Published full-model reference, then measured local recipes. BF16 on Asus gx10-e789 and DGX Spark spark-5c2f is a desk plan only — Not run yet, not MEASURED.
Recipe by benchmark scores. Published reference is not a rank. Blank cells have no cite.
The published full-model reference is the top row — or the dashed gold tick on Graphic — not rank #1. A blank cell, missing tick, or missing bead has no recorded cite. Scores are never invented.
500 human-verified repository issues. Public-comparable headline for repo software engineering. Agent and harness belong on the cite.
Scoring & limits
swe-bench-verified · sample size not reported
This is the source’s reported aggregate. Its metric, agent configuration, and evaluation protocol determine how it should be interpreted. Read the original grading definition before comparing completion rates across setups.