PostTrainBench Lite Released
xennygrimmato_ · x · 2026-07-10
PostTrainBench has released a Lite version. According to reports, the Lite version extracts 12 combinations from the full PostTrainBench suite: {Qwen3-4B-Base, Qwen3-1.7B-Base, SmolLM3-3B-Base} × {AIME 2025, BFCL, GSM8K, HumanEval}.
Additionally, the Lite version reduces the evaluation time limit from 10 hours to 5 hours, serving as a lightweight adjustment to the original benchmark for faster evaluations.
More from Research
- NSA's Mike O'Hara: AI Puts Math Research Progress on 'Fruit Fly Years' — AlexKontorovich · 2026-07-21
- Cell study: localized PD-1 engineered T cells reduce brain inflammation in mice — EricTopol · 2026-07-21
- Linear Digressions returns with a new season of audio essays on AI agents — ChrisGPotts · 2026-07-21
- A forecasting lesson on why R-squared alone led to overfitting and worse predictions — mdancho84 · 2026-07-21
- Google DeepMind’s Project Genie talk shows how creatives feed into model research — alexanderchen · 2026-07-21
- Nat Lambert says RL distillation does not use the strongest models as teachers — natolambert · 2026-07-21