eyebench-v3 adds Muse-Spark 1.3 at 33%, Gemini-3.8-Flash flat vs predecessor

adonis_singh · x · 2026-09-04

The community benchmark eyebench-v3 added two new results:

The author is also hoping for Astra results soon. A minor third-party eval update, but a useful data point for cross-model comparison.

Original post →

More from Models

Models channel →