Meta Muse Spark 1.3 takes #2 on ProgramBench at rock-bottom cost

jyangballin · x · 2026-09-30

ProgramBench's author announces results for Meta Muse Spark 1.3: on a benchmark where a SWE-agent must write whole programs (sqlite, ffmpeg, php) from scratch, 1.3 (max) ranks #2 overall and 1.3 (xhigh) #3, at remarkable cost tiers—"intelligence too cheap to meter." Detailed profiles and trajectories are open-sourced.

Related event: Meta Muse Spark 1.3 Ranks Second on ProgramBench with Open Evaluation Data(2 posts)→

Original post →

More from coding & agent

coding & agent channel →