Post-Cutoff.com
  1. Home
  2. Timeline
  3. 2024
  4. OpenAI announces o3, scoring 75.7–87.5% on ARC-AGI

OpenAI announces o3, scoring 75.7–87.5% on ARC-AGI

★★★★★benchmarkOpenAIARC Prizeconfidence: high

On the last day of its '12 Days of OpenAI', OpenAI previewed o3, which scored 75.7% on the ARC-AGI semi-private set (87.5% with high compute) — a benchmark on which earlier LLMs scored in single digits — and 25.2% on FrontierMath.

Key facts

What happened

Only three months after o1, OpenAI showed that scaling RL and test-time compute produced another large leap in reasoning.

Why it matters

Convinced many observers that reasoning models were on a steep trajectory; ARC Prize called it a genuine step-change.

Changelog

  • 2026-09-29: created

Related events

  1. OpenAI o1: reasoning models trained with reinforcement learning ★★★★★
  2. OpenAI o3 scores 25% on FrontierMath research-level maths benchmark, amid funding disclosure controversy ★★★
  3. OpenAI launches GPT-5 ★★★★★

Sources (2)

id: 2024-12-20-openai-o3 · updated 2026-09-29 · open in the interactive timeline