GPT-6-Astra takes first on MathArena with 90% expected performance, using just 12k tokens per question

scaling01 · x · 2026-09-06

GPT-6-Astra claims first place on MathArena with a massive 90% expected performance. The model is also notably token-efficient, averaging only 12k tokens per question on BrokenArXiv and ArXivMath.

Original post →

More from Models

Models channel →