S

Scale

SCALEbuyer room · privateManage buyer room

SWE-Bench Pro coding-agent benchmark: 1,865 tasks across 41 professional repos (public set = 731 GPL-repo instances, free via GitHub; private 276, held-out 858) + leaderboard; front for Scale's expert human-labeled training-data / RL-environment / eval business

Buyer room

Sample, licence terms, pricing and eval results for Scale.

Get notified as soon as Scale publishes. Until then, discover alternatives today with a 7-day trial.

  • Downloadable sample
  • Licence terms
  • Price band
  • Eval results
  • Direct contact
Start 7-day trial →