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

Official leaderboard

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

Leaderboard
ModelArena score (Elo scale)Score CI (+/-)VotesProvenanceSourceEvaluated
Claude Opus 5.5
Anthropic · Max effort
1827—1607IndependentArena25 Sep 2026
GPT-6 Astra
OpenAI · Max effort
1792—4908IndependentArena25 Sep 2026
Claude Fable 5.1
Anthropic · Max effort
1751—5313IndependentArena25 Sep 2026
Claude Opus 5
Anthropic · Max effort
1693—15627IndependentArena25 Sep 2026
GPT-6 Sol
OpenAI · Max effort
1681—2019IndependentArena25 Sep 2026
Qwen3.8-Max
Alibaba Group · Max effort
1672—3469IndependentArena25 Sep 2026
Claude Opus 5
Anthropic · High effort
1662—18930IndependentArena25 Sep 2026
Qwen3.8-Max1662—6203IndependentArena25 Sep 2026
Kimi K3
Moonshot AI · Max effort
1660—14739IndependentArena25 Sep 2026
Muse Spark 1.3
Meta · Max effort
1656—5945IndependentArena25 Sep 2026
Qwen3.8-Flash-Next1636—4980IndependentArena25 Sep 2026
Hy4 preview1631—4954IndependentArena25 Sep 2026
Grok 4.7
SpaceXAI (xAI) · Xhigh effort
1629—2047IndependentArena25 Sep 2026
Claude Fable 5
Anthropic · High effort
1627—13086IndependentArena25 Sep 2026
DeepSeek-V4.1-Flash
DeepSeek · Max effort
1621—3815IndependentArena25 Sep 2026
Grok 4.6
SpaceXAI (xAI) · High effort
1621—7040IndependentArena25 Sep 2026
GLM-5.3
Z.ai (Zhipu AI) · Max effort
1619—6410IndependentArena25 Sep 2026
MiMo-V2.6-Pro1618—2591IndependentArena25 Sep 2026
GLM-5.3-Flash1613—6665IndependentArena25 Sep 2026
GLM-5.2
Z.ai (Zhipu AI) · Max effort
1602—13601IndependentArena25 Sep 2026
Gemini 3.7 Flash
Google DeepMind · High effort
1593—8086IndependentArena25 Sep 2026
GPT-6 Luna
OpenAI · Max effort
1593—1903IndependentArena25 Sep 2026
Qwen3.8-27B1591—10236IndependentArena25 Sep 2026
DeepSeek-V4-Pro1582—4897IndependentArena25 Sep 2026
DeepSeek-V4-Flash
DeepSeek · High effort
1581—5067IndependentArena25 Sep 2026
Gemini 3.8 Flash
Google DeepMind · High effort
1580—7338IndependentArena25 Sep 2026
Step 5 Preview
StepFun · High effort
1565—1247IndependentArena25 Sep 2026
Claude Opus 4.7
Anthropic · High effort
1557—17538IndependentArena25 Sep 2026
Claude Opus 4.71556—16945IndependentArena25 Sep 2026
Claude Opus 4.8
Anthropic · High effort
1555—17611IndependentArena25 Sep 2026
Grok 4.51552—11302IndependentArena25 Sep 2026
Claude Opus 4.6
Anthropic · High effort
1546—19527IndependentArena25 Sep 2026
Muse Spark 1.11541—8102IndependentArena25 Sep 2026
Claude Sonnet 5
Anthropic · High effort
1539—12862IndependentArena25 Sep 2026
Claude Opus 4.61537—20788IndependentArena25 Sep 2026
Gemini 3.6 Flash
Google DeepMind · High effort
1536—8857IndependentArena25 Sep 2026
Claude Opus 4.81535—16576IndependentArena25 Sep 2026
Claude Sonnet 4.61521—22980IndependentArena25 Sep 2026
Qwen3.7-Max1515—8931IndependentArena25 Sep 2026
Hy31509—5302IndependentArena25 Sep 2026
Kimi K2.61509—10202IndependentArena25 Sep 2026
GLM-5.11508—10822IndependentArena25 Sep 2026
Gemini 3.5 Flash
Google DeepMind · High effort
1499—9530IndependentArena25 Sep 2026
Gemini 3.5 Flash
Google DeepMind · Medium effort
1490—12270IndependentArena25 Sep 2026
MiniMax-M31483—16349IndependentArena25 Sep 2026
Qwen3.6-Max-Preview1481—2713IndependentArena25 Sep 2026
MiMo-V2.5-Pro1477—19401IndependentArena25 Sep 2026
Kimi K2.7 Code1473—5004IndependentArena25 Sep 2026
Claude Opus 4.51468—13430IndependentArena25 Sep 2026
