benchmark evidence
WebDev Arena
Arena.ai WebDev / Code Arena frontier coding preference leaderboard.
winner on WebDev Arena
direct benchmark result, not a broad vertical composite | source row dated 2026-07-10
scored on 2026-07-10
latest mapped results | top 20
| # | Model | Score | Evidence | Tested |
|---|---|---|---|---|
| 1 | Anthropic: Claude Opus 4.7 | 100.0 | model-only independent_benchmark | 2026-07-10 |
| 2 | Anthropic: Claude Opus 4.6 | 100.0 | model-only independent_benchmark | 2026-07-10 |
| 3 | Anthropic: Claude Sonnet 4.6 | 100.0 | model-only independent_benchmark | 2026-07-10 |
| 4 | Anthropic: Claude Opus 4.5 | 91.5 | model-only independent_benchmark | 2026-07-10 |
| 5 | DeepSeek: DeepSeek V4 Pro | 86.5 | model-only independent_benchmark | 2026-07-10 |
| 6 | Z.ai: GLM 5 | 82.6 | model-only independent_benchmark | 2026-07-10 |
| 7 | OpenAI: GPT-5.2 | 76.3 | model-only independent_benchmark | 2026-07-10 |
| 8 | OpenAI: GPT-5.4 Mini | 74.3 | model-only independent_benchmark | 2026-07-10 |
| 9 | OpenAI: GPT-5.4 | 73.1 | model-only independent_benchmark | 2026-07-10 |
| 10 | Anthropic: Claude Sonnet 4.5 | 71.5 | model-only independent_benchmark | 2026-07-10 |
| 11 | OpenAI: GPT-5.1 | 59.9 | model-only independent_benchmark | 2026-07-10 |
| 12 | DeepSeek: DeepSeek V3.2 | 58.0 | model-only independent_benchmark | 2026-07-10 |
| 13 | Anthropic: Claude Haiku 4.5 | 56.6 | model-only independent_benchmark | 2026-07-10 |
| 14 | Google: Gemini 2.5 Pro | 26.1 | model-only independent_benchmark | 2026-07-10 |
what this result means
Arena.ai WebDev / Code Arena frontier coding preference leaderboard.
This benchmark contributes direct public evidence. Read its scope before generalizing the result.
A win here is a win on WebDev Arena. Broad task pages require independent corroboration before naming a general winner.
source record
category: coding
metric: accuracy
matched models: 14
latest source date: 2026-07-10
direction: higher is better