Logistic fits: OpenAI 50% horizon ~6 hours, 80% horizon just 15 minutes
BasilHalperin · x · 2026-11-09
BasilHalperin details Method 2 — fitting logistic distributions to the success curves and reading off fitted horizons: 50% success time horizon 6 hours (63-day doubling), 80% only 15 minutes (86-day doubling), 25% 143 hours, 90% 5 minutes.
Takeaway: the 80% horizon is low in level but rising very quickly. Alex Barry4 notes one should fit curves to the success rates themselves rather than empirical p80, and that the early p80 gap was an artifact of bin coverage.
More from Models
- Artificial Analysis launches Decision Index v2 with 45% private data and calibration-based scoring — ArtificialAnlys · 2026-11-09
- GLM-4.5 Hit #1 on Hugging Face Within 48 Hours of MIT-Licensed Release — ccerrato147 · 2026-11-09
- Has any LLM release ever been decidedly worse than its predecessor? — adonis_singh · 2026-11-09
- CEOs say Google's Argon stands out for writing, calling Google the AI dark horse — danshipper · 2026-11-09
- Epoch AI adds ECI scores, projects Gemini 3 Pro time horizon at 4.9 hours — CFGeek · 2026-11-09
- Infosec researcher maps 3 low-hanging abuse paths for open-weight models — matthew_d_green · 2026-11-09