Skip to main content

System status

Coverage is stale.

Collection is paused. Latest public event: Aug 21, 2026 (10 days ago).

← Intel index

This coverage is stale.

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

product · May 18, 2026

Augment Code Reports 70.6% SWE-Bench Verified Score Using Its Context Engine

Share the canonical public link.

Share as image

MarkTechPost published a ranking on May 15, 2026, that lists Augment Code at 70.6% on SWE-Bench Verified using its own harness and Context Engine. The score reflects Augment's full repository indexing approach that outperformed other frameworks on the same model by 17 problems out of 731 in a February 2026 scaffold comparison. Augment Code offers Team and Enterprise pricing tiers with credit-based consumption for its Context Engine and coding agents.

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

Supporting evidence