JamBench - Function Completion (Large 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 large code bases (over 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 2029. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 12 |
| 2 | GLM-5 | 9 |
| 3 | Gemini 3.1 Pro (Preview) | 7 |
| 4 | GPT-5.4 | 7 |
| 5 | Kimi K2.5 | 5 |
| 6 | Qwen 3.5 397B A17B | 5 |
| 7 | DeepSeek V4 Pro | 4 |
| 8 | Qwen 3.5 27B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=jambench-function-completion-large-projects · How It Works · Data refreshed daily, snapshot 2026-09-29.