# Landmark Arena leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/external-landmark-arena

Every model the catalog carries a published Landmark Arena value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Relative rating fitted to human pairwise votes |
| Tasks | 20 famous landmarks built as three.js web pages, rated by human votes |
| Difficulty | 3D scenes in browser code |
| Published by | [BenchLM](https://benchlm.ai/benchmarks/landmark-arena) |

Kaggle's Landmark Arena has models build 20 famous landmarks, including the Seven Wonders of the Ancient World, as single-page three.js web apps, and people vote for the better scene.

## Landmark Arena ranking

13 models with a published Landmark Arena value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Relative rating fitted to human pairwise votes | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 1788 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 1751 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | 1699 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 1610 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 1604 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Gemini 4 Carbon](https://modelscale.dev/models/gemini-4-carbon) | Google | 1574 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 1482 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 1481 | Observed 2026-11-21 · source benchlm:models |
| 9 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 1423 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 1408 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 1361 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | 1315 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | 1157 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
