Meta and NYU propose h1, a simple Lean proof loop for theorem proving
Overview
Meta and NYU researchers propose h1, a loop that gives a model fast Lean feedback and search tools without imposing a fixed plan, according to a paper reported by Rohan Paul on X. With the same model, h1 solves 598 of 672 PutnamBench problems, against 597 for the hand-built Goedel-Architect, at $1.08 per problem against $1.47. The paper also reports that with Opus 4.8, h1 solves 83 of 100 hard algebra problems, compared with 63 for Claude Code.
Written by AI from the articles below · updated Nov 1, 2:32 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
Rohan Paul@rohanpaul_aiXMeta and NYU paper finds simple Lean loop matches hand-built theorem-proving workflowsAIMeta and NYU researchers present h1, a loop that gives a model fast Lean feedback and search tools without imposing a fixed plan. With the same model, h1 solved 598 of 672 PutnamBench problems against 597 for the hand-built Goedel-Architect, at $1.08 per problem against $1.47. The paper also reports that with Opus 4.8, h1 solved 83 of 100 hard algebra problems, versus 63 for Claude Code.

Heat Trend
- Current comparable heat
- 5
- Peak comparable heat
- 10Nov 1, 3:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.