WHAT NEW IN X10.31 SAT

AI collections from X · 22 collections · 63,169 posts

Back to No.020 DeepSeek V4.1 Flash hands-on tests and comparisonsUpdated 2 hours ago
deepseek-v4.1POST

motionbench animation benchmark: Opus 5.5 leads, GPT-6.1 Sol and DeepSeek V4.1 Flash within margin

The open motionbench benchmark scores seven models frame by frame on animation, with Claude Opus 5.5 first and GPT-6.1 Sol and DeepSeek V4.1 Flash within its margin.

Coral Bricks AI
@coralbricks_aiArchived 12 days agoOriginally posted 2026.10.19
Coral Bricks AI @coralbricks_aiOriginally posted 2026.10.19
Open original on X

Today we're releasing motionbench, an open benchmark that asks AI models to animate and measures every frame they produce. Across seven models, Claude Opus 5.5 leads, with GPT-6.1 Sol and DeepSeek V4.1 Flash within its margin. Full results in the thread: https://x.com/coralbricksdev/status/2111978020382949458

This post quotes another post: x.com/coralbricksdev/status/2111978020382949458

x.com/coralbricks_ai/status/2111979992028524840Archived 2026.10.19 12:01
Open original on X