ARC Prize Verified

GPT-5.6 Terra

OpenAI·Jul 9, 2026·5 reasoning variants

GPT-5.6 Terra is the middle tier model of the GPT-5.6 family averaging 2.3% on Public and 0.80% on ARC-AGI-3 Semi-Private. Notably, more reasoning effort does not help it: `xhigh` performed worse than `max` reasoning, signaling that its ceiling is a comprehension/planning limitation rather than a budget one.

Related models: GPT-5.6 Sol, GPT-5.6 Luna

ARC-AGI 3 leaderboard

GPT-5.6 Terra

Verified scores

VariantARC-AGI-1ARC-AGI-2ARC-AGI-3
Max
96.5%
83.9%
0.8%
Extra High
94.0%
74.2%
0.7%
High
92.0%
67.1%
0.5%
Medium
77.0%
37.5%
0.1%
Low
60.2%
18.8%
0.0%

Tasks & environments

Pass/fail per reasoning level across each benchmark. Hardest tasks (fewest levels solving) are listed first.

ARC-AGI-3 Public Demo

25 environments

ARC-AGI-2 Public Eval

120 tasks
Task
Max
Extra High
High
Medium
Low

ARC-AGI-1 Public Eval

400 tasks
Task
Max
Extra High
High
Medium
Low