gemini-4IMAGE
Gemini 4 Argon scores 78% on FrontierMath Tier 4, user reports
A user reports Gemini 4 Argon scoring 78% on FrontierMath Tier 4, and says its claimed progress on a random Erdős problem was mostly incorrect, making it hard to use for research math.
Leeham
@Liam06972452Archived 22 days agoOriginally posted 2026.10.15
Leeham @Liam06972452Originally posted 2026.10.15
Gemini 4 Argon scores 78% on Frontiermath Tier 4 which isn't great. I tried a random Erdos problem with the model in which it claimed to make substantial progress, however it was mostly incorrect. I don't think this model can realistically be used for research math.
x.com/liam06972452/status/2110507498977550365Archived 2026.10.15 11:25