LMArena tests Gemini 4 Carbon preview: strong on 3D worlds and creativity, gaps in detail
arena · x · 2026-10-29
LMArena publishes first impressions of Google DeepMind's Gemini 4 Carbon preview. Peter Gostev ran it through a long battery of tasks against Gemini 4 Argon, Claude Opus 5.5, GPT-6.1 Sol, Muse Wonderful, Kimi and DeepSeek.
Highlights:
- 3D world generation: White House, Stonehenge, Golden Gate Bridge prompts; Carbon builds playable 3D games but shows gaps in detail completeness
- Creativity tests: Monet and Van Gogh painting worlds, London through the ages, Istanbul, Harbin ice city
- Visual explainers: how lightning works, John Snow's cholera map
- UI work: ski resort site, ramen ordering page, cross-model comparisons
Verdict: Carbon leads on creativity and 3D generation but falls short on fine detail; the video ends with a full verdict segment.
Related event: Gemini 4 Carbon Preview Tested on LMArena Against Six Rivals(2 posts)→
More from Models
- DeepMind slammed for announcing models weeks before availability amid Gemini Xenon chatter — adonis_singh · 2026-10-29
- Alphabet Q3 call: Gemini Carbon frontier model, MCP apps in Search, AI Mode ads expand — lilyraynyc · 2026-10-29
- gpt-6.1-terra runs 4-hour browser session at ~1 action/second on 10% of quota — prd_008 · 2026-10-29
- AA Index revamp right before Gemini Carbon release raises benchmark timing eyebrows — stablequan · 2026-10-29
- Gemini 4 Carbon debuts #1 on Text Arena, #2 on Agent Arena at 72% less cost — prajdabre · 2026-10-29
- Google mocked for element-named models; unreleased Barium model rumored — andrew_n_carr · 2026-10-29