Astra-max scores 95% on eyebench-v3 at half the cost of Sol-max

Benchmarks shared by adonissingh show Astra-max scoring 95% on eyebench-v3 with roughly 3.8x fewer output tokens, half the cost and nearly double the score of Sol-max. Even at low reasoning intensity, it leads on intelligence per token.

2026-09-05 ~ 2026-09-05 · 3 related posts

• Astra-max hits 95% on eyebench-v3 at half the cost of Sol-max, tokens ~3.8x fewer — adonis_singh · 2026-09-05
• Blogger: Astra-max's eyebench-v3 dominance is 'just not fair' — adonis_singh · 2026-09-05
• Astra-max claims vastly better intelligence-per-token even at low reasoning — adonis_singh · 2026-09-05