eyebench author says no v4, moving on to harder benchmarks
adonis_singh · x · 2026-09-05
adonissingh says he won't build a v4 of eyebench and will move on to harder benchmarks. The post implies eyebench-v3 is his own benchmark, the source of the earlier Astra-max 95% claim.
More from Models
- No usage reset on GPT-6 Astra launch day, developer calls out OpenAI — tobowers · 2026-09-05
- Debate: Models Fuzzily Recall Concepts, Not Text — SAE Features vs Edit-Distance Memorization — voooooogel · 2026-09-05
- Blogger feeds GPT6 Astra a PPT template, gets 30 conference slides with the right avatar — vista8 · 2026-09-05
- Dozens of GPT-6 Astra prompts collected via GPT 6 pro web search — vista8 · 2026-09-05
- Tencent Hunyuan Hy4 preview: 770B total/49B active, 1M context, Apache 2.0, day-0 vLLM — aftahi_ai · 2026-09-05
- Astra Draws Stunning Illustrations Stroke by Stroke, Not Generated — Tolopono · 2026-09-05