OpenAI GPT-5.6: AI Could Do Anything, Then It Met ARC-AGI-3
The Algorithmic Bridge Alberto Romero ● Covered by 4 sources
OpenAI's GPT-5.6 Sol scored 7.8% on the ARC-AGI-3 benchmark, a test designed to measure fluid intelligence through pattern recognition games that humans solve over 90% of the time. This represents a 20-fold improvement over GPT-5.5's 0.43% score three months earlier, and the model distinguishes itself by correctly identifying game mechanics before execution rather than simply executing learned patterns. The result suggests that further progress toward general intelligence requires improved reasoning scaffolding and planning rather than raw intelligence, since the model's failures occur in multi-step inference composition rather than perception.
Why it matters
GPT-5.6’s ARC-AGI-3 score is scandalously bad and scandalously good