Back to Home

RiftRunner Blog

Latest insights on AI animation, benchmarks, and cutting-edge technology

4 min read
AI Experiments

One-Prompt Physics: Riftrunner Simulates a 10kg Ball vs 10kg Cotton Drop

With a single prompt, riftrunner on LMArena generated a gravity experiment: a 10kg ball and 10kg cotton falling from 100m. Here’s the video and why this matters for fast science visuals.

#riftrunner#LMArena#Gemini 3
Read more
5 min read
AI Experiments

Riftrunner Cracks a Mate-in-2 Chess Puzzle: Outsmarts Claude 4.5

An unusually hard mate-in-2 chess puzzle forced deep planning before coding. Riftrunner on LMArena crushed the attempt, outperforming Claude 4.5.

#riftrunner#LMArena#Gemini 3
Read more
4 min read
AI Experiments

Riftrunner Clones Cut the Rope in LMArena

Riftrunner on LMArena recreated a Cut the Rope-style mini-game, showing quick game-loop reasoning and tidy code scaffolding.

#riftrunner#LMArena#Gemini 3
Read more
4 min read
AI Experiments

Riftrunner on LMArena: Outstanding Performance (Video Walkthrough)

Riftrunner on LMArena shows outstanding performance. See the full run, learn why Gemini 3 + riftrunner feels sharper, and how to prompt for consistent wins.

#riftrunner#LMArena#Gemini 3
Read more
5 min read
AI Experiments

Gemini 3 + riftrunner on LMArena: 3D Fox Modeling vs SOTA

I asked riftrunner on LMArena to generate a 3D fox and compared it with other state-of-the-art models. Early signal: Gemini 3 + riftrunner shows promising shape fidelity and mesh cleanliness.

#Gemini 3#riftrunner#LMArena
Read more
7 min read
AI Experiments

Hunting for "riftrunner" on LMArena: Gemini 3.0 Rumor + Battle Derivation

Chased the rumor that Gemini 3.0 hides as riftrunner on LMArena. Battle-mode derivation walkthrough on the cosine-power recurrence and why riftrunner felt sharper.

#Gemini 3.0#Riftrunner#LMArena
Read more
5 min read
AI Performance

Gemini 3.0 Pro (Riftrunner) KingBench Performance Analysis

Detailed analysis of Gemini 3.0 Pro (Riftrunner) performance on KingBench AI coding benchmark. Compare with Claude Sonnet 4.5, GPT-4, and other leading AI models.

#AI Benchmarks#Gemini 3.0 Pro#KingBench
Read more