Leak: OpenAI internal model 'bel' reportedly solves ~2.5x more math problems than astra
imjustnewatai · x · 2026-09-09
An unverified leak claims OpenAI's internal model 'bel' is a full generation ahead of astra: roughly 2.5x as many problems solved at similar compute on its published math test, with even bel's lowest compute setting beating astra's highest. OpenAI also reportedly reports record internal benchmark performance, with training ongoing. The author expects stronger reasoning and coding, though how broadly the math jump generalizes remains open.
More from Models
- Zuckerberg: Meta already training post-Watermelon models on its 1GW Prometheus cluster — rohanpaul_ai · 2026-09-09
- Dev Pushes Back on Astra Hype: Being Good at Blender Isn't an AGI Benchmark — carsonfarmer · 2026-09-09
- Meta's Muse Spark 1.3 Max lands #8 on Code Arena: WebDev, reshaping the price-performance frontier — arena · 2026-09-09
- Aidan Gomez: labs train on rewritten user data even under ZDR promises — josh_wills · 2026-09-09
- Open problems turned into RL environments: benchmarks and RL envs are two sides of the same coin — burny_tech · 2026-09-09
- ChatGPT $200 plan 'unusable': two GPT-6 xHigh chats burn the quota in 2-3 days — ChrisGPT · 2026-09-09