New generation's jump equals 100x tokens on old model, like four generations in the o1-to-GPT-5 era
tobyordoxford · x · 2026-09-14
In a thread with ramez on inference-time scaling, tobyordoxford notes the new generation's jump equals what the old model would achieve with 100x more tokens. The log-scaling slope itself hasn't improved, but the between-generation jump is huge — comparable to four generations in the o1→o3→GPT-5 era. He also cites his rule of thumb: each 10x more RLVR data cut required tokens by 3x.
More from Models
- ARC Prize 2026 closes in 3 days as Yi-Chia Chen tops ARC-AGI-3 at 75.56% — GregKamradt · 2026-10-31
- Fable 5.5 Max stuns with gorgeous SVG of a pelican riding a bicycle, headed to Claude Code — ChrisGPT · 2026-10-31
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- NVIDIA Nemotron 3.5 scales LLM self-verification, +9-10 points on agentic benchmarks — sarahcat21 · 2026-10-31
- Mistral Large 4 scores 94% on 1,273 USMLE-style questions but flips 44 at temp 0 — MaziyarPanahi · 2026-10-31
- Researchers find 5 personality structures in LLM weight space, Big Five-like — luke_drago_ · 2026-10-31