Grok Image 2 + Seedance 2.0 + Opus 5
Prompt ↓
Advanced Frontier LLM Coding Benchmark 2 14.08.2026
Models: - Opus 5 Max - Claude Code (App) - Qwen 3.8 Max - Qwen-Code (CLI) - GLM 5.3 Max - Zcode (App) - GPT 5.6 Sol Ultra - Codex (App) Task: Ferrofluid: Rising towards metaball surface + magnet cursor
Today I made a photorealistic horror sim from scratch
I never made a video game before. instead of only using opus 5, I asked fable to be the orchestrator, with opus subagents as builders. inspired by mattshumer_, 0xRishi and Ryancampbell play it here:
I tested GLM 5.3 on the same tasks I used for the other models yesterday.
For complex animated 3D design, it is still far behind Kimi K3 and Opus 5. The lack of vision is still a real limitation here. It is also very slow, even slower than GLM 5.2. The same test took Opus,
You have reached the end of the archive
All of Claude Opus 5