Do you have any plans to evaluate GPT-6 Astra on representative spatial reasoning benchmarks, such as VSI-Bench and CV-Bench? Given GPT-6 Astra's strong capabilities in spatial understanding and generation, I think it would be very meaningful to systematically assess how far these capabilities extend across established spatial benchmarks.
Do you have any plans to evaluate GPT-6 Astra on representative spatial reasoning benchmarks, such as VSI-Bench and CV-Bench? Given GPT-6 Astra's strong capabilities in spatial understanding and generation, I think it would be very meaningful to systematically assess how far these capabilities extend across established spatial benchmarks.