Web Clone Bench v1 - Gmail: leaderboard

Metric: Full score on the Gmail clone (%). Source: plato.so. Saturation forecast: Around May 2027. 10 models tracked. Updated 18 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Fable 5.2High82.9#1
2Claude Opus 5.5High71.8#6
3Claude Fable 5.1High57.6#17
4GPT-6 AstraxHigh36.1#7
5GPT-6.1 SolMax30.4#12
6Gemini 4 ArgonMedium30.2#14
7Muse WonderHigh23.6#31
8Grok 4.7Low12.4#48
9Muse Spark 1.3Medium8.7#45
10Gemini 3.8 FlashHigh2.4#39

No result here: #2 GPT-6.2 Astra, #3 Gemini 4 Carbon, #10 GPT-6.2 Sol.

Interactive version: theaggregate.ai/benchmark?slug=web-clone-bench-v1-gmail · How It Works · Data refreshed daily, snapshot 2026-11-18.