GPT-6.1-Sol ranks second on eyebench-v3 at a fraction of the cost

GPT-6.1-Sol ranks second on eyebench-v3, matching near-top performance at about 1/8 the price of Opus-5.5. It is Pareto-optimal on cost and second only to Astra in output token efficiency.

2026-09-30 ~ 2026-09-30 · 3 related posts

• GPT-6.1-Sol Takes #2 on eyebench-v3, ~8x Cheaper Than Opus-5.5 — adonis_singh · 2026-09-30
• Cost Pareto-dominant, but second only to Astra on output-token efficiency — adonis_singh · 2026-09-30

1 near-duplicate retellings: adonis_singh