AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?
Latest release media-v1 — Demo media (v1) · 23 May 2026
2 files for Codex, OpenCode and Claude Code: agentic-vbench AGENTS.md, agentic-vbench CLAUDE.md — 890 tokens loaded in every session.
AGENTS.md A 887 tok CLAUDE.md A 3 tok These files are PhiloLabs/agentic-vbench's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.