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.
Related event: GPT-6-Astra tops MathArena leaderboard(2 posts)→
More from Models
- Claude $200 plan delivers 45.3x API value, author denies Anthropic quota cut — RexDouglass · 2026-10-23
- User slams OpenAI's GPT-6.1 Sol: 20 hours lost, ignores human feedback — RexDouglass · 2026-10-23
- Dexmal's open-source VLA model DM0.5 lands in LeRobot, tops RoboColiseum — AdinaYakup · 2026-10-23
- Dev: all open-source audio models today are subpar, even representation ones — A_K_Nain · 2026-10-23
- Codex $200 subscriber burns through a week's quota in 16 hours, suspects silent usage change — zac_attack_ · 2026-10-23
- OpenAI's Tibo Sottiaux confirms a Codex reset is landing tomorrow amid quota complaints — jeppa35 · 2026-10-23