DeepSeek V4 Flash 0731 hits 61.4% on ARC-AGI-2 at $0.04 per task

DeepSeek V4 Flash 0731

DeepSeek submitted V4 Flash 0731 to ARC Prize's verified leaderboard with three reasoning variants. The max-effort variant scores 89.0% on ARC-AGI-1 Semi-Private at $0.02 per task and 61.4% on ARC-AGI-2 at $0.04 per task. The low variant drops to 46% on ARC-AGI-2, showing how much reasoning budget matters. The post does not disclose model size, architecture details, or ARC-AGI-3 results.

Why it matters: DeepSeek submitted V4 Flash 0731 to the ARC Prize leaderboard, hitting 61.4% on ARC-AGI-2 — the highest public score so far — at $0.04 per task. Three inference budgets with scores and costs are provided, making it information-dense. Not scored higher because this is a leaderb...