Qwen3.6-Plus1461—18718IndependentArena25 Sep 2026
Gemini 3.1 Pro1446—24363IndependentArena25 Sep 2026
DeepSeek-V4-Pro1446—14064IndependentArena25 Sep 2026
Gemini 3.5 Flash-Lite1439—242IndependentArena25 Sep 2026
Gemini 3 Pro1439—14103IndependentArena25 Sep 2026
Gemini 3 Flash1439—10900IndependentArena25 Sep 2026
MiMo-V2.51438—15041IndependentArena25 Sep 2026
Kimi K2.5
Moonshot AI · Thinking effort
1436—20171IndependentArena25 Sep 2026
GLM-4.71435—4007IndependentArena25 Sep 2026
GLM-51434—7504IndependentArena25 Sep 2026
MiMo-V2-Pro1433—7247IndependentArena25 Sep 2026
GPT-5
OpenAI · Medium effort
1418—3090IndependentArena25 Sep 2026
GPT-5.21415—1083IndependentArena25 Sep 2026
Inkling1411—12520IndependentArena25 Sep 2026
Inkling Small1408—5441IndependentArena25 Sep 2026
GLM-5V-Turbo1400—2426IndependentArena25 Sep 2026
Qwen3.5-397B-A17B1400—21305IndependentArena25 Sep 2026
GPT-5.4 mini
OpenAI · High effort
1397—12008IndependentArena25 Sep 2026
MiniMax-M2.71397—16103IndependentArena25 Sep 2026
GPT-5.1
OpenAI · Medium effort
1394—4915IndependentArena25 Sep 2026
GPT-5.41394—3484IndependentArena25 Sep 2026
Claude Opus 4.11390—6933IndependentArena25 Sep 2026
MiniMax-M2.51386—7637IndependentArena25 Sep 2026
Claude Sonnet 4.51384—15728IndependentArena25 Sep 2026
Grok 4.20
SpaceXAI (xAI) · Reasoning effort
1374—15502IndependentArena25 Sep 2026
Solar Pro 41372—4813IndependentArena25 Sep 2026
Gemma 4 31B1363—12479IndependentArena25 Sep 2026
DeepSeek-V3.2
DeepSeek · Thinking effort
1362—6922IndependentArena25 Sep 2026
Qwen3.5-122B-A10B1360—8239IndependentArena25 Sep 2026
Gemma 4 26B A4B1358—1505IndependentArena25 Sep 2026
Qwen3.5-27B1357—7783IndependentArena25 Sep 2026
Grok 4.31357—15063IndependentArena25 Sep 2026
Laguna M.11348—5425IndependentArena25 Sep 2026
GPT-5.11341—10720IndependentArena25 Sep 2026
GLM-4.61339—6782IndependentArena25 Sep 2026
GPT-5.2-Codex1339—6723IndependentArena25 Sep 2026
GPT-5.1-Codex1337—5012IndependentArena25 Sep 2026
Claude Haiku 4.51330—29211IndependentArena25 Sep 2026
DeepSeek-V3.21325—9388IndependentArena25 Sep 2026
Kimi K2 Thinking1322—13100IndependentArena25 Sep 2026
Laguna XS.21302—4248IndependentArena25 Sep 2026
MiniMax-M21297—6717IndependentArena25 Sep 2026
Qwen3-Coder-480B-A35B-Instruct1274—12720IndependentArena25 Sep 2026
DeepSeek-V3.2-Exp1272—3972IndependentArena25 Sep 2026
Mistral Medium 3.51263—2322IndependentArena25 Sep 2026
Gemini 3.1 Flash-Lite1256—14412IndependentArena25 Sep 2026
Qwen3.5-35B-A3B1254—1617IndependentArena25 Sep 2026
GPT-5.1-Codex-Mini1244—1155IndependentArena25 Sep 2026
Qwen3.5-Flash1243—1329IndependentArena25 Sep 2026
Grok 4.1 Fast
SpaceXAI (xAI) · Reasoning effort
1242—5490IndependentArena25 Sep 2026
Trinity Large Thinking
Arcee AI · Thinking effort
1238—1362IndependentArena25 Sep 2026
Mistral Large 31230—840IndependentArena25 Sep 2026
Gemini 2.5 Pro1227—2731IndependentArena25 Sep 2026
Grok 4.1
SpaceXAI (xAI) · Thinking effort
1214—961IndependentArena25 Sep 2026
Devstral 21196—1182IndependentArena25 Sep 2026
Granite 4.1 8B1191—1773IndependentArena25 Sep 2026
Mercury 21170—955IndependentArena25 Sep 2026
Grok Code Fast 11167—789IndependentArena25 Sep 2026
Grok 4 Fast
SpaceXAI (xAI) · Reasoning effort
1160—743IndependentArena25 Sep 2026
Devstral Medium 1.01075—842IndependentArena25 Sep 2026
  • Arena (arena.ai), lmarena-ai/leaderboard-dataset, CC BY 4.0.

Sources