Understand this story
On November 17, 2026, ARC Prize announced the evaluation results of Inception's Mercury 3 Preview on the ARC-AGI series of benchmarks. It scored 88.5% on ARC-AGI-1 at $0.03 per task; 61.8% on ARC-AGI-2 at $0.06 per task; and 0.2% on ARC-AGI-3 at $299 per task (provider adapter), or 0.1% at $333 per task (standard). ARC Prize stated that this is the first diffusion model it has evaluated; under instant reasoning effort, it averaged 981 output tokens/second on the public ARC-AGI-2 dataset, with a peak of 1,743 tokens/second for a single call, and averaged 500-600 tokens/second with reasoning enabled. ARC Prize also provided links to the leaderboard, reproduction methods, and testing policy.
AI-generated from public reports
Latest development · Report
ARC Prize announces evaluation results of Mercury 3 Preview on ARC-AGIDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 17
ARC PrizeFirst-partySelected
ARC Prize announces evaluation results of Mercury 3 Preview on ARC-AGI
ARC Prize announced the evaluation results of Inception's Mercury 3 Preview on ARC-AGI: ARC-AGI-1 score 88.5%, $0.03 per task; ARC-AGI-2 score 61.8%, $0.06 per task; ARC-AGI-3 score 0.2%, $299 per task (provider adapter) or 0.1%, $333 (standard). This is the first diffusion model evaluated by ARC Prize; under instant reasoning effort it averages 981 output tokens/second on the ARC-AGI-2 public dataset, with a peak of 1,743 tokens/second for a single call; with reasoning enabled it averages 500-600 tokens/second. ARC Prize also provided links to the leaderboard, reproduction method, and testing policy.
AI Trends