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:
- Muse-Spark 1.3 scored 33%, marginally better than its predecessor
- Gemini-3.8-Flash scored the same as its previous version
The author is also hoping for Astra results soon. A minor third-party eval update, but a useful data point for cross-model comparison.
More from Models
- OpenAI officially launches GPT-6 Astra with new announcement page — Mxmtm · 2026-09-04
- GPT-6 Astra system card: CoT control jumps to 60.9%, model can evade monitors — rohanpaul_ai · 2026-09-04
- Greenblatt: GPT-6 Astra's opaque reasoning could end chain-of-thought oversight — RyanGreenblatt · 2026-09-04
- OpenAI launches GPT-6 Astra: 99.9% on ARC-AGI-3, state-of-the-art computer use — mervenoyann · 2026-09-04
- OpenAI release cadence compressing: GPT-5.4 to Astra in just ~2 months — msg · 2026-09-04
- GPT-6 Astra now available in Microsoft Foundry as frontier work model — DanWahlin · 2026-09-04