SLDBench v2: Claude Opus 5.5 beats classic fits using 4% of compute budget
jiqizhixin · x · 2026-11-16
Researchers from CUHK-Shenzhen, HKU, Tsinghua, Peking University and collaborators introduce SLDBench v2 (arXiv preprint) to benchmark active scaling-law discovery: agents see a catalog of experiments with prices, choose which results to buy, refine candidate laws, and decide when to stop. The environment replays recorded training runs at original compute cost and validates predictions on hidden larger-scale experiments. Claude Opus 5.5 reaches median R² 0.570 using just 4.01% of the pool's historical compute, beating the classic reference law fitted on all data (0.455). Across 30 tasks, all eight evaluated systems degrade when forced to actively select experiments versus receiving all outcomes — cheap observations can leave key assumptions untested.
More from Models
- Grok Bot 1.0 lands with bots that join meetings, take initiative and self-improve — mattyp · 2026-11-16
- Leaked 'Fable 5.5' / 'Model 4' is likely a new Claude pricing tier, not a new model — lyraxana · 2026-11-16
- Parakeet Adds a Phantom Full Stop Every 30-Second Window, Silently Truncating Transcripts — shauntrennery · 2026-11-16
- It's only Monday and my weekly AI usage quota is nearly gone — gefei55 · 2026-11-16
- Alibaba says Qwen4-Max training data filtered to weaken offensive cyber and CBRN risks — terryyuezhuo · 2026-11-16
- Qwen4 Max jumps 9 points on Intelligence Index while cutting task costs 67% — 141_1337 · 2026-11-16