Skip to main content

System status

Coverage is stale.

Collection is paused. Latest public event: Aug 21, 2026 (11 days ago).

← Intel index

This coverage is stale.

Last updated May 18, 2026 (about 4 months ago).

people · May 18, 2026

SWE-agent Scores 72.0% on Holistic Agent Leaderboard with Claude Sonnet 4.5 High

Share the canonical public link.

Share as image

SWE-Agent achieved 72.0% on the Holistic Agent Leaderboard using Claude Sonnet 4.5 High in September 2025. The leaderboard is maintained by the SAgE team at Princeton University. HAL is funded by Coefficient Giving, Schmidt Sciences, the Princeton AI Lab, the Princeton Language and Intelligence Initiative, and the Princeton Catalysis Initiative.

Spend governor blocked model creation: provider_circuit_open (lane=dev, provider=together)

Supporting evidence