Gemini 4 Neon leads MazeBench on uncached token efficiency by a wide margin
patience_cave · x · 2026-11-20
Blogger patiencecave says Gemini 4 Neon solves MazeBench puzzles at a remarkable rate, far ahead on uncached input tokens—meaning far less exploration time before submitting long solution chains—making it the cost-efficiency frontier. A log-scale chart shows Neon finishing most exploration around 100K uncached tokens, while claude-fable-5-2 and gpt-6.2-astra need tens of millions.
More from Models
- Meta's Muse AI, 10M+ downloads, hit by new privacy breaches including bank balances — karmay007 · 2026-11-20
- Datalab shows ParseBench is gameable: a 650M model hit near the top with a few RL steps — VikParuchuri · 2026-11-20
- GPT-6.2 Astra matches predecessor's MazeBench score at $225 vs $840 — patience_cave · 2026-11-20
- MazeBench: GPT-6.2 Sol narrows gap with Astra but still scores less at same price — patience_cave · 2026-11-20
- MazeBench: GPT-6.2 Astra tops at 16% while costing 25% of its predecessor — patience_cave · 2026-11-20
- NeuroVL medical VLM trained on 1M neuroimaging studies claims to beat OpenAI and Google models — Dr_Alex_Crimi · 2026-11-20