# Landing Page Arena

> Kaggle's Landing Page Arena has models build a one-page website for a small business from a client brief, and people vote for the better page.

Canonical page: https://benchlm.ai/benchmarks/landing-page-arena

- Category: [external](/external)
- Last updated: Latest evaluation November 12, 2026

Evaluation results published by [Kaggle](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena). undefined

A page qualifies only if it is self-contained, works on desktop and phone, and includes the information the brief requires. Kaggle shows two anonymous outputs for the same prompt and a person picks the better one. The Arena column is the relative rating Kaggle fits to those votes, published with an interval; it is not a percentage.

The rating moves as votes arrive, and Kaggle publishes no confidence level for its interval. Rows with few votes have wide intervals, so neighbouring models are often not separable. Voters are self-selected Kaggle visitors. The board declares no license; we keep published aggregates with attribution and no task or output contents.

A rating gap smaller than the two rows' intervals is not a reliable difference.

- [Kaggle arena leaderboard](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena)
- [Published leaderboard data](https://www.kaggle.com/api/v1/benchmarks/kaggle/landing-page-arena/leaderboard)

## About Landing Page Arena

- Year: 2026
- Tasks: 12 client briefs for small-business landing pages, rated by human votes
- Format: Relative rating fitted to human pairwise votes
- Difficulty: Marketing page design and copy

A page qualifies only if it is self-contained, works on desktop and phone, and includes the information the brief requires. Kaggle shows two anonymous outputs for the same prompt and a person picks the better one. The Arena column is the relative rating Kaggle fits to those votes, published with an interval; it is not a percentage. These results are display-only and do not enter overall or category rankings.

Landing Page Arena is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (14 source rows)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [GPT-6.1 Sol](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Max Reasoning; 124 votes; ±113; Evaluated 2026-11-12 | — | 1691 |
| 2 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Max Reasoning; 129 votes; ±111; Evaluated 2026-11-12 | — | 1668 |
| 3 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Max Reasoning; 85 votes; ±116; Evaluated 2026-11-12 | — | 1574 |
| 4 | [Qwen 3.8 Max](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Xhigh Reasoning; 107 votes; ±111; Evaluated 2026-11-12 | — | 1563 |
| 5 | [Kimi K3](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Max Reasoning; 38 votes; ±138; Evaluated 2026-11-12 | — | 1560 |
| 6 | [Claude Fable 5.1](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Max Reasoning; 128 votes; ±108; Evaluated 2026-11-12 | — | 1551 |
| 7 | [Deepseek V4.1 Flash](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | High Reasoning; 100 votes; ±112; Evaluated 2026-11-12 | — | 1479 |
| 8 | [GLM-5.3](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Max Reasoning; 132 votes; ±108; Evaluated 2026-11-12 | — | 1477 |
| 9 | [Gemini 4 Carbon](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | High Reasoning; 73 votes; ±118; Evaluated 2026-11-12 | — | 1473 |
| 10 | [Claude Sonnet 5](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | 126 votes; ±109; Evaluated 2026-11-12 | — | 1417 |
| 11 | [Grok 4.7](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Xhigh Reasoning; 107 votes; ±112; Evaluated 2026-11-12 | — | 1411 |
| 12 | [Grok 4.6](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | Xhigh Reasoning; 120 votes; ±110; Evaluated 2026-11-12 | — | 1403 |
| 13 | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | High Reasoning; 119 votes; ±110; Evaluated 2026-11-12 | — | 1393 |
| 14 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/kaggle/landing-page-arena) | High Reasoning; 116 votes; ±112; Evaluated 2026-11-12 | — | 1340 |

## FAQ

### What does Landing Page Arena measure?

Kaggle's Landing Page Arena has models build a one-page website for a small business from a client brief, and people vote for the better page.

### Which source row has the highest reported Landing Page Arena value?

GPT-6.1 Sol has the highest reported Landing Page Arena value at 1691. A rating gap smaller than the two rows' intervals is not a reliable difference.

### How many models are evaluated on Landing Page Arena?

The Latest evaluation November 12, 2026 contains 14 AI models.

### Does Landing Page Arena affect BenchLM's overall score?

Not directly. Landing Page Arena is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.