We finally had a moment to run our system with GPT-5.2 X-High on ARC-AGI-2!
Using the same Poetiq harness as before, we saw results as high as 75% at under $8 / problem using GPT-5.2 X-High on the full PUBLIC-EVAL dataset. This beats the previous SOTA by ~15 percentage points.
There was absolutely no training or model-specific optimization done at Poetiq for GPT-5.2.
Nov 20, 2025 • 4 tweets • 1 min read
Is more intelligence always more expensive? Not necessarily.
Introducing Poetiq. We’ve established a new SOTA and Pareto frontier on @arcprize using Gemini 3 and GPT-5.1.
Read the full analysis and get our code: . poetiq.ai/posts/arcagi_a…