Gemini 4 Scores Only 78% on FrontierMath Tier 4 as OpenAI Models Near Saturation

FrontierMath Tier 4 is nearly saturated by OpenAI models with GPT-6.1 Sol reaching 100%, while Gemini 4 scored only 78% (±6.5%), falling well short of expectations.

2026-10-19 ~ 2026-10-21 · 2 related posts

• Gemini 4 Scores Just 78% on Saturated FrontierMath Tier 4, Well Behind OpenAI's Models — haider1 · 2026-10-19
• Gemini 4 Scores Just 78% on FrontierMath Tier 4 as OpenAI Models Saturate It — haider1 · 2026-10-21