JamBench - Full-Script Completion (Medium Projects, Claude Code): leaderboard

Metric: L3a runtime pass rate (%): share of generated Godot 4 projects that pass file-integrity and headless compilation checks and then run 30 seconds in headless mode without crashing; Task 2 code completion: 100 benchmark projects with medium code bases (4K to 15K lines), each manually verified playable; all .gd script files are removed and must be rewritten against the kept scenes; Claude Code as the agent harness, iterating with the Godot toolchain; higher is better. Source: arxiv.org. Saturation forecast: Around July 2027. 3 models tracked.

Top models

Interactive version: theaggregate.ai/benchmark?slug=jambench-full-script-completion-medium-projects-claude-code · How It Works · Data refreshed daily, snapshot 2026-09-29.