Unspecified benchmark
LM Arena Webdev Leaderboard
LM Arena Webdev is a current leaderboard using the Arena Rating metric.
Updated Oct 23, 2026
Models100
Model coverage107
MetricArena Rating
EvidenceA
LM Arena Webdev Ranking
Higher arena rating ranks better on this benchmark.
Sort by
Rank | Model | Arena Rating | Percentile | Participants | Votes | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Arena Rating1,773.78 rating (1,763.61 rating - 1,783.95 rating) | Percentile100.00% | Participants107 | Votes6,169 | EvidenceA | Evaluated |
| Rank02 | ModelAN | Arena Rating1,768.33 rating (1,755.54 rating - 1,781.11 rating) | Percentile99.06% | Participants107 | Votes3,428 | EvidenceA | Evaluated |
| Rank03 | ModelAN | Arena Rating1,742.70 rating (1,733.78 rating - 1,751.63 rating) | Percentile98.11% | Participants107 | Votes7,744 | EvidenceA | Evaluated |
| Rank04 | ModelAN | Arena Rating1,688.86 rating (1,682.65 rating - 1,695.06 rating) | Percentile97.17% | Participants107 | Votes18,555 | EvidenceA | Evaluated |
| Rank05 | ModelGO | Arena Rating1,678.26 rating (1,662.67 rating - 1,693.85 rating) | Percentile96.23% | Participants107 | Votes1,728 | EvidenceA | Evaluated |
| Rank06 | ModelAC | Arena Rating1,674.29 rating (1,667.26 rating - 1,681.32 rating) | Percentile95.28% | Participants107 | Votes14,421 | EvidenceA | Evaluated |
| Rank07 | ModelME | Arena Rating1,659.26 rating (1,651.39 rating - 1,667.12 rating) | Percentile94.34% | Participants107 | Votes9,407 | EvidenceA | Evaluated |
| Rank08 | ModelMA | Arena Rating1,655.29 rating (1,649.31 rating - 1,661.26 rating) | Percentile93.40% | Participants107 | Votes19,592 | EvidenceA | Evaluated |
| Rank09 | ModelXA | Arena Rating1,636.98 rating (1,627.45 rating - 1,646.51 rating) | Percentile92.45% | Participants107 | Votes5,303 | EvidenceA | Evaluated |
| Rank10 | ModelXI | Arena Rating1,633.63 rating (1,624.18 rating - 1,643.08 rating) | Percentile91.51% | Participants107 | Votes5,293 | EvidenceA | Evaluated |
| Rank11 | ModelTE | Arena Rating1,630.97 rating (1,621.34 rating - 1,640.61 rating) | Percentile90.57% | Participants107 | Votes4,798 | EvidenceA | Evaluated |
| Rank12 | ModelAC | Arena Rating1,628.61 rating (1,620.65 rating - 1,636.56 rating) | Percentile89.62% | Participants107 | Votes8,382 | EvidenceA | Evaluated |
| Rank13 | ModelXI | Arena Rating1,624.99 rating (1,615.41 rating - 1,634.57 rating) | Percentile88.68% | Participants107 | Votes5,041 | EvidenceA | Evaluated |
| Rank14 | ModelAN | Arena Rating1,624.28 rating (1,618.15 rating - 1,630.41 rating) | Percentile87.74% | Participants107 | Votes15,899 | EvidenceA | Evaluated |
| Rank15 | ModelZA | Arena Rating1,621.19 rating (1,613.64 rating - 1,628.74 rating) | Percentile86.79% | Participants107 | Votes9,828 | EvidenceA | Evaluated |
| Rank16 | ModelXA | Arena Rating1,616.64 rating (1,609.32 rating - 1,623.96 rating) | Percentile85.85% | Participants107 | Votes10,483 | EvidenceA | Evaluated |
| Rank17 | ModelOP | Arena Rating1,615.62 rating (1,609.73 rating - 1,621.51 rating) | Percentile84.91% | Participants107 | Votes17,786 | EvidenceA | Evaluated |
| Rank18 | ModelZA | Arena Rating1,606.83 rating (1,600.27 rating - 1,613.39 rating) | Percentile83.96% | Participants107 | Votes18,264 | EvidenceA | Evaluated |
