JamBench - Theme and Description Generation (Claude Code): leaderboard
JamBench (2026) tests project-level game programming on the Godot engine with real Game Jam projects; outputs are checked deterministically in headless mode, and the board is the percentage of projects that compile and then run for 30 seconds without crashing. Here the model builds a complete 2D game from a jam theme plus a gameplay description, working inside the Claude Code agent harness; higher is better.
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 1b: the jam theme plus a gameplay description; 50 real Game Jam themes, three runs each; the model writes a complete 2D Godot 4 project from scratch; Claude Code as the agent harness, iterating with the Godot toolchain; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 80 | #102 |
| 2 | Kimi K2.5 | 77.3 | #256 |
| 3 | DeepSeek V4 Pro | 76.7 | #188 |
| 4 | GLM-5 | 73.3 | #260 |
| 5 | Qwen 3.5 397B A17B | 68.7 | #246 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=jambench-theme-and-description-generation-claude-code · How It Works · Data refreshed daily, snapshot 2026-11-13.