Gemini 4 Argon Tops CrusaderBench, Beating Opus 5.5 at Strategy Gaming
Hesamation · x · 2026-10-14
Hesamation tested Gemini 4 Argon on CrusaderBench, a benchmark measuring how well models grow an economy in Stronghold Crusader (strategic reasoning, planning, computer and tool use). Argon ranked 1st, beating Opus 5.5, and praised the benchmark's design. Early notes: Opus is a strong strategic player; Sonnet and Haiku were surprisingly lazy and idle too early; GPT models consistently good; Kimi used buildings well. Some results still need reruns to filter noise.
Related event: Gemini 4 Argon Tops DIY CrusaderBench Strategy Game Benchmark(5 posts)→
More from Models
- Rejected by NeurIPS: study shows a single test-set replica beats uncontaminated irreducible error — RylanSchaeffer · 2026-10-15
- New SWE-bench Multimodal leaderboard: Claude Opus 5.5 leads at 70.21% on visual bugs — OfirPress · 2026-10-15
- Google says Gemini 4 Argon is delivering breakthroughs in quantum computing, fusion and protein design — GoogleDeepMind · 2026-10-15
- Google sits down with Sergey Brin to discuss Gemini 4 Argon and the road ahead — OfficialLoganK · 2026-10-15
- ChatGPT quietly makes GPT-6.1 Sol the default, users report sharper voice chats — shaunralston · 2026-10-15
- The small-model world has changed forever, but the builder community hasn't priced it in — tokenbender · 2026-10-15