sonnet-5.5VIDEO
Four models compared on the same Mario video prompt
GPT Astra, GPT-6.1 Sol, Sonnet 5.5 and Opus 5.5 were given the exact same prompt to generate Mario videos, comparing the results and the large spread in cost.
Luckey Faraday
@luckeyfaradayArchived 2026.10.04Originally posted 2026.10.04
Luckey Faraday @luckeyfaradayOriginally posted 2026.10.04
Took the Mario test one step further. GPT Astra, GPT-6.1 Sol, Sonnet 5.5 and Opus 5.5, all on the exact same prompt. Really interesting results here, especially considering the massive spread in cost. Which one wins? OpenAI or Anthropic?
This post quotes another post: x.com/luckeyfaraday/status/2105451767987061170
x.com/luckeyfaraday/status/2106558072370196921Archived 2026.10.04 10:01