GPT-6 Astra beats two specialist models in retrosynthesis prediction
Researchers say GPT-6 Astra outperformed LocalRetro and RetroKNN in single-step retrosynthesis prediction, ranks third overall on the DDDBenchmark, and generated the reaction's 3D visualization in 15 minutes.
GPT-6 Astra⭐️outperformed 2 specialist models (LocalRetro and RetroKNN) in single-step retrosynthesis prediction. Unbelievable result just a month ago! It is the very first general-purpose model outperforming these stong specialists in our benchmark. Kudos to @gdb @joyjiao12 👏 In the #DDDBenchmark, the model ranks 3rd🥉overall, behind only 2 other specialist models including our model and MHNReact by @gklambauer @phseidl , while significantly outperforming all other frontier models (see in thread⬇️). Btw, this synthesis visualization itself was also generated by GPT-6 Astra in just 15 minutes. We will see an explosion of 3D simulations of reactions thanks to models like Astra! 🧵1/2 #insilicoSOTAFM