AI Trends

ARC Prize announces GPT-6.2 Astra's results on the ARC-AGI series of benchmarks

ARC PrizeUpdated Nov 18 02:31

AI summary

ARC Prize announced OpenAI GPT-6.2 Astra's results on the ARC-AGI series of benchmarks: ARC-AGI-3 reached 100.0% (SOTA), at a cost of $4.1K (provider adapter), and 70.3% at $24.2K in standard mode; ARC-AGI-2 scored 95.8% (SOTA) at $0.50 per task; ARC-AGI-1 scored 98.5% at $0.17 per task. ARC Prize stated that this is the first model to achieve a 100% score on ARC-AGI-3. Compared with Sol's best ARC-AGI-3 result of 98.2% under high reasoning, Astra is 1.8 percentage points higher under max reasoning, but costs 64% more. On the 25 public ARC-AGI-3 games, Astra used 64.1% fewer actions than the human baseline and 5.2% fewer than GPT-6 Astra.

Why read this

SelectedAI score 78

ARC Prize announced the scores and costs of GPT-6.2 Astra on the three ARC-AGI benchmarks, and provided an item-by-item comparison with Sol and previous generations.

Topics

Tags

Body

@OpenAI Join ARC Prize @ NeurIPS 2026 on Sat, Dec 12, 6-9 PM in Atlanta for a rooftop happy hour across from the convention center. Space is limited and registration requires approval: https://t.co/1cdZppwijd

Source

ARC Prize