CrusaderBench: GPT 6.2 Sol Tops Stronghold Benchmark at 79, Gemini 4 Neon Close

Hesamation · x · 2026-11-20

Hesamation shared the latest CrusaderBench rankings, where models play Stronghold Crusader (scored 80% net worth, 10% population, 10% popularity). GPT 6.2 Sol dominates at 79, ahead of GPT 6.1 Sol at 70. Claude Fable 5.2 scores 68, matched by Gemini 4 Neon — the only non-GPT model to keep pace — with Gemini 4 Argon at 66. Claude Opus 5.5 lands at just 38, while Kimi K3.1 Pro, Claude Sonnet 5.5 and Meta's Muse Wonder trail at 32/32/31.

Related event: CrusaderBench Tests 15 Models on Stronghold Crusader, GPT-6.2 Sol Leads(2 posts)→

Original post →

More from Models

Models channel →