GPT-6 Astra hits 68.7% on DrugDiscoveryBench, benchmark authors call it a step function
KexinHuang5 · x · 2026-09-16
DrugDiscoveryBench co-author afeyzaakyurek reports that GPT-6 Astra scored 68.7% on their benchmark for early-stage drug discovery computational workflows — described as a step-function jump, with Muse Spark 1.3 and Opus 5 trailing. The authors will host a talk explaining what the benchmark measures. Unverified claim pending details.
More from Models
- V4.1 Flash called the first open model that feels proto-AGI — teortaxesTex · 2026-09-16
- Claude Opus 5's PRs proactively confess every mistake made while coding — repligate · 2026-09-16
- Six efficiency breakthroughs labs didn't see coming upend semiconductor demand assumptions — bookwormengr · 2026-09-16
- A common jailbreak: third-person role-play gradually blurs lines to widen the model's Overton window — BlancheMinerva · 2026-09-16
- cocktail-peanut predicts Jev will go open weights, seeing more potential locally than as an API — cocktailpeanut · 2026-09-16
- Speculation mounts OpenAI's mysterious 'new model' is a fresh pretrain, not an RL run — teortaxesTex · 2026-09-16