boogiebench — leaderboard
Elo-ranked LLM music-composition arena where text models write Strudel JavaScript compositions from music prompts and users vote on the generated tracks.
Metric: Elo Rating. Source: www.boogiebench.com. Status: saturation imminent. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 1694 |
| 2 | GPT-5.2 | 1656 |
| 3 | Claude Sonnet 4.5 | 1617 |
| 4 | Claude Opus 4.5 | 1610 |
| 5 | Claude Opus 4.6 | 1598 |
| 6 | GPT-5.4 | 1570 |
| 7 | GPT-5 | 1500 |
| 8 | DeepSeek V3.1 Terminus | 1455 |
| 9 | Kimi K2 0905 | 1441 |
| 10 | Gemini 2.5 Pro | 1435 |
| 11 | GLM-4.6 | 1426 |
| 12 | GPT-OSS-120B | 1397 |
| 13 | MiniMax-M2 | 1382 |
Interactive version: theaggregate.ai/benchmark?slug=boogiebench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.