Model compare
City Scroll Journey
Compare the same prompt across GPT-6 Astra.
Missing runs for deepseek-v4-flash, KimiK3, gpt-sol-5-6-high on this benchmark.
OpenAI
Model compare
Compare the same prompt across GPT-6 Astra.
Missing runs for deepseek-v4-flash, KimiK3, gpt-sol-5-6-high on this benchmark.
OpenAI