JamBench - Function Completion (Medium Projects): 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; 30 to 50% of function bodies are cleared and must be rewritten; direct generation, the model writes every file in one pass; higher is better. Source: arxiv.org. Saturation forecast: Around February 2028. 8 models tracked.

Top models

#ModelScore
1Claude Opus 4.644
2Kimi K2.543
3Qwen 3.5 397B A17B41
4GPT-5.438
5GLM-537
6DeepSeek V4 Pro34
7Gemini 3.1 Pro (Preview)32
8Qwen 3.5 27B17

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