| Rank19 | ModelZA | Arena Rating1,604.22 rating (1,598.16 rating - 1,610.27 rating) | Percentile83.02% | Participants107 | Votes16,657 | EvidenceA | Evaluated |
| Rank20 | ModelAC | Arena Rating1,592.76 rating (1,586.24 rating - 1,599.29 rating) | Percentile82.08% | Participants107 | Votes16,385 | EvidenceA | Evaluated |
| Rank21 | ModelGO | Arena Rating1,590.78 rating (1,584.00 rating - 1,597.55 rating) | Percentile81.13% | Participants107 | Votes12,636 | EvidenceA | Evaluated |
| Rank22 | ModelMI | Arena Rating1,587.48 rating (1,573.22 rating - 1,601.74 rating) | Percentile80.19% | Participants107 | Votes1,853 | EvidenceA | Evaluated |
| Rank23 | ModelAN | Arena Rating1,586.15 rating (1,575.24 rating - 1,597.07 rating) | Percentile79.25% | Participants107 | Votes3,514 | EvidenceA | Evaluated |
| Rank24 | ModelGO | Arena Rating1,584.70 rating (1,577.34 rating - 1,592.05 rating) | Percentile78.30% | Participants107 | Votes10,851 | EvidenceA | Evaluated |
| Rank25 | ModelDE | Arena Rating1,582.38 rating (1,572.91 rating - 1,591.85 rating) | Percentile77.36% | Participants107 | Votes4,714 | EvidenceA | Evaluated |
| Rank26 | ModelDE | Arena Rating1,582.10 rating (1,572.80 rating - 1,591.39 rating) | Percentile76.42% | Participants107 | Votes4,947 | EvidenceA | Evaluated |
| Rank27 | ModelAN | Arena Rating1,557.87 rating (1,552.12 rating - 1,563.63 rating) | Percentile75.47% | Participants107 | Votes17,910 | EvidenceA | Evaluated |
| Rank28 | ModelAN | Arena Rating1,555.88 rating (1,550.12 rating - 1,561.64 rating) | Percentile74.53% | Participants107 | Votes18,493 | EvidenceA | Evaluated |
| Rank29 | ModelXA | Arena Rating1,552.97 rating (1,546.29 rating - 1,559.65 rating) | Percentile73.58% | Participants107 | Votes11,082 | EvidenceA | Evaluated |
| Rank30 | ModelAN | Arena Rating1,546.56 rating (1,541.09 rating - 1,552.02 rating) | Percentile72.64% | Participants107 | Votes19,383 | EvidenceA | Evaluated |
LM Arena Webdev Highlights
The leading models and scores on this benchmark.
LM Arena Webdev Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LM Arena Webdev
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is LM Arena Webdev?
What LM Arena Webdev measures and how its scores work.
LM Arena Webdev is a current leaderboard.
It reports Arena Rating in rating units.
Scores are shown in rating. This benchmark is verified and has an evidence level of A.
- Family
- lm-arena-webdev
- Modality
- Unspecified
- Primary category
- Unspecified
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LM Arena. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about LM Arena Webdev.
Which model scores highest on LM Arena Webdev?
GPT-6 Astra is currently ranked first with 1,773.78 rating.
What are the top three models on LM Arena Webdev?
The current leaders are GPT-6 Astra (1,773.78 rating), Claude Sonnet 5.5 (1,768.33 rating), and Claude Fable 5.1 (1,742.70 rating).
Which LM Arena Webdev model has the lowest official input price?
Claude Haiku 5.5 has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.
Which models are fastest among LM Arena Webdev results?
The fastest matched records are Gemini 3.7 Flash (409.96 tok/s via Google), GPT-5.6 Luna (215.52 tok/s via OpenAI), and GPT-5.1 Codex Mini (200.00 tok/s via OpenAI).
Does the highest arena rating result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.