# Design Arena Agentic Web Dev Elo (Design Arena Agentic Web Dev)

> A display-only Elo rating from blinded comparisons of multi-file web applications built by coding agents.

Canonical page: https://benchlm.ai/benchmarks/designarenaagenticwebdev

- Category: [Agentic](/agentic)
- Last updated: September 10, 2026

## About Design Arena Agentic Web Dev

- Year: 2026
- Tasks: Multi-file web application development
- Format: Elo from blinded human preferences
- Difficulty: Agentic frontend development
- Paper: [Design Arena Web Dev (Agentic) Leaderboard](https://intelligence.ai/leaderboard/webapps)

Design Arena's Agentic Web Dev evaluation compares deployed React applications head to head using real user votes. The harness records long-horizon agent behavior including multi-file changes, tool calls, retries, and failure recovery. BenchLM stores the live Elo and excludes it from weighted scoring.

Design Arena Agentic Web Dev is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Inkling](/models/inkling) | Thinking Machines Lab | 1257 |

## FAQ

### What does Design Arena Agentic Web Dev measure?

A display-only Elo rating from blinded comparisons of multi-file web applications built by coding agents.

### Which model scores highest on Design Arena Agentic Web Dev?

Inkling by Thinking Machines Lab currently leads with a score of 1257 on Design Arena Agentic Web Dev.

### How many models are evaluated on Design Arena Agentic Web Dev?

1 AI models have been evaluated on Design Arena Agentic Web Dev on BenchLM.

### Does Design Arena Agentic Web Dev affect BenchLM's overall score?

Not directly. Design Arena Agentic Web Dev is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.