DeepSeek V4 Flash 0731

hackernews
ARC Prize Verified

DeepSeek V4 Flash 0731

DeepSeek·Jul 31, 2026·3 reasoning variants

At max effort, DeepSeek V4 Flash 0731 scores 89.0% on ARC-AGI-1 Semi-Private at $0.02 per task and 61.4% on ARC-AGI-2 Semi-Private at $0.04 per task.

ARC-AGI 2 leaderboard

DeepSeek V4 Flash 0731

Verified scores

VariantARC-AGI-1ARC-AGI-2ARC-AGI-3
Max
89.0%
61.4%
—
High
87.0%
56.0%
—
Low
84.0%
46.0%
—

Tasks & environments

Pass/fail per reasoning level across each benchmark.

ARC-AGI-2 Public Eval

120 tasks
Task
Max
High
Low
✗✓✗
✓✓✓
✓✓✓
✗✗✗
✗✓✗
✗✗✗
✓✓✓
✓✓✓
✓✗✗
✓✓✓
✓✓✗
✗✗✗
✗✗✗
✓✓✗
✓✓✓
✗✗✗
✗✓✗
✓✗✗
✓✓✗
✗✗✗
✓✓✓
✓✓✗
✗✗✗
✓✓✓
✓✗✗
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✗✗✗
✓✗✗
✓✓✗
✗✗✗
✓✓✓
✓✗✓
✗✓✓
✗✗✗
✗✗✗
✗✗✗
✓✓✓
✗✗✗
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✗✗
✗✗✗
✗✓✗
✓✓✓
✓✓✓
✓✓✓
✓✗✗
✗✗✗
✓✓✗
✓✗✓
✓✓✗
✗✗✗
✓✗✗
✓✓✗
✗✗✓
✗✗✗
✗✗✓
✓✓✗
✗✗✗
✓✓✓
✗✗✗
✗✗✗
✗✗✗
✓✗✓
✓✓✓
✗✗✗
✓✗✗
✓✗✓
✓✓✓
✓✓✓
✓✓✗
✓✗✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✗✗✗
✗✗✗
✓✓✓
✗✓✓
✓✓✓
✓✓✓
✗✗✗
✓✗✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✗✗
✓✓✗
✓✓✗
✗✗✗
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✗
✗✗✗
✗✗✗
✗✓✗
✗✗✗
✗✗✗
✓✓✗
✓✓✓
✓✓✗
✗✓✓
✓✗✗
✗✗✗
✓✓✓
✗✗✗
✗✓✗

ARC-AGI-1 Public Eval

400 tasks
Task
Max
High
Low
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✗
✓✓✓
✓✓✓
✓✓✓
✓✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✗✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✗
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✓
✓✓✓
✓✓✓
✗✓✗
✓✓✗
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✓✓
✗✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✗✓
✓✓✓
✓✗✓
✓✗✓
✓✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✗✓✗
✓✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✗✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓

Source: hackernews

arrow_back Back to News