gemini-4POST
Code2Video-AA results: Opus 5.5 leads, Gemini 4 Argon catches up
In the Code2Video-AA benchmark, Opus 5.5 tops the list, the GPT-6 family follows closely and Gemini 4 Argon has caught up, prompting a difficulty increase.
Bin Liu
@liu8inArchived 1 day agoOriginally posted 2026.10.27
Bin Liu @liu8inOriginally posted 2026.10.27
really enjoyed working with the AA team on publishing Code2Video-AA Opus 5.5 crowned, GPT-6 family not far behind, Gemini 4 Argon caught-up too. models are getting good at @HyperFrames_ basics time to level-up difficulty 🦾
This post quotes another post: “Artificial Analysis launches Code2Video-AA with Gemini 4 Argon as judge”
x.com/liu8in/status/2114848239958757765Archived 2026.10.27 09:54