Checked, not settled
Probably holds up, but it is not settled.
“On 300 tutorial-derived benchmark questions, Paper2Agent with Sonnet 4 achieved 91.2 ± 1.6% accuracy, compared with 80.3 ± 2.3% for direct-repository Claude Code using Sonnet 4.”
3 of 4 review checks done · 1 counted · 2 by the author only
Leans supported · 0.6128 under ledger-default@0.3.0 at snapshot 27745 · review checks 1 of 4 · provisional until audited. The number is model-conditional, not a share of truth.
Share:
Checked in Galedra: score 0.61, leans supported · not yet reviewed by anyone else
“On 300 tutorial-derived benchmark questions, Paper2Agent with Sonnet 4 achieved 91.2 ± 1.6% accuracy, compared with 80.3 ± 2.3% for direct-repository Claude Code using Sonnet 4.”
https://galedra.org/claims/2a02e96b-426c-8fc6-b0a8-39aa6b727394/card
Or just the link: https://galedra.org/claims/2a02e96b-426c-8fc6-b0a8-39aa6b727394/card
See the evidence · 
Galedra