GPT-6 Astra reportedly scores 3% on FrontierMath Erdős, spending $220K in compute
haider1 · x · 2026-09-05
Unconfirmed report: GPT-6 "Astra" scored 3% on FrontierMath Erdős while every other tested model (Fable 5.1, Fable 5, 5.6 Sol, 5.5) scored 0%. Across repeated attempts Astra eventually solved 5 of 68 open problems, but at a compute cost of over $220,000.
Related event: Epoch AI Launches FrontierMath Erdős; GPT-6 Astra First to Break Zero(10 posts)→
More from Models
- Opus 5.5 tops OpenRouter spending in 20 of 29 task categories — mmurph · 2026-10-21
- Meta team builds open-source 30B LLM from scratch in months, hails 'second era' — TimDarcet · 2026-10-21
- DFlash drafter for Muse Glimmer-30B: 5 layers, blockwise 16-token spec decoding — TimDarcet · 2026-10-21
- EvoPress quantization shrinks 30B model from 56GB to 19GB at near-bf16 accuracy — TimDarcet · 2026-10-21
- Radar chart: Muse Glimmer-30B benchmarked against Gemma4-31B and Qwen3.6-27B — TimDarcet · 2026-10-21
- Privacy evals: Muse Glimmer-30B leaks less than Qwen3.6-27B on CIMemories — TimDarcet · 2026-10-21