sep 2026 |
| GPT-6 Astra OpenAI · Max effort | 1792 | — | 4908 | Independent | Arena | 25 Sep 2026 |
| Claude Opus 5.5 Anthropic · Max effort | 1827 | — | 1607 | Independent | Arena | 25 Sep 2026 |
- Arena (arena.ai), lmarena-ai/leaderboard-dataset, CC BY 4.0.