MuLA-Bench - Factual: leaderboard

Factual and completeness questions in MuLA-Bench (Yang et al., 2026), a benchmark of open-ended questions over long in-the-wild recordings, answered from the audio alone, asking for single facts, full lists or several required details from spoken content or natural sounds. Each answer is judged correct or wrong by GPT-5.6 Sol against the reference with rubric and timing checks; accuracy in percent, higher is better.

Metric: Accuracy (%; the 1,891 factual and completeness questions (single facts, exhaustive lists, multi-slot answers) over both 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 February 2027. 10 models tracked.

Top models

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=mula-bench-factual · How It Works · Data refreshed daily, snapshot 2026-11-12.