MuLA-Bench - German: leaderboard

Metric: Accuracy (%; the 304 German-language questions over both evidence tracks; open-ended questions over in-the-wild long-form recordings (median 36.8 minutes, capped at three hours) in the source language, answered from the full recording without transcripts, audio clipped only to a local model's native input limit; each answer judged correct or not by GPT-5.6 Sol on a route-specific binary rubric with programmatic structural and 3-second timing checks; missing or invalid answers scored wrong). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.

Top models

#ModelScore
1Gemini 3.8 Flash73.7
2Gemini 3.7 Flash73.4
3Gemini 3.1 Pro (Preview)62.5
4Qwen 3.5 Omni Plus57.6
5Qwen3.5 Omni Flash45.7
6Muse Spark 1.239.1

Interactive version: theaggregate.ai/benchmark?slug=mula-bench-german · How It Works · Data refreshed daily, snapshot 2026-09-26.