Arena ranking
Browse Webdev results, model ratings and supporting selection context.
Data as of 2026-09-08
This source leaderboard ranking orders models by their original Arena rank rather than an aggregated benchmark score.
Rank | Model | Source Arena rating | LLMBoard Score | Votes | Official input / 1M | Output speed |
|---|
| Rank01 | ModelOP | Source Arena rating1,797.04 | LLMBoard ScoreN/A | Votes1,199 | Official input / 1M$10 | Output speed30.66 tok/s |
| Rank02 | ModelAN | Source Arena rating1,762.25 | LLMBoard ScoreN/A | Votes2,275 | Official input / 1M$10 | Output speed7.67 tok/s |
| Rank03 | ModelAN | Source Arena rating1,687.61 | LLMBoard ScoreN/A | Votes10,904 | Official input / 1M$5 | Output speed62.88 tok/s |
| Rank04 | ModelAC | Source Arena rating1,686.07 | LLMBoard ScoreN/A | Votes1,868 | Official input / 1M$2 | Output speed60.87 tok/s |
| Rank05 | ModelMA | Source Arena rating1,674.35 | LLMBoard ScoreN/A | Votes4,546 | Official input / 1M$3 | Output speedN/A |
| Rank06 | ModelAN | Source Arena rating1,629.05 | LLMBoard ScoreN/A | Votes9,356 | Official input / 1M$10 | Output speed43.18 tok/s |
| Rank07 | ModelAC | Source Arena rating1,626.46 | LLMBoard ScoreN/A | Votes2,158 | Official input / 1MN/A | Output speedN/A |
| Rank08 | ModelXA | Source Arena rating1,624.86 | LLMBoard ScoreN/A | Votes3,487 | Official input / 1M$2 | Output speed132.69 tok/s |
| Rank09 | ModelME | Source Arena rating1,622.48 | LLMBoard ScoreN/A | Votes1,274 | Official input / 1M$1.25 | Output speed8.44 tok/s |
| Rank10 | ModelTE | Source Arena rating1,621.26 | LLMBoard ScoreN/A | Votes1,661 | Official input / 1MN/A | Output speedN/A |
| Rank11 | ModelOP | Source Arena rating1,617.42 | LLMBoard ScoreN/A | Votes11,014 | Official input / 1M$4 | Output speed2.36 tok/s |
| Rank12 | ModelZA | Source Arena rating1,608.96 | LLMBoard ScoreN/A | Votes2,930 | Official input / 1M$1.4 | Output speed472.69 tok/s |
| Rank13 | ModelZA | Source Arena rating1,604.97 | LLMBoard ScoreN/A | Votes1,961 | Official input / 1M$0.075 | Output speed74.28 tok/s |
| Rank14 | ModelAC | Source Arena rating1,593.73 | LLMBoard ScoreN/A | Votes3,543 | Official input / 1MN/A | Output speedN/A |
| Rank15 | ModelGO | Source Arena rating1,586.89 | LLMBoard ScoreN/A | Votes3,008 | Official input / 1M$0.75 | Output speed117.86 tok/s |
| Rank16 | ModelZA | Source Arena rating1,586.57 | LLMBoard ScoreN/A | Votes9,836 | Official input / 1M$1.4 | Output speed3.96 tok/s |
| Rank17 | ModelDE | Source Arena rating1,581.68 | LLMBoard ScoreN/A | Votes3,518 | Official input / 1MN/A | Output speed45.48 tok/s |
| Rank18 | ModelDE | Source Arena rating1,579.64 | LLMBoard ScoreN/A | Votes4,177 | Official input / 1M$0.14 | Output speed15.91 tok/s |
| Rank19 | ModelGO | Source Arena rating1,567.23 | LLMBoard ScoreN/A | Votes2,727 | Official input / 1M$0.75 | Output speed51.56 tok/s |
| Rank20 | ModelAN | Source Arena rating1,562.72 | LLMBoard ScoreN/A | Votes12,937 | Official input / 1M$5 | Output speed42.00 tok/s |
| Rank21 | ModelAN | Source Arena rating1,557.29 | LLMBoard ScoreN/A | Votes15,724 | Official input / 1M$5 | Output speed42.00 tok/s |
| Rank22 | ModelXA | Source Arena rating1,555.87 | LLMBoard ScoreN/A | Votes7,361 | Official input / 1M$2 | Output speed80.00 tok/s |
| Rank23 | ModelAN | Source Arena rating1,546.01 | LLMBoard ScoreN/A | Votes18,177 | Official input / 1M$5 | Output speed123.15 tok/s |
| Rank24 | ModelME | Source Arena rating1,541.01 | LLMBoard ScoreN/A | Votes7,378 | Official input / 1M$1.25 | Output speed14.00 tok/s |
| Rank25 | ModelGO | Source Arena rating1,538.37 | LLMBoard ScoreN/A | Votes8,062 | Official input / 1M$0.75 | Output speed62.56 tok/s |
| Rank26 | ModelAN | Source Arena rating1,536.91 | LLMBoard ScoreN/A | Votes8,401 | Official input / 1M$2 | Output speed42.00 tok/s |
| Rank27 | ModelME | Source Arena rating1,534.19 | LLMBoard ScoreN/A | Votes2,065 | Official input / 1M$1.25 | Output speed28.44 tok/s |
| Rank28 | ModelAN | Source Arena rating1,521.49 | LLMBoard ScoreN/A | Votes21,457 | Official input / 1M$3 | Output speed7.67 tok/s |
| Rank29 | ModelBY | Source Arena rating1,521.12 | LLMBoard ScoreN/A | Votes8,617 | Official input / 1MN/A | Output speedN/A |
| Rank30 | ModelOP | Source Arena rating1,519.67 | LLMBoard ScoreN/A | Votes6,834 | Official input / 1M$2 | Output speed99.35 tok/s |
This leaderboard overview compares the source ranking, rating gaps and voting activity.
Use intervals and vote counts to judge how firmly each leaderboard position is supported; source ratings remain separate from the benchmark ranking.
Vendor representation among the top-ranked models in this leaderboard.
A practical summary of the first five entries in this webdev AI model leaderboard, with benchmark evidence and pricing kept in context.
Common questions about the Webdev Leaderboard.
GPT-6-Astra is currently ranked first with 1,797.04 Rating.
The current leaders are GPT-6-Astra (rank #1), Claude Fable 5.1 (rank #2), and Claude Opus 5 (rank #3).
GLM 5.3 Flash has the lowest matched official input price at $0.075 per 1M tokens.
The fastest matched records are GLM 5.3 (472.69 tok/s via FriendliAI), GPT-5.1 (369.03 tok/s via OpenAI), and GPT-5.1 (369.03 tok/s via OpenAI).
No. Source Arena results describe a particular task or preference signal. Capability benchmarks, prices and runtime can produce different rankings.
This source-native ranking follows the original source metric. Benchmark evidence is shown separately and is not substituted for the source result.
This page currently compares 97 models.
A model may not yet have a matching Arena result, or multiple version results may resolve to the same model.
Ranking basisThis webdev AI model leaderboard uses the source Arena rating and rank. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
GPT-6-Astra currently leads the webdev ranking at 1,797.04. Compare evidence coverage, source activity and price separately before choosing a model for production.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.