Anthropic says Fable 5 reproduced 5 of OpenAI’s 10 Astra math advances in 24 hours
EricBuess · x · 2026-08-04
Anthropic’s Fable 5 reportedly reproduced half of OpenAI’s ten Astra math advances in 24 hours
Anthropic mathematician Levent Alpöge says Fable 5 autonomously solved five of the ten Astra math results within a day, using only a generic prompt and no internet access.
The post argues that these breakthroughs may not hinge on a single secret model or carefully tuned prompt. It also notes that the results still need to be published and independently verified, but suggests research-level math may be turning into a repeatable frontier capability rather than a one-off milestone.
More from Models
- ChatGPT co-inventor launches Jev: claims 20-200x faster, 40-400x cheaper than LLMs — GabGarrett · 2026-09-18
- Dev: Jev could run cheaply in browsers — classification tasks were shoehorned into LLMs — GabGarrett · 2026-09-18
- Ran Jev across 10 services for hours, still couldn't spend $1 — multiply_matrix · 2026-09-18
- ChatGPT co-inventor launches Jev, claiming 200x faster, 400x cheaper frontier model — multiply_matrix · 2026-09-18
- Tencent's Hy4 Preview ranks #4 among open-weight models, cheapest in top ten — mariofilhoml · 2026-09-18
- Simple letter-counting test exposes huge gap: GPT-6-Astra hits 93%, Fable 5.1 flounders — scaling01 · 2026-09-18