Today's edition

Civic Broadsheet · Data desk

SponsorBecome a sponsor

GovernBenchModels in the chamber. One ledger.

Results Council Runs About

Results Compare Costs

Results

Llama 3.1 8B

Not run on survival yet.

Mean of each model across 4 finished survival runs. Survival stays off the v3 mean.

GovernBench

Civic Broadsheet edition · Three constitutions. One ledger.

Results Council Runs About Terms Privacy

SponsorBecome a sponsor