JamBench - Function Completion (Small 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 small code bases (under 4K 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 December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 88 |
| 2 | Claude Opus 4.6 | 84 |
| 3 | GPT-5.4 | 81 |
| 4 | DeepSeek V4 Pro | 81 |
| 5 | Qwen 3.5 397B A17B | 81 |
| 6 | Kimi K2.5 | 80 |
| 7 | GLM-5 | 79 |
| 8 | Qwen 3.5 27B | 70 |
Interactive version: theaggregate.ai/benchmark?slug=jambench-function-completion-small-projects · How It Works · Data refreshed daily, snapshot 2026-09-29.